7 files changed, 4494 insertions, 0 deletions

diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
new file mode 100644
index 00000000000..58ca6a972c4
--- /dev/null
+++ b/net/xfrm/Kconfig
@@ -0,0 +1,12 @@
+#
+# XFRM configuration
+#
+config XFRM_USER
+	tristate "IPsec user configuration interface"
+	depends on INET && XFRM
+	---help---
+	  Support for IPsec user configuration interface used
+	  by native Linux tools.
+
+	  If unsure, say Y.
+
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
new file mode 100644
index 00000000000..693aac1aa83
--- /dev/null
+++ b/net/xfrm/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the XFRM subsystem.
+#
+
+obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_input.o xfrm_algo.o
+obj-$(CONFIG_XFRM_USER) += xfrm_user.o
+
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
new file mode 100644
index 00000000000..080aae243ce
--- /dev/null
+++ b/net/xfrm/xfrm_algo.c
@@ -0,0 +1,729 @@
+/* 
+ * xfrm algorithm interface
+ *
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option) 
+ * any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pfkeyv2.h>
+#include <linux/crypto.h>
+#include <net/xfrm.h>
+#if defined(CONFIG_INET_AH) || defined(CONFIG_INET_AH_MODULE) || defined(CONFIG_INET6_AH) || defined(CONFIG_INET6_AH_MODULE)
+#include <net/ah.h>
+#endif
+#if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE)
+#include <net/esp.h>
+#endif
+#include <asm/scatterlist.h>
+
+/*
+ * Algorithms supported by IPsec.  These entries contain properties which
+ * are used in key negotiation and xfrm processing, and are used to verify
+ * that instantiated crypto transforms have correct parameters for IPsec
+ * purposes.
+ */
+static struct xfrm_algo_desc aalg_list[] = {
+{
+	.name = "digest_null",
+	
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 0,
+			.icv_fullbits = 0,
+		}
+	},
+	
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_NULL,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 0,
+		.sadb_alg_maxbits = 0
+	}
+},
+{
+	.name = "md5",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 128,
+		}
+	},
+	
+	.desc = {
+		.sadb_alg_id = SADB_AALG_MD5HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 128
+	}
+},
+{
+	.name = "sha1",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 160,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_AALG_SHA1HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 160
+	}
+},
+{
+	.name = "sha256",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 256,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_SHA2_256HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 256,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+	.name = "ripemd160",
+
+	.uinfo = {
+		.auth = {
+			.icv_truncbits = 96,
+			.icv_fullbits = 160,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_X_AALG_RIPEMD160HMAC,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 160
+	}
+},
+};
+
+static struct xfrm_algo_desc ealg_list[] = {
+{
+	.name = "cipher_null",
+	
+	.uinfo = {
+		.encr = {
+			.blockbits = 8,
+			.defkeybits = 0,
+		}
+	},
+	
+	.desc = {
+		.sadb_alg_id =	SADB_EALG_NULL,
+		.sadb_alg_ivlen = 0,
+		.sadb_alg_minbits = 0,
+		.sadb_alg_maxbits = 0
+	}
+},
+{
+	.name = "des",
+
+	.uinfo = {
+		.encr = {
+			.blockbits = 64,
+			.defkeybits = 64,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_EALG_DESCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 64,
+		.sadb_alg_maxbits = 64
+	}
+},
+{
+	.name = "des3_ede",
+
+	.uinfo = {
+		.encr = {
+			.blockbits = 64,
+			.defkeybits = 192,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_EALG_3DESCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 192,
+		.sadb_alg_maxbits = 192
+	}
+},
+{
+	.name = "cast128",
+
+	.uinfo = {
+		.encr = {
+			.blockbits = 64,
+			.defkeybits = 128,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_CASTCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 40,
+		.sadb_alg_maxbits = 128
+	}
+},
+{
+	.name = "blowfish",
+
+	.uinfo = {
+		.encr = {
+			.blockbits = 64,
+			.defkeybits = 128,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_BLOWFISHCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 40,
+		.sadb_alg_maxbits = 448
+	}
+},
+{
+	.name = "aes",
+
+	.uinfo = {
+		.encr = {
+			.blockbits = 128,
