Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
1) Remove a duplicated call to skb_orphan() in pf_key, from Cong Wang.

2) Prepare xfrm and pf_key for algorithms without pf_key support,
   from Jussi Kivilinna.

3) Fix an unbalanced lock in xfrm_output_one(), from Li RongQing.

4) Add an IPsec state resolution packet queue to handle
   packets that are send before the states are resolved.

5) xfrm4_policy_fini() is unused since 2.6.11, time to remove it.
   From Michal Kubecek.

6) The xfrm gc threshold was configurable just in the initial
   namespace, make it configurable in all namespaces. From
   Michal Kubecek.

7) We currently can not insert policies with mark and mask
   such that some flows would be matched from both policies.
   Allow this if the priorities of these policies are different,
   the one with the higher priority is used in this case.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 425 insertions, 39 deletions

diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 3be0ac2c192..9a459be24af 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -262,21 +262,56 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static struct ctl_table_header *sysctl_hdr;
-#endif
-
-static void __init xfrm4_policy_init(void)
+static int __net_init xfrm4_net_init(struct net *net)
 {
-	xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = xfrm4_policy_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL);
+		if (!table)
+			goto err_alloc;
+
+		table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh;
+	}
+
+	hdr = register_net_sysctl(net, "net/ipv4", table);
+	if (!hdr)
+		goto err_reg;
+
+	net->ipv4.xfrm4_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
 }
 
-static void __exit xfrm4_policy_fini(void)
+static void __net_exit xfrm4_net_exit(struct net *net)
 {
-#ifdef CONFIG_SYSCTL
-	if (sysctl_hdr)
-		unregister_net_sysctl_table(sysctl_hdr);
+	struct ctl_table *table;
+
+	if (net->ipv4.xfrm4_hdr == NULL)
+		return;
+
+	table = net->ipv4.xfrm4_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->ipv4.xfrm4_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+static struct pernet_operations __net_initdata xfrm4_net_ops = {
+	.init	= xfrm4_net_init,
+	.exit	= xfrm4_net_exit,
+};
 #endif
-	xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
+
+static void __init xfrm4_policy_init(void)
+{
+	xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
 }
 
 void __init xfrm4_init(void)
@@ -286,8 +321,7 @@ void __init xfrm4_init(void)
 	xfrm4_state_init();
 	xfrm4_policy_init();
 #ifdef CONFIG_SYSCTL
-	sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4",
-					 xfrm4_policy_table);
+	register_pernet_subsys(&xfrm4_net_ops);
 #endif
 }
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 12827374433..4ef7bdb6544 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -320,7 +320,51 @@ static struct ctl_table xfrm6_policy_table[] = {
 	{ }
 };
 
-static struct ctl_table_header *sysctl_hdr;
+static int __net_init xfrm6_net_init(struct net *net)
+{
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = xfrm6_policy_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL);
+		if (!table)
+			goto err_alloc;
+
+		table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh;
+	}
+
+	hdr = register_net_sysctl(net, "net/ipv6", table);
+	if (!hdr)
+		goto err_reg;
+
+	net->ipv6.sysctl.xfrm6_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+static void __net_exit xfrm6_net_exit(struct net *net)
+{
+	struct ctl_table *table;
+
+	if (net->ipv6.sysctl.xfrm6_hdr == NULL)
+		return;
+
+	table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+static struct pernet_operations xfrm6_net_ops = {
+	.init	= xfrm6_net_init,
+	.exit	= xfrm6_net_exit,
+};
 #endif
 
 int __init xfrm6_init(void)
@@ -339,8 +383,7 @@ int __init xfrm6_init(void)
 		goto out_policy;
 
