aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/clocksource/timer-integrator-ap.c
blob: 19fb7de4b928847fd89d337750b927174deb1cab (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
/*
 * Integrator/AP timer driver
 * Copyright (C) 2000-2003 Deep Blue Solutions Ltd
 * Copyright (c) 2014, Linaro Limited
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/clk.h>
#include <linux/clocksource.h>
#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
#include <linux/sched_clock.h>

#include "timer-sp.h"

static void __iomem * sched_clk_base;

static u64 notrace integrator_read_sched_clock(void)
{
	return -readl(sched_clk_base + TIMER_VALUE);
}

static int __init integrator_clocksource_init(unsigned long inrate,
					      void __iomem *base)
{
	u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC;
	unsigned long rate = inrate;
	int ret;

	if (rate >= 1500000) {
		rate /= 16;
		ctrl |= TIMER_CTRL_DIV16;
	}

	writel(0xffff, base + TIMER_LOAD);
	writel(ctrl, base + TIMER_CTRL);

	ret = clocksource_mmio_init(base + TIMER_VALUE, "timer2",
				    rate, 200, 16, clocksource_mmio_readl_down);
	if (ret)
		return ret;

	sched_clk_base = base;
	sched_clock_register(integrator_read_sched_clock, 16, rate);

	return 0;
}

static unsigned long timer_reload;
static void __iomem * clkevt_base;

/*
 * IRQ handler for the timer
 */
static irqreturn_t integrator_timer_interrupt(int irq, void *dev_id)
{
	struct clock_event_device *evt = dev_id;

	/* clear the interrupt */
	writel(1, clkevt_base + TIMER_INTCLR);

	evt->event_handler(evt);

	return IRQ_HANDLED;
}

static int clkevt_shutdown(struct clock_event_device *evt)
{
	u32 ctrl = readl(clkevt_base + TIMER_CTRL) & ~TIMER_CTRL_ENABLE;

	/* Disable timer */
	writel(ctrl, clkevt_base + TIMER_CTRL);
	return 0;
}

static int clkevt_set_oneshot(struct clock_event_device *evt)
{
	u32 ctrl = readl(clkevt_base + TIMER_CTRL) &
		   ~(TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC);

	/* Leave the timer disabled, .set_next_event will enable it */
	writel(ctrl, clkevt_base + TIMER_CTRL);
	return 0;
}

static int clkevt_set_periodic(struct clock_event_device *evt)
{
	u32 ctrl = readl(clkevt_base + TIMER_CTRL) & ~TIMER_CTRL_ENABLE;

	/* Disable timer */
	writel(ctrl, clkevt_base + TIMER_CTRL);

	/* Enable the timer and start the periodic tick */
	writel(timer_reload, clkevt_base + TIMER_LOAD);
	ctrl |= TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE;
	writel(ctrl, clkevt_base + TIMER_CTRL);
	return 0;
}

static int clkevt_set_next_event(unsigned long next, struct clock_event_device *evt)
{
	unsigned long ctrl = readl(clkevt_base + TIMER_CTRL);

	writel(ctrl & ~TIMER_CTRL_ENABLE, clkevt_base + TIMER_CTRL);
	writel(next, clkevt_base + TIMER_LOAD);
	writel(ctrl | TIMER_CTRL_ENABLE, clkevt_base + TIMER_CTRL);

	return 0;
}

static struct clock_event_device integrator_clockevent = {
	.name			= "timer1",
	.features		= CLOCK_EVT_FEAT_PERIODIC |
				  CLOCK_EVT_FEAT_ONESHOT,
	.set_state_shutdown	= clkevt_shutdown,
	.set_state_periodic	= clkevt_set_periodic,
	.set_state_oneshot	= clkevt_set_oneshot,
	.tick_resume		= clkevt_shutdown,
	.set_next_event		= clkevt_set_next_event,
	.rating			= 300,
};

static struct irqaction integrator_timer_irq = {
	.name		= "timer",
	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
	.handler	= integrator_timer_interrupt,
	.dev_id		= &integrator_clockevent,
};

static int integrator_clockevent_init(unsigned long inrate,
				      void __iomem *base, int irq)
{
	unsigned long rate = inrate;
	unsigned int ctrl = 0;
	int ret;

	clkevt_base = base;
	/* Calculate and program a divisor */
	if (rate > 0x100000 * HZ) {
		rate /= 256;
		ctrl |= TIMER_CTRL_DIV256;
	} else if (rate > 0x10000 * HZ) {
		rate /= 16;
		ctrl |= TIMER_CTRL_DIV16;
	}
	timer_reload = rate / HZ;
	writel(ctrl, clkevt_base + TIMER_CTRL);