+			.defkeybits = 128,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_AESCBC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
+{
+        .name = "serpent",
+
+        .uinfo = {
+                .encr = {
+                        .blockbits = 128,
+                        .defkeybits = 128,
+                }
+        },
+
+        .desc = {
+                .sadb_alg_id = SADB_X_EALG_SERPENTCBC,
+                .sadb_alg_ivlen = 8,
+                .sadb_alg_minbits = 128,
+                .sadb_alg_maxbits = 256,
+        }
+},
+{
+        .name = "twofish",
+                 
+        .uinfo = {
+                .encr = {
+                        .blockbits = 128,
+                        .defkeybits = 128,
+                }
+        },
+
+        .desc = {
+                .sadb_alg_id = SADB_X_EALG_TWOFISHCBC,
+                .sadb_alg_ivlen = 8,
+                .sadb_alg_minbits = 128,
+                .sadb_alg_maxbits = 256
+        }
+},
+};
+
+static struct xfrm_algo_desc calg_list[] = {
+{
+	.name = "deflate",
+	.uinfo = {
+		.comp = {
+			.threshold = 90,
+		}
+	},
+	.desc = { .sadb_alg_id = SADB_X_CALG_DEFLATE }
+},
+{
+	.name = "lzs",
+	.uinfo = {
+		.comp = {
+			.threshold = 90,
+		}
+	},
+	.desc = { .sadb_alg_id = SADB_X_CALG_LZS }
+},
+{
+	.name = "lzjh",
+	.uinfo = {
+		.comp = {
+			.threshold = 50,
+		}
+	},
+	.desc = { .sadb_alg_id = SADB_X_CALG_LZJH }
+},
+};
+
+static inline int aalg_entries(void)
+{
+	return ARRAY_SIZE(aalg_list);
+}
+
+static inline int ealg_entries(void)
+{
+	return ARRAY_SIZE(ealg_list);
+}
+
+static inline int calg_entries(void)
+{
+	return ARRAY_SIZE(calg_list);
+}
+
+/* Todo: generic iterators */
+struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id)
+{
+	int i;
+
+	for (i = 0; i < aalg_entries(); i++) {
+		if (aalg_list[i].desc.sadb_alg_id == alg_id) {
+			if (aalg_list[i].available)
+				return &aalg_list[i];
+			else
+				break;
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(xfrm_aalg_get_byid);
+
+struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id)
+{
+	int i;
+
+	for (i = 0; i < ealg_entries(); i++) {
+		if (ealg_list[i].desc.sadb_alg_id == alg_id) {
+			if (ealg_list[i].available)
+				return &ealg_list[i];
+			else
+				break;
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(xfrm_ealg_get_byid);
+
+struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id)
+{
+	int i;
+
+	for (i = 0; i < calg_entries(); i++) {
+		if (calg_list[i].desc.sadb_alg_id == alg_id) {
+			if (calg_list[i].available)
+				return &calg_list[i];
+			else
+				break;
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(xfrm_calg_get_byid);
+
+static struct xfrm_algo_desc *xfrm_get_byname(struct xfrm_algo_desc *list,
+					      int entries, char *name,
+					      int probe)
+{
+	int i, status;
+
+	if (!name)
+		return NULL;
+
+	for (i = 0; i < entries; i++) {
+		if (strcmp(name, list[i].name))
+			continue;
+
+		if (list[i].available)
+			return &list[i];
+
+		if (!probe)
+			break;
+
+		status = crypto_alg_available(name, 0);
+		if (!status)
+			break;
+
+		list[i].available = status;
+		return &list[i];
+	}
+	return NULL;
+}
+
+struct xfrm_algo_desc *xfrm_aalg_get_byname(char *name, int probe)
+{
+	return xfrm_get_byname(aalg_list, aalg_entries(), name, probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_aalg_get_byname);
+
+struct xfrm_algo_desc *xfrm_ealg_get_byname(char *name, int probe)
+{
+	return xfrm_get_byname(ealg_list, ealg_entries(), name, probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_ealg_get_byname);
+
+struct xfrm_algo_desc *xfrm_calg_get_byname(char *name, int probe)
+{
+	return xfrm_get_byname(calg_list, calg_entries(), name, probe);
+}
+EXPORT_SYMBOL_GPL(xfrm_calg_get_byname);
+
+struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx)
+{
+	if (idx >= aalg_entries())
+		return NULL;
+
+	return &aalg_list[idx];
+}
+EXPORT_SYMBOL_GPL(xfrm_aalg_get_byidx);
+
+struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx)
+{
+	if (idx >= ealg_entries())
+		return NULL;
+
+	return &ealg_list[idx];
+}
+EXPORT_SYMBOL_GPL(xfrm_ealg_get_byidx);
+
+/*
+ * Probe for the availability of crypto algorithms, and set the available
+ * flag for any algorithms found on the system.  This is typically called by
+ * pfkey during userspace SA add, update or register.