 #ifdef CONFIG_SYSCTL
-	sysctl_hdr = register_net_sysctl(&init_net, "net/ipv6",
-					 xfrm6_policy_table);
+	register_pernet_subsys(&xfrm6_net_ops);
 #endif
 out:
 	return ret;
@@ -352,8 +395,7 @@ out_policy:
 void xfrm6_fini(void)
 {
 #ifdef CONFIG_SYSCTL
-	if (sysctl_hdr)
-		unregister_net_sysctl_table(sysctl_hdr);
+	unregister_pernet_subsys(&xfrm6_net_ops);
 #endif
 	xfrm6_policy_fini();
 	xfrm6_state_fini();
diff --git a/net/key/af_key.c b/net/key/af_key.c
index cc2630ac806..7b3ba32ca67 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -203,7 +203,6 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
 	}
 	if (*skb2 != NULL) {
 		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
-			skb_orphan(*skb2);
 			skb_set_owner_r(*skb2, sk);
 			skb_queue_tail(&sk->sk_receive_queue, *skb2);
 			sk->sk_data_ready(sk, (*skb2)->len);
@@ -816,18 +815,21 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x,
 	sa->sadb_sa_auth = 0;
 	if (x->aalg) {
 		struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
-		sa->sadb_sa_auth = a ? a->desc.sadb_alg_id : 0;
+		sa->sadb_sa_auth = (a && a->pfkey_supported) ?
+					a->desc.sadb_alg_id : 0;
 	}
 	sa->sadb_sa_encrypt = 0;
 	BUG_ON(x->ealg && x->calg);
 	if (x->ealg) {
 		struct xfrm_algo_desc *a = xfrm_ealg_get_byname(x->ealg->alg_name, 0);
-		sa->sadb_sa_encrypt = a ? a->desc.sadb_alg_id : 0;
+		sa->sadb_sa_encrypt = (a && a->pfkey_supported) ?
+					a->desc.sadb_alg_id : 0;
 	}
 	/* KAME compatible: sadb_sa_encrypt is overloaded with calg id */
 	if (x->calg) {
 		struct xfrm_algo_desc *a = xfrm_calg_get_byname(x->calg->alg_name, 0);
-		sa->sadb_sa_encrypt = a ? a->desc.sadb_alg_id : 0;
+		sa->sadb_sa_encrypt = (a && a->pfkey_supported) ?
+					a->desc.sadb_alg_id : 0;
 	}
 
 	sa->sadb_sa_flags = 0;
@@ -1138,7 +1140,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 	if (sa->sadb_sa_auth) {
 		int keysize = 0;
 		struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth);
-		if (!a) {
+		if (!a || !a->pfkey_supported) {
 			err = -ENOSYS;
 			goto out;
 		}
@@ -1160,7 +1162,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 	if (sa->sadb_sa_encrypt) {
 		if (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP) {
 			struct xfrm_algo_desc *a = xfrm_calg_get_byid(sa->sadb_sa_encrypt);
-			if (!a) {
+			if (!a || !a->pfkey_supported) {
 				err = -ENOSYS;
 				goto out;
 			}
@@ -1172,7 +1174,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 		} else {
 			int keysize = 0;
 			struct xfrm_algo_desc *a = xfrm_ealg_get_byid(sa->sadb_sa_encrypt);
-			if (!a) {
+			if (!a || !a->pfkey_supported) {
 				err = -ENOSYS;
 				goto out;
 			}
@@ -1578,13 +1580,13 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig,
 	struct sadb_msg *hdr;
 	int len, auth_len, enc_len, i;
 
-	auth_len = xfrm_count_auth_supported();
+	auth_len = xfrm_count_pfkey_auth_supported();
 	if (auth_len) {
 		auth_len *= sizeof(struct sadb_alg);
 		auth_len += sizeof(struct sadb_supported);
 	}
 
-	enc_len = xfrm_count_enc_supported();
+	enc_len = xfrm_count_pfkey_enc_supported();
 	if (enc_len) {
 		enc_len *= sizeof(struct sadb_alg);
 		enc_len += sizeof(struct sadb_supported);
@@ -1615,6 +1617,8 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig,
 			struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i);
 			if (!aalg)
 				break;
+			if (!aalg->pfkey_supported)
+				continue;
 			if (aalg->available)
 				*ap++ = aalg->desc;
 		}
@@ -1634,6 +1638,8 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig,
 			struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i);
 			if (!ealg)
 				break;
+			if (!ealg->pfkey_supported)
+				continue;
 			if (ealg->available)
 				*ap++ = ealg->desc;
 		}
@@ -2825,6 +2831,8 @@ static int count_ah_combs(const struct xfrm_tmpl *t)
 		const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i);
 		if (!aalg)
 			break;
+		if (!aalg->pfkey_supported)
+			continue;
 		if (aalg_tmpl_set(t, aalg) && aalg->available)
 			sz += sizeof(struct sadb_comb);
 	}
@@ -2840,6 +2848,9 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 		if (!ealg)
 			break;
 
+		if (!ealg->pfkey_supported)
+			continue;
+
 		if (!(ealg_tmpl_set(t, ealg) && ealg->available))
 			continue;
 