	ret = setup_irq(irq, &integrator_timer_irq);
	if (ret)
		return ret;

	clockevents_config_and_register(&integrator_clockevent,
					rate,
					1,
					0xffffU);
	return 0;
}

static int __init integrator_ap_timer_init_of(struct device_node *node)
{
	const char *path;
	void __iomem *base;
	int err;
	int irq;
	struct clk *clk;
	unsigned long rate;
	struct device_node *alias_node;

	base = of_io_request_and_map(node, 0, "integrator-timer");
	if (IS_ERR(base))
		return PTR_ERR(base);

	clk = of_clk_get(node, 0);
	if (IS_ERR(clk)) {
		pr_err("No clock for %pOFn\n", node);
		return PTR_ERR(clk);
	}
	clk_prepare_enable(clk);
	rate = clk_get_rate(clk);
	writel(0, base + TIMER_CTRL);

	err = of_property_read_string(of_aliases,
				"arm,timer-primary", &path);
	if (err) {
		pr_warn("Failed to read property\n");
		return err;
	}

	alias_node = of_find_node_by_path(path);

	/*
	 * The pointer is used as an identifier not as a pointer, we
	 * can drop the refcount on the of__node immediately after
	 * getting it.
	 */
	of_node_put(alias_node);

	if (node == alias_node)
		/* The primary timer lacks IRQ, use as clocksource */
		return integrator_clocksource_init(rate, base);

	err = of_property_read_string(of_aliases,
				"arm,timer-secondary", &path);
	if (err) {
		pr_warn("Failed to read property\n");
		return err;
	}

	alias_node = of_find_node_by_path(path);

	of_node_put(alias_node);

	if (node == alias_node) {
		/* The secondary timer will drive the clock event */
		irq = irq_of_parse_and_map(node, 0);
		return integrator_clockevent_init(rate, base, irq);
	}

	pr_info("Timer @%p unused\n", base);
	clk_disable_unprepare(clk);

	return 0;
}

TIMER_OF_DECLARE(integrator_ap_timer, "arm,integrator-timer",
		       integrator_ap_timer_init_of);
> 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		RAW - implementation of IP "raw" sockets.
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * Fixes:
 *		Alan Cox	:	verify_area() fixed up
 *		Alan Cox	:	ICMP error handling
 *		Alan Cox	:	EMSGSIZE if you send too big a packet
 *		Alan Cox	: 	Now uses generic datagrams and shared
 *					skbuff library. No more peek crashes,
 *					no more backlogs
 *		Alan Cox	:	Checks sk->broadcast.
 *		Alan Cox	:	Uses skb_free_datagram/skb_copy_datagram
 *		Alan Cox	:	Raw passes ip options too
 *		Alan Cox	:	Setsocketopt added
 *		Alan Cox	:	Fixed error return for broadcasts
 *		Alan Cox	:	Removed wake_up calls
 *		Alan Cox	:	Use ttl/tos
 *		Alan Cox	:	Cleaned up old debugging
 *		Alan Cox	:	Use new kernel side addresses
 *	Arnt Gulbrandsen	:	Fixed MSG_DONTROUTE in raw sockets.
 *		Alan Cox	:	BSD style RAW socket demultiplexing.
 *		Alan Cox	:	Beginnings of mrouted support.
 *		Alan Cox	:	Added IP_HDRINCL option.
 *		Alan Cox	:	Skip broadcast check if BSDism set.
 *		David S. Miller	:	New socket lookup architecture.
 *
 *		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/types.h>
#include <linux/atomic.h>
#include <asm/byteorder.h>
#include <asm/current.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/aio.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/sockios.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/mroute.h>
#include <linux/netdevice.h>
#include <linux/in_route.h>
#include <linux/route.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/dst.h>
#include <net/sock.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/snmp.h>
#include <net/tcp_states.h>
#include <net/inet_common.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>

static struct raw_hashinfo raw_v4_hashinfo = {
	.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};

void raw_hash_sk(struct sock *sk)
{
	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
	struct hlist_head *head;

	head = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)];

	write_lock_bh(&h->lock);
	sk_add_node(sk, head);
	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
	write_unlock_bh(&h->lock);
}
EXPORT_SYMBOL_GPL(raw_hash_sk);

void raw_unhash_sk(struct sock *sk)
{
	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;

	write_lock_bh(&h->lock);
	if (sk_del_node_init(sk))
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
	write_unlock_bh(&h->lock);
}
EXPORT_SYMBOL_GPL(raw_unhash_sk);

static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
		unsigned short num, __be32 raddr, __be32 laddr, int dif)
{
	struct hlist_node *node;

	sk_for_each_from(sk, node) {
		struct inet_sock *inet = inet_sk(sk);

		if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
		    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
		    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
		    !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
			goto found; /* gotcha */
	}
	sk = NULL;
found:
	return sk;
}