+ */
+void xfrm_probe_algs(void)
+{
+#ifdef CONFIG_CRYPTO
+	int i, status;
+	
+	BUG_ON(in_softirq());
+
+	for (i = 0; i < aalg_entries(); i++) {
+		status = crypto_alg_available(aalg_list[i].name, 0);
+		if (aalg_list[i].available != status)
+			aalg_list[i].available = status;
+	}
+	
+	for (i = 0; i < ealg_entries(); i++) {
+		status = crypto_alg_available(ealg_list[i].name, 0);
+		if (ealg_list[i].available != status)
+			ealg_list[i].available = status;
+	}
+	
+	for (i = 0; i < calg_entries(); i++) {
+		status = crypto_alg_available(calg_list[i].name, 0);
+		if (calg_list[i].available != status)
+			calg_list[i].available = status;
+	}
+#endif
+}
+EXPORT_SYMBOL_GPL(xfrm_probe_algs);
+
+int xfrm_count_auth_supported(void)
+{
+	int i, n;
+
+	for (i = 0, n = 0; i < aalg_entries(); i++)
+		if (aalg_list[i].available)
+			n++;
+	return n;
+}
+EXPORT_SYMBOL_GPL(xfrm_count_auth_supported);
+
+int xfrm_count_enc_supported(void)
+{
+	int i, n;
+
+	for (i = 0, n = 0; i < ealg_entries(); i++)
+		if (ealg_list[i].available)
+			n++;
+	return n;
+}
+EXPORT_SYMBOL_GPL(xfrm_count_enc_supported);
+
+/* Move to common area: it is shared with AH. */
+
+void skb_icv_walk(const struct sk_buff *skb, struct crypto_tfm *tfm,
+		  int offset, int len, icv_update_fn_t icv_update)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct scatterlist sg;
+
+	/* Checksum header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		
+		sg.page = virt_to_page(skb->data + offset);
+		sg.offset = (unsigned long)(skb->data + offset) % PAGE_SIZE;
+		sg.length = copy;
+		
+		icv_update(tfm, &sg, 1);
+		
+		if ((len -= copy) == 0)
+			return;
+		offset += copy;
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		BUG_TRAP(start <= offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+			if (copy > len)
+				copy = len;
+			
+			sg.page = frag->page;
+			sg.offset = frag->page_offset + offset-start;
+			sg.length = copy;
+			
+			icv_update(tfm, &sg, 1);
+
+			if (!(len -= copy))
+				return;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	if (skb_shinfo(skb)->frag_list) {
+		struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+		for (; list; list = list->next) {
+			int end;
+
+			BUG_TRAP(start <= offset + len);
+
+			end = start + list->len;
+			if ((copy = end - offset) > 0) {
+				if (copy > len)
+					copy = len;
+				skb_icv_walk(list, tfm, offset-start, copy, icv_update);
+				if ((len -= copy) == 0)
+					return;
+				offset += copy;
+			}
+			start = end;
+		}
+	}
+	if (len)
+		BUG();
+}
+EXPORT_SYMBOL_GPL(skb_icv_walk);
+
+#if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE)
+
+/* Looking generic it is not used in another places. */
+
+int
+skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	int elt = 0;
+
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		sg[elt].page = virt_to_page(skb->data + offset);
+		sg[elt].offset = (unsigned long)(skb->data + offset) % PAGE_SIZE;
+		sg[elt].length = copy;
+		elt++;
+		if ((len -= copy) == 0)
+			return elt;
+		offset += copy;
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		BUG_TRAP(start <= offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+			if (copy > len)
+				copy = len;
