1. 根目录:
2. net
3. ipv4
4. esp4.c

#include <crypto/aead.h>
#include <crypto/authenc.h>
#include <linux/err.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
#include <linux/scatterlist.h>
#include <linux/kernel.h>
#include <linux/pfkeyv2.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/in6.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/udp.h>

struct esp_skb_cb {
	struct xfrm_skb_cb xfrm;
	void *tmp;
};

#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.
 *
 * For alignment considerations the IV is placed at the front, followed
 * by the request and finally the SG list.
 *
 * TODO: Use spare space in skb for this where possible.
 */
static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
{
	unsigned int len;

	len = seqhilen;

	len += crypto_aead_ivsize(aead);

	if (len) {
		len += crypto_aead_alignmask(aead) &
		       ~(crypto_tfm_ctx_alignment() - 1);
		len = ALIGN(len, crypto_tfm_ctx_alignment());
	}

	len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead);
	len = ALIGN(len, __alignof__(struct scatterlist));

	len += sizeof(struct scatterlist) * nfrags;

	return kmalloc(len, GFP_ATOMIC);
}

static inline __be32 *esp_tmp_seqhi(void *tmp)
{
	return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
}
static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
{
	return crypto_aead_ivsize(aead) ?
	       PTR_ALIGN((u8 *)tmp + seqhilen,
			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
}

static inline struct aead_givcrypt_request *esp_tmp_givreq(
	struct crypto_aead *aead, u8 *iv)
{
	struct aead_givcrypt_request *req;

	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
				crypto_tfm_ctx_alignment());
	aead_givcrypt_set_tfm(req, aead);
	return req;
}

static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
{
	struct aead_request *req;

	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
				crypto_tfm_ctx_alignment());
	aead_request_set_tfm(req, aead);
	return req;
}

static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
					     struct aead_request *req)
{
	return (void *)ALIGN((unsigned long)(req + 1) +
			     crypto_aead_reqsize(aead),
			     __alignof__(struct scatterlist));
}

static inline struct scatterlist *esp_givreq_sg(
	struct crypto_aead *aead, struct aead_givcrypt_request *req)
{
	return (void *)ALIGN((unsigned long)(req + 1) +
			     crypto_aead_reqsize(aead),
			     __alignof__(struct scatterlist));
}

static void esp_output_done(struct crypto_async_request *base, int err)
{
	struct sk_buff *skb = base->data;

	kfree(ESP_SKB_CB(skb)->tmp);
	xfrm_output_resume(skb, err);
}

static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
{
	int err;
	struct ip_esp_hdr *esph;
	struct crypto_aead *aead;
	struct aead_givcrypt_request *req;
	struct scatterlist *sg;
	struct scatterlist *asg;
	struct esp_data *esp;
	struct sk_buff *trailer;
	void *tmp;
	u8 *iv;
	u8 *tail;
	int blksize;
	int clen;
	int alen;
	int plen;
	int tfclen;
	int nfrags;
	int assoclen;
	int sglists;
	int seqhilen;
	__be32 *seqhi;

	/* skb is pure payload to encrypt */

	err = -ENOMEM;

	esp = x->data;
	aead = esp->aead;
	alen = crypto_aead_authsize(aead);

	tfclen = 0;
	if (x->tfcpad) {
		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
		u32 padto;

		padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached));
		if (skb->len < padto)
			tfclen = padto - skb->len;
	}
	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
	clen = ALIGN(skb->len + 2 + tfclen, blksize);
	if (esp->padlen)
		clen = ALIGN(clen, esp->padlen);
	plen = clen - skb->len - tfclen;

	err = skb_cow_data(skb, tfclen + plen + alen, &trailer);
	if (err < 0)
		goto error;
	nfrags = err;

	assoclen = sizeof(*esph);
	sglists = 1;
	seqhilen = 0;

	if (x->props.flags & XFRM_STATE_ESN) {
		sglists += 2;
		seqhilen += sizeof(__be32);
		assoclen += seqhilen;
	}