/*
 *	0 - deliver
 *	1 - block
 */
static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
{
	struct icmphdr _hdr;
	const struct icmphdr *hdr;

	hdr = skb_header_pointer(skb, skb_transport_offset(skb),
				 sizeof(_hdr), &_hdr);
	if (!hdr)
		return 1;

	if (hdr->type < 32) {
		__u32 data = raw_sk(sk)->filter.data;

		return ((1U << hdr->type) & data) != 0;
	}

	/* Do not block unknown ICMP types */
	return 0;
}

/* IP input processing comes here for RAW socket delivery.
 * Caller owns SKB, so we must make clones.
 *
 * RFC 1122: SHOULD pass TOS value up to the transport layer.
 * -> It does. And not only TOS, but all IP header.
 */
static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
{
	struct sock *sk;
	struct hlist_head *head;
	int delivered = 0;
	struct net *net;

	read_lock(&raw_v4_hashinfo.lock);
	head = &raw_v4_hashinfo.ht[hash];
	if (hlist_empty(head))
		goto out;

	net = dev_net(skb->dev);
	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
			     iph->saddr, iph->daddr,
			     skb->dev->ifindex);

	while (sk) {
		delivered = 1;
		if (iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) {
			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);

			/* Not releasing hash table! */
			if (clone)
				raw_rcv(sk, clone);
		}
		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
				     iph->saddr, iph->daddr,
				     skb->dev->ifindex);
	}
out:
	read_unlock(&raw_v4_hashinfo.lock);
	return delivered;
}

int raw_local_deliver(struct sk_buff *skb, int protocol)
{
	int hash;
	struct sock *raw_sk;

	hash = protocol & (RAW_HTABLE_SIZE - 1);
	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);

	/* If there maybe a raw socket we must check - if not we
	 * don't care less
	 */
	if (raw_sk && !raw_v4_input(skb, ip_hdr(skb), hash))
		raw_sk = NULL;

	return raw_sk != NULL;

}

static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
{
	struct inet_sock *inet = inet_sk(sk);
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	int err = 0;
	int harderr = 0;

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
		ipv4_sk_update_pmtu(skb, sk, info);
	else if (type == ICMP_REDIRECT)
		ipv4_sk_redirect(skb, sk);

	/* Report error on raw socket, if:
	   1. User requested ip_recverr.
	   2. Socket is connected (otherwise the error indication
	      is useless without ip_recverr and error is hard.
	 */
	if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED)
		return;

	switch (type) {
	default:
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	case ICMP_SOURCE_QUENCH:
		return;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		harderr = 1;
		break;
	case ICMP_DEST_UNREACH:
		err = EHOSTUNREACH;
		if (code > NR_ICMP_UNREACH)
			break;
		err = icmp_err_convert[code].errno;
		harderr = icmp_err_convert[code].fatal;
		if (code == ICMP_FRAG_NEEDED) {
			harderr = inet->pmtudisc != IP_PMTUDISC_DONT;
			err = EMSGSIZE;
		}
	}

	if (inet->recverr) {
		const struct iphdr *iph = (const struct iphdr *)skb->data;
		u8 *payload = skb->data + (iph->ihl << 2);

		if (inet->hdrincl)
			payload = skb->data;
		ip_icmp_error(sk, skb, err, 0, info, payload);
	}

	if (inet->recverr || harderr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	}
}

void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
{
	int hash;
	struct sock *raw_sk;
	const struct iphdr *iph;
	struct net *net;

	hash = protocol & (RAW_HTABLE_SIZE - 1);

	read_lock(&raw_v4_hashinfo.lock);
	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
	if (raw_sk != NULL) {
		iph = (const struct iphdr *)skb->data;
		net = dev_net(skb->dev);

		while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
						iph->daddr, iph->saddr,
						skb->dev->ifindex)) != NULL) {
			raw_err(raw_sk, skb, info);
			raw_sk = sk_next(raw_sk);
			iph = (const struct iphdr *)skb->data;
		}
	}
	read_unlock(&raw_v4_hashinfo.lock);
}