+			sg[elt].page = frag->page;
+			sg[elt].offset = frag->page_offset+offset-start;
+			sg[elt].length = copy;
+			elt++;
+			if (!(len -= copy))
+				return elt;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	if (skb_shinfo(skb)->frag_list) {
+		struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+		for (; list; list = list->next) {
+			int end;
+
+			BUG_TRAP(start <= offset + len);
+
+			end = start + list->len;
+			if ((copy = end - offset) > 0) {
+				if (copy > len)
+					copy = len;
+				elt += skb_to_sgvec(list, sg+elt, offset - start, copy);
+				if ((len -= copy) == 0)
+					return elt;
+				offset += copy;
+			}
+			start = end;
+		}
+	}
+	if (len)
+		BUG();
+	return elt;
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec);
+
+/* Check that skb data bits are writable. If they are not, copy data
+ * to newly created private area. If "tailbits" is given, make sure that
+ * tailbits bytes beyond current end of skb are writable.
+ *
+ * Returns amount of elements of scatterlist to load for subsequent
+ * transformations and pointer to writable trailer skb.
+ */
+
+int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
+{
+	int copyflag;
+	int elt;
+	struct sk_buff *skb1, **skb_p;
+
+	/* If skb is cloned or its head is paged, reallocate
+	 * head pulling out all the pages (pages are considered not writable
+	 * at the moment even if they are anonymous).
+	 */
+	if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
+	    __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL)
+		return -ENOMEM;
+
+	/* Easy case. Most of packets will go this way. */
+	if (!skb_shinfo(skb)->frag_list) {
+		/* A little of trouble, not enough of space for trailer.
+		 * This should not happen, when stack is tuned to generate
+		 * good frames. OK, on miss we reallocate and reserve even more
+		 * space, 128 bytes is fair. */
+
+		if (skb_tailroom(skb) < tailbits &&
+		    pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC))
+			return -ENOMEM;
+
+		/* Voila! */
+		*trailer = skb;
+		return 1;
+	}
+
+	/* Misery. We are in troubles, going to mincer fragments... */
+
+	elt = 1;
+	skb_p = &skb_shinfo(skb)->frag_list;
+	copyflag = 0;
+
+	while ((skb1 = *skb_p) != NULL) {
+		int ntail = 0;
+
+		/* The fragment is partially pulled by someone,
+		 * this can happen on input. Copy it and everything
+		 * after it. */
+
+		if (skb_shared(skb1))
+			copyflag = 1;
+
+		/* If the skb is the last, worry about trailer. */
+
+		if (skb1->next == NULL && tailbits) {
+			if (skb_shinfo(skb1)->nr_frags ||
+			    skb_shinfo(skb1)->frag_list ||
+			    skb_tailroom(skb1) < tailbits)
+				ntail = tailbits + 128;
+		}
+
+		if (copyflag ||
+		    skb_cloned(skb1) ||
+		    ntail ||
+		    skb_shinfo(skb1)->nr_frags ||
+		    skb_shinfo(skb1)->frag_list) {
+			struct sk_buff *skb2;
+
+			/* Fuck, we are miserable poor guys... */
+			if (ntail == 0)
+				skb2 = skb_copy(skb1, GFP_ATOMIC);
+			else
+				skb2 = skb_copy_expand(skb1,
+						       skb_headroom(skb1),
+						       ntail,
+						       GFP_ATOMIC);
+			if (unlikely(skb2 == NULL))
+				return -ENOMEM;
+
+			if (skb1->sk)
+				skb_set_owner_w(skb, skb1->sk);
+
+			/* Looking around. Are we still alive?