	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
	if (!tmp)
		goto error;

	seqhi = esp_tmp_seqhi(tmp);
	iv = esp_tmp_iv(aead, tmp, seqhilen);
	req = esp_tmp_givreq(aead, iv);
	asg = esp_givreq_sg(aead, req);
	sg = asg + sglists;

	/* Fill padding... */
	tail = skb_tail_pointer(trailer);
	if (tfclen) {
		memset(tail, 0, tfclen);
		tail += tfclen;
	}
	do {
		int i;
		for (i = 0; i < plen - 2; i++)
			tail[i] = i + 1;
	} while (0);
	tail[plen - 2] = plen - 2;
	tail[plen - 1] = *skb_mac_header(skb);
	pskb_put(skb, trailer, clen - skb->len + alen);

	skb_push(skb, -skb_network_offset(skb));
	esph = ip_esp_hdr(skb);
	*skb_mac_header(skb) = IPPROTO_ESP;

	/* this is non-NULL only with UDP Encapsulation */
	if (x->encap) {
		struct xfrm_encap_tmpl *encap = x->encap;
		struct udphdr *uh;
		__be32 *udpdata32;
		__be16 sport, dport;
		int encap_type;

		spin_lock_bh(&x->lock);
		sport = encap->encap_sport;
		dport = encap->encap_dport;
		encap_type = encap->encap_type;
		spin_unlock_bh(&x->lock);

		uh = (struct udphdr *)esph;
		uh->source = sport;
		uh->dest = dport;
		uh->len = htons(skb->len - skb_transport_offset(skb));
		uh->check = 0;

		switch (encap_type) {
		default:
		case UDP_ENCAP_ESPINUDP:
			esph = (struct ip_esp_hdr *)(uh + 1);
			break;
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			udpdata32 = (__be32 *)(uh + 1);
			udpdata32[0] = udpdata32[1] = 0;
			esph = (struct ip_esp_hdr *)(udpdata32 + 2);
			break;
		}

		*skb_mac_header(skb) = IPPROTO_UDP;
	}

	esph->spi = x->id.spi;
	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);

	sg_init_table(sg, nfrags);
	skb_to_sgvec(skb, sg,
		     esph->enc_data + crypto_aead_ivsize(aead) - skb->data,
		     clen + alen);

	if ((x->props.flags & XFRM_STATE_ESN)) {
		sg_init_table(asg, 3);
		sg_set_buf(asg, &esph->spi, sizeof(__be32));
		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
		sg_set_buf(asg + 1, seqhi, seqhilen);
		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
	} else
		sg_init_one(asg, esph, sizeof(*esph));

	aead_givcrypt_set_callback(req, 0, esp_output_done, skb);
	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
	aead_givcrypt_set_assoc(req, asg, assoclen);
	aead_givcrypt_set_giv(req, esph->enc_data,
			      XFRM_SKB_CB(skb)->seq.output.low);

	ESP_SKB_CB(skb)->tmp = tmp;
	err = crypto_aead_givencrypt(req);
	if (err == -EINPROGRESS)
		goto error;

	if (err == -EBUSY)
		err = NET_XMIT_DROP;

	kfree(tmp);

error:
	return err;
}

static int esp_input_done2(struct sk_buff *skb, int err)
{
	const struct iphdr *iph;
	struct xfrm_state *x = xfrm_input_state(skb);
	struct esp_data *esp = x->data;
	struct crypto_aead *aead = esp->aead;
	int alen = crypto_aead_authsize(aead);
	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
	int elen = skb->len - hlen;
	int ihl;
	u8 nexthdr[2];
	int padlen;

	kfree(ESP_SKB_CB(skb)->tmp);

	if (unlikely(err))
		goto out;

	if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
		BUG();

	err = -EINVAL;
	padlen = nexthdr[0];
	if (padlen + 2 + alen >= elen)
		goto out;