static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	/* Charge it to the socket. */

	ipv4_pktinfo_prepare(skb);
	if (sock_queue_rcv_skb(sk, skb) < 0) {
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	return NET_RX_SUCCESS;
}

int raw_rcv(struct sock *sk, struct sk_buff *skb)
{
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
		atomic_inc(&sk->sk_drops);
		kfree_skb(skb);
		return NET_RX_DROP;
	}
	nf_reset(skb);

	skb_push(skb, skb->data - skb_network_header(skb));

	raw_rcv_skb(sk, skb);
	return 0;
}

static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
			   void *from, size_t length,
			   struct rtable **rtp,
			   unsigned int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	struct net *net = sock_net(sk);
	struct iphdr *iph;
	struct sk_buff *skb;
	unsigned int iphlen;
	int err;
	struct rtable *rt = *rtp;
	int hlen, tlen;

	if (length > rt->dst.dev->mtu) {
		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
			       rt->dst.dev->mtu);
		return -EMSGSIZE;
	}
	if (flags&MSG_PROBE)
		goto out;

	hlen = LL_RESERVED_SPACE(rt->dst.dev);
	tlen = rt->dst.dev->needed_tailroom;
	skb = sock_alloc_send_skb(sk,
				  length + hlen + tlen + 15,
				  flags & MSG_DONTWAIT, &err);
	if (skb == NULL)
		goto error;
	skb_reserve(skb, hlen);

	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;
	skb_dst_set(skb, &rt->dst);
	*rtp = NULL;

	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	skb_put(skb, length);

	skb->ip_summed = CHECKSUM_NONE;

	skb->transport_header = skb->network_header;
	err = -EFAULT;
	if (memcpy_fromiovecend((void *)iph, from, 0, length))
		goto error_free;

	iphlen = iph->ihl * 4;

	/*
	 * We don't want to modify the ip header, but we do need to
	 * be sure that it won't cause problems later along the network
	 * stack.  Specifically we want to make sure that iph->ihl is a
	 * sane value.  If ihl points beyond the length of the buffer passed
	 * in, reject the frame as invalid
	 */
	err = -EINVAL;
	if (iphlen > length)
		goto error_free;

	if (iphlen >= sizeof(*iph)) {
		if (!iph->saddr)
			iph->saddr = fl4->saddr;
		iph->check   = 0;
		iph->tot_len = htons(length);
		if (!iph->id)
			ip_select_ident(iph, &rt->dst, NULL);

		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
	}
	if (iph->protocol == IPPROTO_ICMP)
		icmp_out_count(net, ((struct icmphdr *)
			skb_transport_header(skb))->type);

	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
		      rt->dst.dev, dst_output);
	if (err > 0)
		err = net_xmit_errno(err);
	if (err)
		goto error;
out:
	return 0;

error_free:
	kfree_skb(skb);
error:
	IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
	if (err == -ENOBUFS && !inet->recverr)
		err = 0;
	return err;
}

static int raw_probe_proto_opt(struct flowi4 *fl4, struct msghdr *msg)
{
	struct iovec *iov;
	u8 __user *type = NULL;
	u8 __user *code = NULL;
	int probed = 0;
	unsigned int i;

	if (!msg->msg_iov)
		return 0;

	for (i = 0; i < msg->msg_iovlen; i++) {
		iov = &msg->msg_iov[i];
		if (!iov)
			continue;

		switch (fl4->flowi4_proto) {
		case IPPROTO_ICMP:
			/* check if one-byte field is readable or not. */
			if (iov->iov_base && iov->iov_len < 1)
				break;

			if (!type) {
				type = iov->iov_base;
				/* check if code field is readable or not. */
				if (iov->iov_len > 1)
					code = type + 1;
			} else if (!code)
				code = iov->iov_base;

			if (type && code) {
				if (get_user(fl4->fl4_icmp_type, type) ||
				    get_user(fl4->fl4_icmp_code, code))
					return -EFAULT;
				probed = 1;
			}
			break;
		default:
			probed = 1;
			break;
		}
		if (probed)
			break;
	}
	return 0;
}

static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		       size_t len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipcm_cookie ipc;
	struct rtable *rt = NULL;
	struct flowi4 fl4;
	int free = 0;
	__be32 daddr;
	__be32 saddr;
	u8  tos;
	int err;
	struct ip_options_data opt_copy;

	err = -EMSGSIZE;
	if (len > 0xFFFF)
		goto out;