@@ -2848,6 +2859,9 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 			if (!aalg)
 				break;
 
+			if (!aalg->pfkey_supported)
+				continue;
+
 			if (aalg_tmpl_set(t, aalg) && aalg->available)
 				sz += sizeof(struct sadb_comb);
 		}
@@ -2871,6 +2885,9 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 		if (!aalg)
 			break;
 
+		if (!aalg->pfkey_supported)
+			continue;
+
 		if (aalg_tmpl_set(t, aalg) && aalg->available) {
 			struct sadb_comb *c;
 			c = (struct sadb_comb*)skb_put(skb, sizeof(struct sadb_comb));
@@ -2903,6 +2920,9 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 		if (!ealg)
 			break;
 
+		if (!ealg->pfkey_supported)
+			continue;
+
 		if (!(ealg_tmpl_set(t, ealg) && ealg->available))
 			continue;
 
@@ -2911,6 +2931,8 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
 			const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k);
 			if (!aalg)
 				break;
+			if (!aalg->pfkey_supported)
+				continue;
 			if (!(aalg_tmpl_set(t, aalg) && aalg->available))
 				continue;
 			c = (struct sadb_comb*)skb_put(skb, sizeof(struct sadb_comb));
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index f9a54955474..6fb9d00a75d 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -35,6 +35,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AES_GCM_ICV8,
 		.sadb_alg_ivlen = 8,
@@ -51,6 +53,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AES_GCM_ICV12,
 		.sadb_alg_ivlen = 8,
@@ -67,6 +71,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AES_GCM_ICV16,
 		.sadb_alg_ivlen = 8,
@@ -83,6 +89,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AES_CCM_ICV8,
 		.sadb_alg_ivlen = 8,
@@ -99,6 +107,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AES_CCM_ICV12,
 		.sadb_alg_ivlen = 8,
@@ -115,6 +125,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AES_CCM_ICV16,
 		.sadb_alg_ivlen = 8,
@@ -131,6 +143,8 @@ static struct xfrm_algo_desc aead_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_NULL_AES_GMAC,
 		.sadb_alg_ivlen = 8,
@@ -151,6 +165,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_AALG_NULL,
 		.sadb_alg_ivlen = 0,
@@ -169,6 +185,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_AALG_MD5HMAC,
 		.sadb_alg_ivlen = 0,
@@ -187,6 +205,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_AALG_SHA1HMAC,
 		.sadb_alg_ivlen = 0,
@@ -205,6 +225,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_AALG_SHA2_256HMAC,
 		.sadb_alg_ivlen = 0,
@@ -222,6 +244,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_AALG_SHA2_384HMAC,
 		.sadb_alg_ivlen = 0,
@@ -239,6 +263,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_AALG_SHA2_512HMAC,
 		.sadb_alg_ivlen = 0,
@@ -257,6 +283,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_AALG_RIPEMD160HMAC,
 		.sadb_alg_ivlen = 0,
@@ -274,6 +302,8 @@ static struct xfrm_algo_desc aalg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_AALG_AES_XCBC_MAC,
 		.sadb_alg_ivlen = 0,
@@ -295,6 +325,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id =	SADB_EALG_NULL,
 		.sadb_alg_ivlen = 0,
@@ -313,6 +345,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_EALG_DESCBC,
 		.sadb_alg_ivlen = 8,
@@ -331,6 +365,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_EALG_3DESCBC,
 		.sadb_alg_ivlen = 8,
@@ -349,6 +385,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_CASTCBC,
 		.sadb_alg_ivlen = 8,
@@ -367,6 +405,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_BLOWFISHCBC,
 		.sadb_alg_ivlen = 8,
@@ -385,6 +425,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AESCBC,
 		.sadb_alg_ivlen = 8,
@@ -403,6 +445,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_SERPENTCBC,
 		.sadb_alg_ivlen = 8,
@@ -421,6 +465,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_CAMELLIACBC,
 		.sadb_alg_ivlen = 8,
@@ -439,6 +485,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_TWOFISHCBC,
 		.sadb_alg_ivlen = 8,
@@ -456,6 +504,8 @@ static struct xfrm_algo_desc ealg_list[] = {
 		}
 	},
 