+			 * OK, link new skb, drop old one */
+
+			skb2->next = skb1->next;
+			*skb_p = skb2;
+			kfree_skb(skb1);
+			skb1 = skb2;
+		}
+		elt++;
+		*trailer = skb1;
+		skb_p = &skb1->next;
+	}
+
+	return elt;
+}
+EXPORT_SYMBOL_GPL(skb_cow_data);
+
+void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
+{
+	if (tail != skb) {
+		skb->data_len += len;
+		skb->len += len;
+	}
+	return skb_put(tail, len);
+}
+EXPORT_SYMBOL_GPL(pskb_put);
+#endif
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
new file mode 100644
index 00000000000..c58a6f05a0b
--- /dev/null
+++ b/net/xfrm/xfrm_input.c
@@ -0,0 +1,89 @@
+/*
+ * xfrm_input.c
+ *
+ * Changes:
+ * 	YOSHIFUJI Hideaki @USAGI
+ * 		Split up af-specific portion
+ * 	
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+
+static kmem_cache_t *secpath_cachep;
+
+void __secpath_destroy(struct sec_path *sp)
+{
+	int i;
+	for (i = 0; i < sp->len; i++)
+		xfrm_state_put(sp->x[i].xvec);
+	kmem_cache_free(secpath_cachep, sp);
+}
+EXPORT_SYMBOL(__secpath_destroy);
+
+struct sec_path *secpath_dup(struct sec_path *src)
+{
+	struct sec_path *sp;
+
+	sp = kmem_cache_alloc(secpath_cachep, SLAB_ATOMIC);
+	if (!sp)
+		return NULL;
+
+	sp->len = 0;
+	if (src) {
+		int i;
+
+		memcpy(sp, src, sizeof(*sp));
+		for (i = 0; i < sp->len; i++)
+			xfrm_state_hold(sp->x[i].xvec);
+	}
+	atomic_set(&sp->refcnt, 1);
+	return sp;
+}
+EXPORT_SYMBOL(secpath_dup);
+
+/* Fetch spi and seq from ipsec header */
+
+int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq)
+{
+	int offset, offset_seq;
+
+	switch (nexthdr) {
+	case IPPROTO_AH:
+		offset = offsetof(struct ip_auth_hdr, spi);
+		offset_seq = offsetof(struct ip_auth_hdr, seq_no);
+		break;
+	case IPPROTO_ESP:
+		offset = offsetof(struct ip_esp_hdr, spi);
+		offset_seq = offsetof(struct ip_esp_hdr, seq_no);
+		break;
+	case IPPROTO_COMP:
+		if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr)))
+			return -EINVAL;
+		*spi = ntohl(ntohs(*(u16*)(skb->h.raw + 2)));
+		*seq = 0;
+		return 0;
+	default:
+		return 1;
+	}
+
+	if (!pskb_may_pull(skb, 16))
+		return -EINVAL;
+
+	*spi = *(u32*)(skb->h.raw + offset);
+	*seq = *(u32*)(skb->h.raw + offset_seq);
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_parse_spi);
+
+void __init xfrm_input_init(void)
+{
+	secpath_cachep = kmem_cache_create("secpath_cache",
+					   sizeof(struct sec_path),
+					   0, SLAB_HWCACHE_ALIGN,
+					   NULL, NULL);
+	if (!secpath_cachep)
+		panic("XFRM: failed to allocate secpath_cache\n");
+}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
new file mode 100644
index 00000000000..80828078733
--- /dev/null
+++ b/net/xfrm/xfrm_policy.c
@@ -0,0 +1,1367 @@
+/* 
+ * xfrm_policy.c
+ *
+ * Changes:
+ *	Mitsuru KANDA @USAGI
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * 		IPv6 support
+ * 	Kazunori MIYAZAWA @USAGI
+ * 	YOSHIFUJI Hideaki
+ * 		Split up af-specific portion
+ *	Derek Atkins <derek@ihtfp.com>		Add the post_input processor
+ * 	
+ */
+
+#include <asm/bug.h>
+#include <linux/config.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/module.h>
+#include <net/xfrm.h>
+#include <net/ip.h>
+
+DECLARE_MUTEX(xfrm_cfg_sem);
+EXPORT_SYMBOL(xfrm_cfg_sem);
+
