/*
 * xfrm_output.c - Common IPsec encapsulation code.
 *
 * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.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/errno.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
#include <net/xfrm.h>

#include <avm/pa/avm_pa.h>
static struct avm_pa_dev_info xfrm_out_dev_info __read_mostly;

static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);

static int xfrm_skb_check_space(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev)
		- skb_headroom(skb);
	int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);

	if (nhead <= 0) {
		if (ntail <= 0)
			return 0;
		nhead = 0;
	} else if (ntail < 0)
		ntail = 0;

	return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
}

/* Children define the path of the packet through the
 * Linux networking.  Thus, destinations are stackable.
 */

static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
{
	struct dst_entry *child = dst_clone(skb_dst(skb)->child);

	skb_dst_drop(skb);
	return child;
}

static int xfrm_output_one(struct sk_buff *skb, int err)
{
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_state *x = dst->xfrm;
	struct net *net = xs_net(x);

	if (err <= 0)
		goto resume;

	do {
		err = xfrm_skb_check_space(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			goto error_nolock;
		}

		err = x->outer_mode->output(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
			goto error_nolock;
		}

		spin_lock_bh(&x->lock);

		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
			err = -EINVAL;
			goto error;
		}

		err = xfrm_state_check_expire(x);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
			goto error;
		}

		err = x->repl->overflow(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
			goto error;
		}

		x->curlft.bytes += skb->len;
		x->curlft.packets++;

		spin_unlock_bh(&x->lock);

		skb_dst_force(skb);

		err = x->type->output(x, skb);
		if (err == -EINPROGRESS)
			goto out;

resume:
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			goto error_nolock;
		}

		dst = skb_dst_pop(skb);
		if (!dst) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			err = -EHOSTUNREACH;
			goto error_nolock;
		}
		skb_dst_set(skb, dst);
		x = dst->xfrm;
	} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));

	return 0;

error:
	spin_unlock_bh(&x->lock);
error_nolock:
	kfree_skb(skb);
out:
	return err;
}

int xfrm_output_resume(struct sk_buff *skb, int err)
{
	struct net *net = xs_net(skb_dst(skb)->xfrm);

	while (likely((err = xfrm_output_one(skb, err)) == 0)) {
		nf_reset_no_generic_ct(skb);

		if (!skb_dst(skb)->xfrm) {
			/* Now encrypted, try to accelerate the other half.
			 * The skb must be reset to allow for a secondary session.
			 */
			avm_pa_reset_skb(skb);
		}
		/* We want to invert the likely indication because avm_pa
		 * very likely accelerates the packet. We take the opportunity
		 * and do a direct call optimization as well.
		 */
		if (skb_dst(skb)->ops->local_out == __ip_local_out)
			err = __ip_local_out(net, skb->sk, skb);
		else if (skb_dst(skb)->ops->local_out == __ip6_local_out)
			err = __ip6_local_out(net, skb->sk, skb);
		else
			err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);

		if (likely(err != 1)) /* likely accelerated by avm_pa */
			goto out;

		if (!skb_dst(skb)->xfrm)
			return dst_output(net, skb->sk, skb);

		err = nf_hook(skb_dst(skb)->ops->family,
			      NF_INET_POST_ROUTING, net, skb->sk, skb,
			      NULL, skb_dst(skb)->dev, xfrm_output2);
		if (unlikely(err != 1))
			goto out;
	}

	if (err == -EINPROGRESS)
		err = 0;

out:
	return err;
}
EXPORT_SYMBOL_GPL(xfrm_output_resume);

static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	return xfrm_output_resume(skb, 1);
}

static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct sk_buff *segs;

	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
	segs = skb_gso_segment(skb, 0);
	kfree_skb(skb);
	if (IS_ERR(segs))
		return PTR_ERR(segs);
	if (segs == NULL)
		return -EINVAL;

	do {
		struct sk_buff *nskb = segs->next;
		int err;

		segs->next = NULL;
		err = xfrm_output2(net, sk, segs);

		if (unlikely(err)) {
			kfree_skb_list(nskb);
			return err;
		}

		segs = nskb;
	} while (segs);

	return 0;
}

int xfrm_output(struct sock *sk, struct sk_buff *skb)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	int err;

	avm_pa_add_xfrm_session(&xfrm_out_dev_info, skb, skb_dst(skb)->xfrm);

	if (skb_is_gso(skb))
		return xfrm_output_gso(net, sk, skb);

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		err = skb_checksum_help(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			kfree_skb(skb);
			return err;
		}
	}

	return xfrm_output2(net, sk, skb);
}
EXPORT_SYMBOL_GPL(xfrm_output);

int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
	struct xfrm_mode *inner_mode;
	if (x->sel.family == AF_UNSPEC)
		inner_mode = xfrm_ip2inner_mode(x,
				xfrm_af2proto(skb_dst(skb)->ops->family));
	else
		inner_mode = x->inner_mode;

	if (inner_mode == NULL)
		return -EAFNOSUPPORT;
	return inner_mode->afinfo->extract_output(x, skb);
}
EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);

void xfrm_local_error(struct sk_buff *skb, int mtu)
{
	unsigned int proto;
	struct xfrm_state_afinfo *afinfo;

	if (skb->protocol == htons(ETH_P_IP))
		proto = AF_INET;
	else if (skb->protocol == htons(ETH_P_IPV6) &&
		 skb->sk->sk_family == AF_INET6)
		proto = AF_INET6;
	else
		return;

	afinfo = xfrm_state_get_afinfo(proto);
	if (!afinfo)
		return;

	afinfo->local_error(skb, mtu);
	xfrm_state_put_afinfo(afinfo);
}
EXPORT_SYMBOL_GPL(xfrm_local_error);

static void xfrm_out_transmit(void *arg, struct sk_buff *skb)
{
	int ret;

	ret = xfrm_output(NULL, skb);
	if (unlikely(ret < 0))
		net_err_ratelimited("%s failed: %d\n", __func__, ret);
}

static void __init xfrm_output_avm_pa_register(void)
{
	struct avm_pa_pid_cfg cfg = {0};
	int ret;

	snprintf(cfg.name, sizeof(cfg.name), "xfrm_out");
	cfg.framing = avm_pa_framing_ipdev;
	cfg.default_mtu = 0xffff;
	cfg.tx_func = xfrm_out_transmit;
	ret = avm_pa_dev_pid_register(&xfrm_out_dev_info, &cfg);
	if (ret < 0)
		pr_err("%s: failed to register avm_pa pid %s: %d\n",
		       __func__, cfg.name, ret);
}

void __init xfrm_output_init(void)
{
	xfrm_output_avm_pa_register();
}