+	.pfkey_supported = 1,
+
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AESCTR,
 		.sadb_alg_ivlen	= 8,
@@ -473,6 +523,7 @@ static struct xfrm_algo_desc calg_list[] = {
 			.threshold = 90,
 		}
 	},
+	.pfkey_supported = 1,
 	.desc = { .sadb_alg_id = SADB_X_CALG_DEFLATE }
 },
 {
@@ -482,6 +533,7 @@ static struct xfrm_algo_desc calg_list[] = {
 			.threshold = 90,
 		}
 	},
+	.pfkey_supported = 1,
 	.desc = { .sadb_alg_id = SADB_X_CALG_LZS }
 },
 {
@@ -491,6 +543,7 @@ static struct xfrm_algo_desc calg_list[] = {
 			.threshold = 50,
 		}
 	},
+	.pfkey_supported = 1,
 	.desc = { .sadb_alg_id = SADB_X_CALG_LZJH }
 },
 };
@@ -714,27 +767,27 @@ void xfrm_probe_algs(void)
 }
 EXPORT_SYMBOL_GPL(xfrm_probe_algs);
 
-int xfrm_count_auth_supported(void)
+int xfrm_count_pfkey_auth_supported(void)
 {
 	int i, n;
 
 	for (i = 0, n = 0; i < aalg_entries(); i++)
-		if (aalg_list[i].available)
+		if (aalg_list[i].available && aalg_list[i].pfkey_supported)
 			n++;
 	return n;
 }
-EXPORT_SYMBOL_GPL(xfrm_count_auth_supported);
+EXPORT_SYMBOL_GPL(xfrm_count_pfkey_auth_supported);
 
-int xfrm_count_enc_supported(void)
+int xfrm_count_pfkey_enc_supported(void)
 {
 	int i, n;
 
 	for (i = 0, n = 0; i < ealg_entries(); i++)
-		if (ealg_list[i].available)
+		if (ealg_list[i].available && ealg_list[i].pfkey_supported)
 			n++;
 	return n;
 }
-EXPORT_SYMBOL_GPL(xfrm_count_enc_supported);
+EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
 
 #if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE)
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 3670526e70b..bcfda8921b5 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -64,7 +64,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 
 		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
-			goto error_nolock;
+			goto error;
 		}
 
 		err = xfrm_state_check_expire(x);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 6c9aa642a2b..5b47180986f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -35,6 +35,10 @@
 
 #include "xfrm_hash.h"
 
+#define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10))
+#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
+#define XFRM_MAX_QUEUE_LEN	100
+
 DEFINE_MUTEX(xfrm_cfg_mutex);
 EXPORT_SYMBOL(xfrm_cfg_mutex);
 
@@ -51,7 +55,7 @@ static struct kmem_cache *xfrm_dst_cache __read_mostly;
 static void xfrm_init_pmtu(struct dst_entry *dst);
 static int stale_bundle(struct dst_entry *dst);
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
-
+static void xfrm_policy_queue_process(unsigned long arg);
 
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
@@ -287,8 +291,11 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
 		INIT_HLIST_NODE(&policy->byidx);
 		rwlock_init(&policy->lock);
 		atomic_set(&policy->refcnt, 1);
+		skb_queue_head_init(&policy->polq.hold_queue);
 		setup_timer(&policy->timer, xfrm_policy_timer,
 				(unsigned long)policy);
+		setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process,
+			    (unsigned long)policy);
 		policy->flo.ops = &xfrm_policy_fc_ops;
 	}
 	return policy;
@@ -309,6 +316,16 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
 }
 EXPORT_SYMBOL(xfrm_policy_destroy);
 
+static void xfrm_queue_purge(struct sk_buff_head *list)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(list)) != NULL) {
+		dev_put(skb->dev);
+		kfree_skb(skb);
+	}
+}
+
 /* Rule must be locked. Release descentant resources, announce
  * entry dead. The rule must be unlinked from lists to the moment.
  */
@@ -319,6 +336,9 @@ static void xfrm_policy_kill(struct xfrm_policy *policy)
 
 	atomic_inc(&policy->genid);
 
+	del_timer(&policy->polq.hold_timer);
+	xfrm_queue_purge(&policy->polq.hold_queue);
+
 	if (del_timer(&policy->timer))
 		xfrm_pol_put(policy);
 
@@ -562,6 +582,46 @@ static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s
 	return 0;
 }
 