+static DEFINE_RWLOCK(xfrm_policy_lock);
+
+struct xfrm_policy *xfrm_policy_list[XFRM_POLICY_MAX*2];
+EXPORT_SYMBOL(xfrm_policy_list);
+
+static DEFINE_RWLOCK(xfrm_policy_afinfo_lock);
+static struct xfrm_policy_afinfo *xfrm_policy_afinfo[NPROTO];
+
+static kmem_cache_t *xfrm_dst_cache;
+
+static struct work_struct xfrm_policy_gc_work;
+static struct list_head xfrm_policy_gc_list =
+	LIST_HEAD_INIT(xfrm_policy_gc_list);
+static DEFINE_SPINLOCK(xfrm_policy_gc_lock);
+
+static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family);
+static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo);
+
+int xfrm_register_type(struct xfrm_type *type, unsigned short family)
+{
+	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	struct xfrm_type_map *typemap;
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EAFNOSUPPORT;
+	typemap = afinfo->type_map;
+
+	write_lock(&typemap->lock);
+	if (likely(typemap->map[type->proto] == NULL))
+		typemap->map[type->proto] = type;
+	else
+		err = -EEXIST;
+	write_unlock(&typemap->lock);
+	xfrm_policy_put_afinfo(afinfo);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_register_type);
+
+int xfrm_unregister_type(struct xfrm_type *type, unsigned short family)
+{
+	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	struct xfrm_type_map *typemap;
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EAFNOSUPPORT;
+	typemap = afinfo->type_map;
+
+	write_lock(&typemap->lock);
+	if (unlikely(typemap->map[type->proto] != type))
+		err = -ENOENT;
+	else
+		typemap->map[type->proto] = NULL;
+	write_unlock(&typemap->lock);
+	xfrm_policy_put_afinfo(afinfo);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_unregister_type);
+
+struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
+{
+	struct xfrm_policy_afinfo *afinfo;
+	struct xfrm_type_map *typemap;
+	struct xfrm_type *type;
+	int modload_attempted = 0;
+
+retry:
+	afinfo = xfrm_policy_get_afinfo(family);
+	if (unlikely(afinfo == NULL))
+		return NULL;
+	typemap = afinfo->type_map;
+
+	read_lock(&typemap->lock);
+	type = typemap->map[proto];
+	if (unlikely(type && !try_module_get(type->owner)))
+		type = NULL;
+	read_unlock(&typemap->lock);
+	if (!type && !modload_attempted) {
+		xfrm_policy_put_afinfo(afinfo);
+		request_module("xfrm-type-%d-%d",
+			       (int) family, (int) proto);
+		modload_attempted = 1;
+		goto retry;
+	}
+
+	xfrm_policy_put_afinfo(afinfo);
+	return type;
+}
+EXPORT_SYMBOL(xfrm_get_type);
+
+int xfrm_dst_lookup(struct xfrm_dst **dst, struct flowi *fl, 
+		    unsigned short family)
+{
+	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EAFNOSUPPORT;
+
+	if (likely(afinfo->dst_lookup != NULL))
+		err = afinfo->dst_lookup(dst, fl);
+	else
+		err = -EINVAL;
+	xfrm_policy_put_afinfo(afinfo);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_dst_lookup);
+
+void xfrm_put_type(struct xfrm_type *type)
+{
+	module_put(type->owner);
+}
+
+static inline unsigned long make_jiffies(long secs)
+{
+	if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
+		return MAX_SCHEDULE_TIMEOUT-1;
+	else
+	        return secs*HZ;
+}
+
+static void xfrm_policy_timer(unsigned long data)
+{
+	struct xfrm_policy *xp = (struct xfrm_policy*)data;