	/* ... check padding bits here. Silly. :-) */

	iph = ip_hdr(skb);
	ihl = iph->ihl * 4;

	if (x->encap) {
		struct xfrm_encap_tmpl *encap = x->encap;
		struct udphdr *uh = (void *)(skb_network_header(skb) + ihl);

		/*
		 * 1) if the NAT-T peer's IP or port changed then
		 *    advertize the change to the keying daemon.
		 *    This is an inbound SA, so just compare
		 *    SRC ports.
		 */
		if (iph->saddr != x->props.saddr.a4 ||
		    uh->source != encap->encap_sport) {
			xfrm_address_t ipaddr;

			ipaddr.a4 = iph->saddr;
			km_new_mapping(x, &ipaddr, uh->source);

			/* XXX: perhaps add an extra
			 * policy check here, to see
			 * if we should allow or
			 * reject a packet from a
			 * different source
			 * address/port.
			 */
		}

		/*
		 * 2) ignore UDP/TCP checksums in case
		 *    of NAT-T in Transport Mode, or
		 *    perform other post-processing fixes
		 *    as per draft-ietf-ipsec-udp-encaps-06,
		 *    section 3.1.2
		 */
		if (x->props.mode == XFRM_MODE_TRANSPORT)
			skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	pskb_trim(skb, skb->len - alen - padlen - 2);
	__skb_pull(skb, hlen);
	skb_set_transport_header(skb, -ihl);

	err = nexthdr[1];

	/* RFC4303: Drop dummy packets without any error */
	if (err == IPPROTO_NONE)
		err = -EINVAL;

out:
	return err;
}

static void esp_input_done(struct crypto_async_request *base, int err)
{
	struct sk_buff *skb = base->data;

	xfrm_input_resume(skb, esp_input_done2(skb, err));
}

/*
 * Note: detecting truncated vs. non-truncated authentication data is very
 * expensive, so we only support truncated data, which is the recommended
 * and common case.
 */
static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
{
	struct ip_esp_hdr *esph;
	struct esp_data *esp = x->data;
	struct crypto_aead *aead = esp->aead;
	struct aead_request *req;
	struct sk_buff *trailer;
	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
	int nfrags;
	int assoclen;
	int sglists;
	int seqhilen;
	__be32 *seqhi;
	void *tmp;
	u8 *iv;
	struct scatterlist *sg;
	struct scatterlist *asg;
	int err = -EINVAL;

	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
		goto out;

	if (elen <= 0)
		goto out;

	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
		goto out;
	nfrags = err;

	assoclen = sizeof(*esph);
	sglists = 1;
	seqhilen = 0;

	if (x->props.flags & XFRM_STATE_ESN) {
		sglists += 2;
		seqhilen += sizeof(__be32);
		assoclen += seqhilen;
	}

	err = -ENOMEM;
	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
	if (!tmp)
		goto out;

	ESP_SKB_CB(skb)->tmp = tmp;
	seqhi = esp_tmp_seqhi(tmp);
	iv = esp_tmp_iv(aead, tmp, seqhilen);
	req = esp_tmp_req(aead, iv);
	asg = esp_req_sg(aead, req);
	sg = asg + sglists;

	skb->ip_summed = CHECKSUM_NONE;

	esph = (struct ip_esp_hdr *)skb->data;