	/*
	 *	Check the flags.
	 */

	err = -EOPNOTSUPP;
	if (msg->msg_flags & MSG_OOB)	/* Mirror BSD error message */
		goto out;               /* compatibility */

	/*
	 *	Get and verify the address.
	 */

	if (msg->msg_namelen) {
		struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
		err = -EINVAL;
		if (msg->msg_namelen < sizeof(*usin))
			goto out;
		if (usin->sin_family != AF_INET) {
			pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n",
				     __func__, current->comm);
			err = -EAFNOSUPPORT;
			if (usin->sin_family)
				goto out;
		}
		daddr = usin->sin_addr.s_addr;
		/* ANK: I did not forget to get protocol from port field.
		 * I just do not know, who uses this weirdness.
		 * IP_HDRINCL is much more convenient.
		 */
	} else {
		err = -EDESTADDRREQ;
		if (sk->sk_state != TCP_ESTABLISHED)
			goto out;
		daddr = inet->inet_daddr;
	}

	ipc.addr = inet->inet_saddr;
	ipc.opt = NULL;
	ipc.tx_flags = 0;
	ipc.oif = sk->sk_bound_dev_if;

	if (msg->msg_controllen) {
		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
		if (err)
			goto out;
		if (ipc.opt)
			free = 1;
	}

	saddr = ipc.addr;
	ipc.addr = daddr;

	if (!ipc.opt) {
		struct ip_options_rcu *inet_opt;

		rcu_read_lock();
		inet_opt = rcu_dereference(inet->inet_opt);
		if (inet_opt) {
			memcpy(&opt_copy, inet_opt,
			       sizeof(*inet_opt) + inet_opt->opt.optlen);
			ipc.opt = &opt_copy.opt;
		}
		rcu_read_unlock();
	}

	if (ipc.opt) {
		err = -EINVAL;
		/* Linux does not mangle headers on raw sockets,
		 * so that IP options + IP_HDRINCL is non-sense.
		 */
		if (inet->hdrincl)
			goto done;
		if (ipc.opt->opt.srr) {
			if (!daddr)
				goto done;
			daddr = ipc.opt->opt.faddr;
		}
	}
	tos = RT_CONN_FLAGS(sk);
	if (msg->msg_flags & MSG_DONTROUTE)
		tos |= RTO_ONLINK;

	if (ipv4_is_multicast(daddr)) {
		if (!ipc.oif)
			ipc.oif = inet->mc_index;
		if (!saddr)
			saddr = inet->mc_addr;
	} else if (!ipc.oif)
		ipc.oif = inet->uc_index;

	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
			   RT_SCOPE_UNIVERSE,
			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
			   inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP,
			   daddr, saddr, 0, 0);

	if (!inet->hdrincl) {
		err = raw_probe_proto_opt(&fl4, msg);
		if (err)
			goto done;
	}

	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
	rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		rt = NULL;
		goto done;
	}

	err = -EACCES;
	if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
		goto done;

	if (msg->msg_flags & MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	if (inet->hdrincl)
		err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,
				      &rt, msg->msg_flags);

	 else {
		if (!ipc.addr)
			ipc.addr = fl4.daddr;
		lock_sock(sk);
		err = ip_append_data(sk, &fl4, ip_generic_getfrag,
				     msg->msg_iov, len, 0,
				     &ipc, &rt, msg->msg_flags);
		if (err)
			ip_flush_pending_frames(sk);
		else if (!(msg->msg_flags & MSG_MORE)) {
			err = ip_push_pending_frames(sk, &fl4);
			if (err == -ENOBUFS && !inet->recverr)
				err = 0;
		}
		release_sock(sk);
	}
done:
	if (free)
		kfree(ipc.opt);
	ip_rt_put(rt);

out:
	if (err < 0)
		return err;
	return len;

do_confirm:
	dst_confirm(&rt->dst);
	if (!(msg->msg_flags & MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto done;
}

static void raw_close(struct sock *sk, long timeout)
{
	/*
	 * Raw sockets may have direct kernel references. Kill them.
	 */
	ip_ra_control(sk, 0, NULL);

	sk_common_release(sk);
}

static void raw_destroy(struct sock *sk)
{
	lock_sock(sk);
	ip_flush_pending_frames(sk);
	release_sock(sk);
}

/* This gets rid of all the nasties in af_inet. -DaveM */
static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
	int ret = -EINVAL;
	int chk_addr_ret;