+	unsigned long now = (unsigned long)xtime.tv_sec;
+	long next = LONG_MAX;
+	int warn = 0;
+	int dir;
+
+	read_lock(&xp->lock);
+
+	if (xp->dead)
+		goto out;
+
+	dir = xp->index & 7;
+
+	if (xp->lft.hard_add_expires_seconds) {
+		long tmo = xp->lft.hard_add_expires_seconds +
+			xp->curlft.add_time - now;
+		if (tmo <= 0)
+			goto expired;
+		if (tmo < next)
+			next = tmo;
+	}
+	if (xp->lft.hard_use_expires_seconds) {
+		long tmo = xp->lft.hard_use_expires_seconds +
+			(xp->curlft.use_time ? : xp->curlft.add_time) - now;
+		if (tmo <= 0)
+			goto expired;
+		if (tmo < next)
+			next = tmo;
+	}
+	if (xp->lft.soft_add_expires_seconds) {
+		long tmo = xp->lft.soft_add_expires_seconds +
+			xp->curlft.add_time - now;
+		if (tmo <= 0) {
+			warn = 1;
+			tmo = XFRM_KM_TIMEOUT;
+		}
+		if (tmo < next)
+			next = tmo;
+	}
+	if (xp->lft.soft_use_expires_seconds) {
+		long tmo = xp->lft.soft_use_expires_seconds +
+			(xp->curlft.use_time ? : xp->curlft.add_time) - now;
+		if (tmo <= 0) {
+			warn = 1;
+			tmo = XFRM_KM_TIMEOUT;
+		}
+		if (tmo < next)
+			next = tmo;
+	}
+
+	if (warn)
+		km_policy_expired(xp, dir, 0);
+	if (next != LONG_MAX &&
+	    !mod_timer(&xp->timer, jiffies + make_jiffies(next)))
+		xfrm_pol_hold(xp);
+
+out:
+	read_unlock(&xp->lock);
+	xfrm_pol_put(xp);
+	return;
+
+expired:
+	read_unlock(&xp->lock);
+	km_policy_expired(xp, dir, 1);
+	xfrm_policy_delete(xp, dir);
+	xfrm_pol_put(xp);
+}
+
+
+/* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2
+ * SPD calls.
+ */
+
+struct xfrm_policy *xfrm_policy_alloc(int gfp)
+{
+	struct xfrm_policy *policy;
+
+	policy = kmalloc(sizeof(struct xfrm_policy), gfp);
+
+	if (policy) {
+		memset(policy, 0, sizeof(struct xfrm_policy));
+		atomic_set(&policy->refcnt, 1);
+		rwlock_init(&policy->lock);
+		init_timer(&policy->timer);
+		policy->timer.data = (unsigned long)policy;
+		policy->timer.function = xfrm_policy_timer;
+	}
+	return policy;
+}
+EXPORT_SYMBOL(xfrm_policy_alloc);
+
+/* Destroy xfrm_policy: descendant resources must be released to this moment. */
+
+void __xfrm_policy_destroy(struct xfrm_policy *policy)
+{
+	if (!policy->dead)
+		BUG();
+
+	if (policy->bundles)
+		BUG();
+
+	if (del_timer(&policy->timer))
+		BUG();
+
+	kfree(policy);
+}
+EXPORT_SYMBOL(__xfrm_policy_destroy);
+
+static void xfrm_policy_gc_kill(struct xfrm_policy *policy)
+{
+	struct dst_entry *dst;
+
+	while ((dst = policy->bundles) != NULL) {
+		policy->bundles = dst->next;
+		dst_free(dst);
+	}
+
+	if (del_timer(&policy->timer))
+		atomic_dec(&policy->refcnt);
+
+	if (atomic_read(&policy->refcnt) > 1)
+		flow_cache_flush();
+
+	xfrm_pol_put(policy);
+}
+
+static void xfrm_policy_gc_task(void *data)
+{
+	struct xfrm_policy *policy;
+	struct list_head *entry, *tmp;
+	struct list_head gc_list = LIST_HEAD_INIT(gc_list);
+
+	spin_lock_bh(&xfrm_policy_gc_lock);
+	list_splice_init(&xfrm_policy_gc_list, &gc_list);
+	spin_unlock_bh(&xfrm_policy_gc_lock);
+
+	list_for_each_safe(entry, tmp, &gc_list) {
+		policy = list_entry(entry, struct xfrm_policy, list);
+		xfrm_policy_gc_kill(policy);
+	}
+}
+
+/* Rule must be locked. Release descentant resources, announce
+ * entry dead. The rule must be unlinked from lists to the moment.