+static void xfrm_policy_requeue(struct xfrm_policy *old,
+				struct xfrm_policy *new)
+{
+	struct xfrm_policy_queue *pq = &old->polq;
+	struct sk_buff_head list;
+
+	__skb_queue_head_init(&list);
+
+	spin_lock_bh(&pq->hold_queue.lock);
+	skb_queue_splice_init(&pq->hold_queue, &list);
+	del_timer(&pq->hold_timer);
+	spin_unlock_bh(&pq->hold_queue.lock);
+
+	if (skb_queue_empty(&list))
+		return;
+
+	pq = &new->polq;
+
+	spin_lock_bh(&pq->hold_queue.lock);
+	skb_queue_splice(&list, &pq->hold_queue);
+	pq->timeout = XFRM_QUEUE_TMO_MIN;
+	mod_timer(&pq->hold_timer, jiffies);
+	spin_unlock_bh(&pq->hold_queue.lock);
+}
+
+static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
+				   struct xfrm_policy *pol)
+{
+	u32 mark = policy->mark.v & policy->mark.m;
+
+	if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
+		return true;
+
+	if ((mark & pol->mark.m) == pol->mark.v &&
+	    policy->priority == pol->priority)
+		return true;
+
+	return false;
+}
+
 int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 {
 	struct net *net = xp_net(policy);
@@ -569,7 +629,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct xfrm_policy *delpol;
 	struct hlist_head *chain;
 	struct hlist_node *entry, *newpos;
-	u32 mark = policy->mark.v & policy->mark.m;
 
 	write_lock_bh(&xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
@@ -578,7 +637,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	hlist_for_each_entry(pol, entry, chain, bydst) {
 		if (pol->type == policy->type &&
 		    !selector_cmp(&pol->selector, &policy->selector) &&
-		    (mark & pol->mark.m) == pol->mark.v &&
+		    xfrm_policy_mark_match(policy, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			if (excl) {
@@ -603,8 +662,10 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	net->xfrm.policy_count[dir]++;
 	atomic_inc(&flow_cache_genid);
 	rt_genid_bump(net);
-	if (delpol)
+	if (delpol) {
+		xfrm_policy_requeue(delpol, policy);
 		__xfrm_policy_unlink(delpol, dir);
+	}
 	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
 	hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
 	policy->curlft.add_time = get_seconds();
@@ -1115,11 +1176,15 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
 		__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
 	}
-	if (old_pol)
+	if (old_pol) {
+		if (pol)
+			xfrm_policy_requeue(old_pol, pol);
+
 		/* Unlinking succeeds always. This is the only function
 		 * allowed to delete or replace socket policy.
 		 */
 		__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
+	}
 	write_unlock_bh(&xfrm_policy_lock);
 
 	if (old_pol) {
@@ -1310,6 +1375,8 @@ static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *f
 		 * It means we need to try again resolving. */
 		if (xdst->num_xfrms > 0)
 			return NULL;
+	} else if (dst->flags & DST_XFRM_QUEUE) {
+		return NULL;
 	} else {
 		/* Real bundle */
 		if (stale_bundle(dst))
@@ -1673,6 +1740,171 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	return xdst;
 }
 