	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
		goto out;
	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
	ret = -EADDRNOTAVAIL;
	if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
		goto out;
	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->inet_saddr = 0;  /* Use device */
	sk_dst_reset(sk);
	ret = 0;
out:	return ret;
}

/*
 *	This should be easy, if there is something there
 *	we return it, otherwise we block.
 */

static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		       size_t len, int noblock, int flags, int *addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	size_t copied = 0;
	int err = -EOPNOTSUPP;
	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
	struct sk_buff *skb;

	if (flags & MSG_OOB)
		goto out;

	if (addr_len)
		*addr_len = sizeof(*sin);

	if (flags & MSG_ERRQUEUE) {
		err = ip_recv_error(sk, msg, len);
		goto out;
	}

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

	copied = skb->len;
	if (len < copied) {
		msg->msg_flags |= MSG_TRUNC;
		copied = len;
	}

	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	if (err)
		goto done;

	sock_recv_ts_and_drops(msg, sk, skb);

	/* Copy the address. */
	if (sin) {
		sin->sin_family = AF_INET;
		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
		sin->sin_port = 0;
		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
	}
	if (inet->cmsg_flags)
		ip_cmsg_recv(msg, skb);
	if (flags & MSG_TRUNC)
		copied = skb->len;
done:
	skb_free_datagram(sk, skb);
out:
	if (err)
		return err;
	return copied;
}

static int raw_init(struct sock *sk)
{
	struct raw_sock *rp = raw_sk(sk);

	if (inet_sk(sk)->inet_num == IPPROTO_ICMP)
		memset(&rp->filter, 0, sizeof(rp->filter));
	return 0;
}

static int raw_seticmpfilter(struct sock *sk, char __user *optval, int optlen)
{
	if (optlen > sizeof(struct icmp_filter))
		optlen = sizeof(struct icmp_filter);
	if (copy_from_user(&raw_sk(sk)->filter, optval, optlen))
		return -EFAULT;
	return 0;
}

static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *optlen)
{
	int len, ret = -EFAULT;

	if (get_user(len, optlen))
		goto out;
	ret = -EINVAL;
	if (len < 0)
		goto out;
	if (len > sizeof(struct icmp_filter))
		len = sizeof(struct icmp_filter);
	ret = -EFAULT;
	if (put_user(len, optlen) ||
	    copy_to_user(optval, &raw_sk(sk)->filter, len))
		goto out;
	ret = 0;
out:	return ret;
}

static int do_raw_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	if (optname == ICMP_FILTER) {
		if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		else
			return raw_seticmpfilter(sk, optval, optlen);
	}
	return -ENOPROTOOPT;
}

static int raw_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	if (level != SOL_RAW)
		return ip_setsockopt(sk, level, optname, optval, optlen);
	return do_raw_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_raw_setsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, unsigned int optlen)
{
	if (level != SOL_RAW)
		return compat_ip_setsockopt(sk, level, optname, optval, optlen);
	return do_raw_setsockopt(sk, level, optname, optval, optlen);
}
#endif

static int do_raw_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (optname == ICMP_FILTER) {
		if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		else
			return raw_geticmpfilter(sk, optval, optlen);
	}
	return -ENOPROTOOPT;
}

static int raw_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (level != SOL_RAW)
		return ip_getsockopt(sk, level, optname, optval, optlen);
	return do_raw_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_raw_getsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, int __user *optlen)
{
	if (level != SOL_RAW)
		return compat_ip_getsockopt(sk, level, optname, optval, optlen);
	return do_raw_getsockopt(sk, level, optname, optval, optlen);
}
#endif

static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ: {
		int amount = sk_wmem_alloc_get(sk);

		return put_user(amount, (int __user *)arg);
	}
	case SIOCINQ: {
		struct sk_buff *skb;
		int amount = 0;

		spin_lock_bh(&sk->sk_receive_queue.lock);
		skb = skb_peek(&sk->sk_receive_queue);
		if (skb != NULL)
			amount = skb->len;
		spin_unlock_bh(&sk->sk_receive_queue.lock);
		return put_user(amount, (int __user *)arg);
	}

	default:
#ifdef CONFIG_IP_MROUTE
		return ipmr_ioctl(sk, cmd, (void __user *)arg);
#else
		return -ENOIOCTLCMD;
#endif
	}
}

#ifdef CONFIG_COMPAT
static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ:
	case SIOCINQ:
		return -ENOIOCTLCMD;
	default:
#ifdef CONFIG_IP_MROUTE
		return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg));
#else
		return -ENOIOCTLCMD;
#endif
	}
}
#endif