+ */
+
+static void xfrm_policy_kill(struct xfrm_policy *policy)
+{
+	int dead;
+
+	write_lock_bh(&policy->lock);
+	dead = policy->dead;
+	policy->dead = 1;
+	write_unlock_bh(&policy->lock);
+
+	if (unlikely(dead)) {
+		WARN_ON(1);
+		return;
+	}
+
+	spin_lock(&xfrm_policy_gc_lock);
+	list_add(&policy->list, &xfrm_policy_gc_list);
+	spin_unlock(&xfrm_policy_gc_lock);
+
+	schedule_work(&xfrm_policy_gc_work);
+}
+
+/* Generate new index... KAME seems to generate them ordered by cost
+ * of an absolute inpredictability of ordering of rules. This will not pass. */
+static u32 xfrm_gen_index(int dir)
+{
+	u32 idx;
+	struct xfrm_policy *p;
+	static u32 idx_generator;
+
+	for (;;) {
+		idx = (idx_generator | dir);
+		idx_generator += 8;
+		if (idx == 0)
+			idx = 8;
+		for (p = xfrm_policy_list[dir]; p; p = p->next) {
+			if (p->index == idx)
+				break;
+		}
+		if (!p)
+			return idx;
+	}
+}
+
+int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+{
+	struct xfrm_policy *pol, **p;
+	struct xfrm_policy *delpol = NULL;
+	struct xfrm_policy **newpos = NULL;
+
+	write_lock_bh(&xfrm_policy_lock);
+	for (p = &xfrm_policy_list[dir]; (pol=*p)!=NULL;) {
+		if (!delpol && memcmp(&policy->selector, &pol->selector, sizeof(pol->selector)) == 0) {
+			if (excl) {
+				write_unlock_bh(&xfrm_policy_lock);
+				return -EEXIST;
+			}
+			*p = pol->next;
+			delpol = pol;
+			if (policy->priority > pol->priority)
+				continue;
+		} else if (policy->priority >= pol->priority) {
+			p = &pol->next;
+			continue;
+		}
+		if (!newpos)
+			newpos = p;
+		if (delpol)
+			break;
+		p = &pol->next;
+	}
+	if (newpos)
+		p = newpos;
+	xfrm_pol_hold(policy);
+	policy->next = *p;
+	*p = policy;
+	atomic_inc(&flow_cache_genid);
+	policy->index = delpol ? delpol->index : xfrm_gen_index(dir);
+	policy->curlft.add_time = (unsigned long)xtime.tv_sec;
+	policy->curlft.use_time = 0;
+	if (!mod_timer(&policy->timer, jiffies + HZ))
+		xfrm_pol_hold(policy);
+	write_unlock_bh(&xfrm_policy_lock);
+
+	if (delpol) {
+		xfrm_policy_kill(delpol);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_policy_insert);
+
+struct xfrm_policy *xfrm_policy_bysel(int dir, struct xfrm_selector *sel,
+				      int delete)
+{
+	struct xfrm_policy *pol, **p;
+
+	write_lock_bh(&xfrm_policy_lock);
+	for (p = &xfrm_policy_list[dir]; (pol=*p)!=NULL; p = &pol->next) {
+		if (memcmp(sel, &pol->selector, sizeof(*sel)) == 0) {
+			xfrm_pol_hold(pol);
+			if (delete)
+				*p = pol->next;
+			break;
+		}
+	}
+	write_unlock_bh(&xfrm_policy_lock);
+
+	if (pol && delete) {
+		atomic_inc(&flow_cache_genid);
+		xfrm_policy_kill(pol);
+	}
+	return pol;
+}
+EXPORT_SYMBOL(xfrm_policy_bysel);
+
+struct xfrm_policy *xfrm_policy_byid(int dir, u32 id, int delete)
+{
+	struct xfrm_policy *pol, **p;
+