	/* Get ivec. This can be wrong, check against another impls. */
	iv = esph->enc_data;

	sg_init_table(sg, nfrags);
	skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen);

	if ((x->props.flags & XFRM_STATE_ESN)) {
		sg_init_table(asg, 3);
		sg_set_buf(asg, &esph->spi, sizeof(__be32));
		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
		sg_set_buf(asg + 1, seqhi, seqhilen);
		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
	} else
		sg_init_one(asg, esph, sizeof(*esph));

	aead_request_set_callback(req, 0, esp_input_done, skb);
	aead_request_set_crypt(req, sg, sg, elen, iv);
	aead_request_set_assoc(req, asg, assoclen);

	err = crypto_aead_decrypt(req);
	if (err == -EINPROGRESS)
		goto out;

	err = esp_input_done2(skb, err);

out:
	return err;
}

static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
{
	struct esp_data *esp = x->data;
	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
	u32 align = max_t(u32, blksize, esp->padlen);
	u32 rem;

	mtu -= x->props.header_len + crypto_aead_authsize(esp->aead);
	rem = mtu & (align - 1);
	mtu &= ~(align - 1);

	switch (x->props.mode) {
	case XFRM_MODE_TUNNEL:
		break;
	default:
	case XFRM_MODE_TRANSPORT:
		/* The worst case */
		mtu -= blksize - 4;
		mtu += min_t(u32, blksize - 4, rem);
		break;
	case XFRM_MODE_BEET:
		/* The worst case. */
		mtu += min_t(u32, IPV4_BEET_PHMAXLEN, rem);
		break;
	}

	return mtu - 2;
}

static void esp4_err(struct sk_buff *skb, u32 info)
{
	struct net *net = dev_net(skb->dev);
	const struct iphdr *iph = (const struct iphdr *)skb->data;
	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
	struct xfrm_state *x;

	if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH ||
	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
		return;

	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
			      esph->spi, IPPROTO_ESP, AF_INET);
	if (!x)
		return;
	NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n",
		 ntohl(esph->spi), ntohl(iph->daddr));
	xfrm_state_put(x);
}

static void esp_destroy(struct xfrm_state *x)
{
	struct esp_data *esp = x->data;

	if (!esp)
		return;

	crypto_free_aead(esp->aead);
	kfree(esp);
}

static int esp_init_aead(struct xfrm_state *x)
{
	struct esp_data *esp = x->data;
	struct crypto_aead *aead;
	int err;

	aead = crypto_alloc_aead(x->aead->alg_name, 0, 0);
	err = PTR_ERR(aead);
	if (IS_ERR(aead))
		goto error;

	esp->aead = aead;

	err = crypto_aead_setkey(aead, x->aead->alg_key,
				 (x->aead->alg_key_len + 7) / 8);
	if (err)
		goto error;

	err = crypto_aead_setauthsize(aead, x->aead->alg_icv_len / 8);
	if (err)
		goto error;

error:
	return err;
}

static int esp_init_authenc(struct xfrm_state *x)
{
	struct esp_data *esp = x->data;
	struct crypto_aead *aead;
	struct crypto_authenc_key_param *param;
	struct rtattr *rta;
	char *key;
	char *p;
	char authenc_name[CRYPTO_MAX_ALG_NAME];
	unsigned int keylen;
	int err;

	err = -EINVAL;
	if (x->ealg == NULL)
		goto error;

	err = -ENAMETOOLONG;

	if ((x->props.flags & XFRM_STATE_ESN)) {
		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
			     "authencesn(%s,%s)",
			     x->aalg ? x->aalg->alg_name : "digest_null",
			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
			goto error;
	} else {
		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
			     "authenc(%s,%s)",
			     x->aalg ? x->aalg->alg_name : "digest_null",
			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
			goto error;
	}

	aead = crypto_alloc_aead(authenc_name, 0, 0);
	err = PTR_ERR(aead);
	if (IS_ERR(aead))
		goto error;

	esp->aead = aead;

	keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) +
		 (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param));
	err = -ENOMEM;
	key = kmalloc(keylen, GFP_KERNEL);
	if (!key)
		goto error;

	p = key;
	rta = (void *)p;
	rta->rta_type = CRYPTO_AUTHENC_KEYA_PARAM;
	rta->rta_len = RTA_LENGTH(sizeof(*param));
	param = RTA_DATA(rta);
	p += RTA_SPACE(sizeof(*param));