+static void xfrm_policy_queue_process(unsigned long arg)
+{
+	int err = 0;
+	struct sk_buff *skb;
+	struct sock *sk;
+	struct dst_entry *dst;
+	struct net_device *dev;
+	struct xfrm_policy *pol = (struct xfrm_policy *)arg;
+	struct xfrm_policy_queue *pq = &pol->polq;
+	struct flowi fl;
+	struct sk_buff_head list;
+
+	spin_lock(&pq->hold_queue.lock);
+	skb = skb_peek(&pq->hold_queue);
+	dst = skb_dst(skb);
+	sk = skb->sk;
+	xfrm_decode_session(skb, &fl, dst->ops->family);
+	spin_unlock(&pq->hold_queue.lock);
+
+	dst_hold(dst->path);
+	dst = xfrm_lookup(xp_net(pol), dst->path, &fl,
+			  sk, 0);
+	if (IS_ERR(dst))
+		goto purge_queue;
+
+	if (dst->flags & DST_XFRM_QUEUE) {
+		dst_release(dst);
+
+		if (pq->timeout >= XFRM_QUEUE_TMO_MAX)
+			goto purge_queue;
+
+		pq->timeout = pq->timeout << 1;
+		mod_timer(&pq->hold_timer, jiffies + pq->timeout);
+		return;
+	}
+
+	dst_release(dst);
+
+	__skb_queue_head_init(&list);
+
+	spin_lock(&pq->hold_queue.lock);
+	pq->timeout = 0;
+	skb_queue_splice_init(&pq->hold_queue, &list);
+	spin_unlock(&pq->hold_queue.lock);
+
+	while (!skb_queue_empty(&list)) {
+		skb = __skb_dequeue(&list);
+
+		xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
+		dst_hold(skb_dst(skb)->path);
+		dst = xfrm_lookup(xp_net(pol), skb_dst(skb)->path,
+				  &fl, skb->sk, 0);
+		if (IS_ERR(dst)) {
+			dev_put(skb->dev);
+			kfree_skb(skb);
+			continue;
+		}
+
+		nf_reset(skb);
+		skb_dst_drop(skb);
+		skb_dst_set(skb, dst);
+
+		dev = skb->dev;
+		err = dst_output(skb);
+		dev_put(dev);
+	}
+
+	return;
+
+purge_queue:
+	pq->timeout = 0;
+	xfrm_queue_purge(&pq->hold_queue);
+}
+
+static int xdst_queue_output(struct sk_buff *skb)
+{
+	unsigned long sched_next;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
+	struct xfrm_policy_queue *pq = &xdst->pols[0]->polq;
+
+	if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) {
+		kfree_skb(skb);
+		return -EAGAIN;
+	}
+
+	skb_dst_force(skb);
+	dev_hold(skb->dev);
+
+	spin_lock_bh(&pq->hold_queue.lock);
+
+	if (!pq->timeout)
+		pq->timeout = XFRM_QUEUE_TMO_MIN;
+
+	sched_next = jiffies + pq->timeout;
+
+	if (del_timer(&pq->hold_timer)) {
+		if (time_before(pq->hold_timer.expires, sched_next))
+			sched_next = pq->hold_timer.expires;
+	}
+
+	__skb_queue_tail(&pq->hold_queue, skb);
+	mod_timer(&pq->hold_timer, sched_next);
+
+	spin_unlock_bh(&pq->hold_queue.lock);
+
+	return 0;
+}
+
+static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
+						 struct dst_entry *dst,
+						 const struct flowi *fl,
+						 int num_xfrms,
+						 u16 family)
+{
+	int err;
+	struct net_device *dev;
+	struct dst_entry *dst1;
+	struct xfrm_dst *xdst;
+
+	xdst = xfrm_alloc_dst(net, family);
+	if (IS_ERR(xdst))
+		return xdst;
+
+	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 ||
+	    (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP))
+		return xdst;
+
+	dst1 = &xdst->u.dst;
+	dst_hold(dst);
+	xdst->route = dst;
+
+	dst_copy_metrics(dst1, dst);
+
+	dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
+	dst1->flags |= DST_HOST | DST_XFRM_QUEUE;
+	dst1->lastuse = jiffies;
+
+	dst1->input = dst_discard;
+	dst1->output = xdst_queue_output;
+
+	dst_hold(dst);
+	dst1->child = dst;
+	dst1->path = dst;
+
+	xfrm_init_path((struct xfrm_dst *)dst1, dst, 0);
+
+	err = -ENODEV;
+	dev = dst->dev;
+	if (!dev)
+		goto free_dst;
+
+	err = xfrm_fill_dst(xdst, dev, fl);
+	if (err)
+		goto free_dst;
+
+out:
+	return xdst;
+
+free_dst:
+	dst_release(dst1);
+	xdst = ERR_PTR(err);
+	goto out;
+}
+
 static struct flow_cache_object *
 xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 		   struct flow_cache_object *oldflo, void *ctx)
@@ -1751,7 +1983,7 @@ make_dummy_bundle:
 	/* We found policies, but there's no bundles to instantiate:
 	 * either because the policy blocks, has no transformations or
 	 * we could not build template (no xfrm_states).*/
-	xdst = xfrm_alloc_dst(net, family);
+	xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family);
 	if (IS_ERR(xdst)) {
 		xfrm_pols_put(pols, num_pols);
 		return ERR_CAST(xdst);
@@ -2359,6 +2591,9 @@ static int xfrm_bundle_ok(struct xfrm_dst *first)
 	    (dst->dev && !netif_running(dst->dev)))
 		return 0;
 
+	if (dst->flags & DST_XFRM_QUEUE)
+		return 1;
+
 	last = NULL;
 
 	do {