	if (x->aalg) {
		struct xfrm_algo_desc *aalg_desc;

		memcpy(p, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8);
		p += (x->aalg->alg_key_len + 7) / 8;

		aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
		BUG_ON(!aalg_desc);

		err = -EINVAL;
		if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
		    crypto_aead_authsize(aead)) {
			NETDEBUG(KERN_INFO "ESP: %s digestsize %u != %hu\n",
				 x->aalg->alg_name,
				 crypto_aead_authsize(aead),
				 aalg_desc->uinfo.auth.icv_fullbits/8);
			goto free_key;
		}

		err = crypto_aead_setauthsize(
			aead, x->aalg->alg_trunc_len / 8);
		if (err)
			goto free_key;
	}

	param->enckeylen = cpu_to_be32((x->ealg->alg_key_len + 7) / 8);
	memcpy(p, x->ealg->alg_key, (x->ealg->alg_key_len + 7) / 8);

	err = crypto_aead_setkey(aead, key, keylen);

free_key:
	kfree(key);

error:
	return err;
}

static int esp_init_state(struct xfrm_state *x)
{
	struct esp_data *esp;
	struct crypto_aead *aead;
	u32 align;
	int err;

	esp = kzalloc(sizeof(*esp), GFP_KERNEL);
	if (esp == NULL)
		return -ENOMEM;

	x->data = esp;

	if (x->aead)
		err = esp_init_aead(x);
	else
		err = esp_init_authenc(x);

	if (err)
		goto error;

	aead = esp->aead;

	esp->padlen = 0;

	x->props.header_len = sizeof(struct ip_esp_hdr) +
			      crypto_aead_ivsize(aead);
	if (x->props.mode == XFRM_MODE_TUNNEL)
		x->props.header_len += sizeof(struct iphdr);
	else if (x->props.mode == XFRM_MODE_BEET && x->sel.family != AF_INET6)
		x->props.header_len += IPV4_BEET_PHMAXLEN;
	if (x->encap) {
		struct xfrm_encap_tmpl *encap = x->encap;

		switch (encap->encap_type) {
		default:
			goto error;
		case UDP_ENCAP_ESPINUDP:
			x->props.header_len += sizeof(struct udphdr);
			break;
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32);
			break;
		}
	}

	align = ALIGN(crypto_aead_blocksize(aead), 4);
	if (esp->padlen)
		align = max_t(u32, align, esp->padlen);
	x->props.trailer_len = align + 1 + crypto_aead_authsize(esp->aead);

error:
	return err;
}

static const struct xfrm_type esp_type =
{
	.description	= "ESP4",
	.owner		= THIS_MODULE,
	.proto	     	= IPPROTO_ESP,
	.flags		= XFRM_TYPE_REPLAY_PROT,
	.init_state	= esp_init_state,
	.destructor	= esp_destroy,
	.get_mtu	= esp4_get_mtu,
	.input		= esp_input,
	.output		= esp_output
};

static const struct net_protocol esp4_protocol = {
	.handler	=	xfrm4_rcv,
	.err_handler	=	esp4_err,
	.no_policy	=	1,
	.netns_ok	=	1,
};

static int __init esp4_init(void)
{
	if (xfrm_register_type(&esp_type, AF_INET) < 0) {
		printk(KERN_INFO "ip esp init: can't add xfrm type\n");
		return -EAGAIN;
	}
	if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) {
		printk(KERN_INFO "ip esp init: can't add protocol\n");
		xfrm_unregister_type(&esp_type, AF_INET);
		return -EAGAIN;
	}
	return 0;
}

static void __exit esp4_fini(void)
{
	if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0)
		printk(KERN_INFO "ip esp close: can't remove protocol\n");
	if (xfrm_unregister_type(&esp_type, AF_INET) < 0)
		printk(KERN_INFO "ip esp close: can't remove xfrm type\n");
}

module_init(esp4_init);
module_exit(esp4_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP);