litmus-rt.git - The LITMUS^RT kernel.

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

diff options

author	Linus Torvalds <torvalds@linux-foundation.org>	2014-09-28 16:45:16 -0400
committer	Linus Torvalds <torvalds@linux-foundation.org>	2014-09-28 16:45:16 -0400
commit	4092dc8f0bcc0963c045460157107d7461a094d7 (patch)
tree	2f659d7ce5b5ea8e9fc27292e69f0b2a84caee04 /include/linux/start_kernel.h
parent	1e3827bf8aebe29af2d6e49b89d85dfae4d0154f (diff)
parent	bfb607451786829430ecdd5bcd51c5dac03e3639 (diff)

Merge branch 'fixes' of git://git.infradead.org/users/vkoul/slave-dma

Pull slave-dmaengine fixes from Vinod Koul: "Two small fixes for omap dmaengine driver which fixes cyclic suspend and resume" * 'fixes' of git://git.infradead.org/users/vkoul/slave-dma: dmaengine: omap-dma: Restore the CLINK_CTRL in resume path dmaengine: omap-dma: Add memory barrier to dma_resume path

Diffstat (limited to 'include/linux/start_kernel.h')

0 files changed, 0 insertions, 0 deletions

emptible code' href='/cgit/cgit.cgi/litmus-rt-pandaboard.git/commit/net/ipv4/icmp.c?id=fdc0bde90a689b9145f2b6f271c03f4c99d09667'>fdc0bde90a6

1
2
3

209
210

211
212

213
214

223
224

255
256
257

264
265

267
268
269

270
271

286
287

288
289

327
328

331
332
333

334
335

338
339

361
362

364
365

368
369

372
373

376
377

392
393

397
398

425
426
427

437
438

492
493

502
503

512
513

534
535

557
558
559

583
584

592
593

601
602
603

617
618

621
622

641
642
643

660
661

688
689

692
693

699
700

733
734

802
803
804

823
824

827
828

859
860
861

862
863
864

945
946

954
955

978
979

981
982
983

997
998

1004
1005

1007
1008

1009
1010

1036
1037

1047
1048

1064
1065
1066

1095
1096
1097

1114
1115
1116

1117
1118
1119

1120
1121

1123
1124
1125

1126
1127
1128

1135
1136

1139
1140

1145
1146

1147
1148
1149

1150
1151

1155
1156

1166
1167

1194
1195
1196

1201
1202

1211
1212

1213
1214

/*
 *	NET3:	Implementation of the ICMP protocol layer.
 *
 *		Alan Cox, <alan@lxorguk.ukuu.org.uk>
 *
 *	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.
 *
 *	Some of the function names and the icmp unreach table for this
 *	module were derived from [icmp.c 1.0.11 06/02/93] by
 *	Ross Biro, Fred N. van Kempen, Mark Evans, Alan Cox, Gerhard Koerting.
 *	Other than that this module is a complete rewrite.
 *
 *	Fixes:
 *	Clemens Fruhwirth	:	introduce global icmp rate limiting
 *					with icmp type masking ability instead
 *					of broken per type icmp timeouts.
 *		Mike Shaver	:	RFC1122 checks.
 *		Alan Cox	:	Multicast ping reply as self.
 *		Alan Cox	:	Fix atomicity lockup in ip_build_xmit
 *					call.
 *		Alan Cox	:	Added 216,128 byte paths to the MTU
 *					code.
 *		Martin Mares	:	RFC1812 checks.
 *		Martin Mares	:	Can be configured to follow redirects
 *					if acting as a router _without_ a
 *					routing protocol (RFC 1812).
 *		Martin Mares	:	Echo requests may be configured to
 *					be ignored (RFC 1812).
 *		Martin Mares	:	Limitation of ICMP error message
 *					transmit rate (RFC 1812).
 *		Martin Mares	:	TOS and Precedence set correctly
 *					(RFC 1812).
 *		Martin Mares	:	Now copying as much data from the
 *					original packet as we can without
 *					exceeding 576 bytes (RFC 1812).
 *	Willy Konynenberg	:	Transparent proxying support.
 *		Keith Owens	:	RFC1191 correction for 4.2BSD based
 *					path MTU bug.
 *		Thomas Quinot	:	ICMP Dest Unreach codes up to 15 are
 *					valid (RFC 1812).
 *		Andi Kleen	:	Check all packet lengths properly
 *					and moved all kfree_skb() up to
 *					icmp_rcv.
 *		Andi Kleen	:	Move the rate limit bookkeeping
 *					into the dest entry and use a token
 *					bucket filter (thanks to ANK). Make
 *					the rates sysctl configurable.
 *		Yu Tianli	:	Fixed two ugly bugs in icmp_send
 *					- IP option length was accounted wrongly
 *					- ICMP header length was not accounted
 *					  at all.
 *              Tristan Greaves :       Added sysctl option to ignore bogus
 *              			broadcast responses from broken routers.
 *
 * To Fix:
 *
 *	- Should use skb_pull() instead of all the manual checking.
 *	  This would also greatly simply some upper layer error handlers. --AK
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/string.h>
#include <linux/netfilter_ipv4.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/protocol.h>
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/init.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <net/inet_common.h>

/*
 *	Build xmit assembly blocks
 */

struct icmp_bxm {
	struct sk_buff *skb;
	int offset;
	int data_len;

	struct {
		struct icmphdr icmph;
		__be32	       times[3];
	} data;
	int head_len;
	struct ip_options replyopts;
	unsigned char  optbuf[40];
};

/* An array of errno for error messages from dest unreach. */
/* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */

struct icmp_err icmp_err_convert[] = {
	{
		.errno = ENETUNREACH,	/* ICMP_NET_UNREACH */
		.fatal = 0,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_HOST_UNREACH */
		.fatal = 0,
	},
	{
		.errno = ENOPROTOOPT	/* ICMP_PROT_UNREACH */,
		.fatal = 1,
	},
	{
		.errno = ECONNREFUSED,	/* ICMP_PORT_UNREACH */
		.fatal = 1,
	},
	{
		.errno = EMSGSIZE,	/* ICMP_FRAG_NEEDED */
		.fatal = 0,
	},
	{
		.errno = EOPNOTSUPP,	/* ICMP_SR_FAILED */
		.fatal = 0,
	},
	{
		.errno = ENETUNREACH,	/* ICMP_NET_UNKNOWN */
		.fatal = 1,
	},
	{
		.errno = EHOSTDOWN,	/* ICMP_HOST_UNKNOWN */
		.fatal = 1,
	},
	{
		.errno = ENONET,	/* ICMP_HOST_ISOLATED */
		.fatal = 1,
	},
	{
		.errno = ENETUNREACH,	/* ICMP_NET_ANO	*/
		.fatal = 1,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_HOST_ANO */
		.fatal = 1,
	},
	{
		.errno = ENETUNREACH,	/* ICMP_NET_UNR_TOS */
		.fatal = 0,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_HOST_UNR_TOS */
		.fatal = 0,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_PKT_FILTERED */
		.fatal = 1,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_PREC_VIOLATION */
		.fatal = 1,
	},
	{
		.errno = EHOSTUNREACH,	/* ICMP_PREC_CUTOFF */
		.fatal = 1,
	},
};

/*
 *	ICMP control array. This specifies what to do with each ICMP.
 */

struct icmp_control {
	void (*handler)(struct sk_buff *skb);
	short   error;		/* This ICMP is classed as an error message */
};

static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];

/*
 *	The ICMP socket(s). This is the most convenient way to flow control
 *	our ICMP output as well as maintain a clean interface throughout
 *	all layers. All Socketless IP sends will soon be gone.
 *
 *	On SMP we have one ICMP socket per-cpu.
 */
static struct sock *icmp_sk(struct net *net)
{
	return net->ipv4.icmp_sk[smp_processor_id()];
}

static inline struct sock *icmp_xmit_lock(struct net *net)
{
	struct sock *sk;

	local_bh_disable();

	sk = icmp_sk(net);

	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
		/* This can happen if the output path signals a
		 * dst_link_failure() for an outgoing ICMP packet.
		 */
		local_bh_enable();
		return NULL;
	}
	return sk;
}

static inline void icmp_xmit_unlock(struct sock *sk)
{
	spin_unlock_bh(&sk->sk_lock.slock);
}

/*
 *	Send an ICMP frame.
 */

/*
 *	Check transmit rate limitation for given message.
 *	The rate information is held in the destination cache now.
 *	This function is generic and could be used for other purposes
 *	too. It uses a Token bucket filter as suggested by Alexey Kuznetsov.
 *
 *	Note that the same dst_entry fields are modified by functions in
 *	route.c too, but these work for packet destinations while xrlim_allow
 *	works for icmp destinations. This means the rate limiting information
 *	for one "ip object" is shared - and these ICMPs are twice limited:
 *	by source and by destination.
 *
 *	RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate
 *			  SHOULD allow setting of rate limits
 *
 * 	Shared between ICMPv4 and ICMPv6.
 */
#define XRLIM_BURST_FACTOR 6
int xrlim_allow(struct dst_entry *dst, int timeout)
{
	unsigned long now, token = dst->rate_tokens;
	int rc = 0;

	now = jiffies;
	token += now - dst->rate_last;
	dst->rate_last = now;
	if (token > XRLIM_BURST_FACTOR * timeout)
		token = XRLIM_BURST_FACTOR * timeout;
	if (token >= timeout) {
		token -= timeout;
		rc = 1;
	}
	dst->rate_tokens = token;
	return rc;
}

static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
		int type, int code)
{
	struct dst_entry *dst = &rt->u.dst;
	int rc = 1;

	if (type > NR_ICMP_TYPES)
		goto out;

	/* Don't limit PMTU discovery. */
	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
		goto out;

	/* No rate limit on loopback */
	if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
		goto out;

	/* Limit if icmp type is enabled in ratemask. */
	if ((1 << type) & net->ipv4.sysctl_icmp_ratemask)
		rc = xrlim_allow(dst, net->ipv4.sysctl_icmp_ratelimit);
out:
	return rc;
}

/*
 *	Maintain the counters used in the SNMP statistics for outgoing ICMP
 */
void icmp_out_count(struct net *net, unsigned char type)
{
	ICMPMSGOUT_INC_STATS(net, type);
	ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS);
}

/*
 *	Checksum each fragment, and on the first include the headers and final
 *	checksum.
 */
static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
			  struct sk_buff *skb)
{
	struct icmp_bxm *icmp_param = (struct icmp_bxm *)from;
	__wsum csum;

	csum = skb_copy_and_csum_bits(icmp_param->skb,
				      icmp_param->offset + offset,
				      to, len, 0);

	skb->csum = csum_block_add(skb->csum, csum, odd);
	if (icmp_pointers[icmp_param->data.icmph.type].error)
		nf_ct_attach(skb, icmp_param->skb);
	return 0;
}

static void icmp_push_reply(struct icmp_bxm *icmp_param,
			    struct ipcm_cookie *ipc, struct rtable **rt)
{
	struct sock *sk;
	struct sk_buff *skb;

	sk = icmp_sk(dev_net((*rt)->u.dst.dev));
	if (ip_append_data(sk, icmp_glue_bits, icmp_param,
			   icmp_param->data_len+icmp_param->head_len,
			   icmp_param->head_len,
			   ipc, rt, MSG_DONTWAIT) < 0)
		ip_flush_pending_frames(sk);
	else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
		struct icmphdr *icmph = icmp_hdr(skb);
		__wsum csum = 0;
		struct sk_buff *skb1;

		skb_queue_walk(&sk->sk_write_queue, skb1) {
			csum = csum_add(csum, skb1->csum);
		}
		csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
						 (char *)icmph,
						 icmp_param->head_len, csum);
		icmph->checksum = csum_fold(csum);
		skb->ip_summed = CHECKSUM_NONE;
		ip_push_pending_frames(sk);
	}
}

/*
 *	Driving logic for building and sending ICMP messages.
 */

static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
{
	struct ipcm_cookie ipc;
	struct rtable *rt = skb_rtable(skb);
	struct net *net = dev_net(rt->u.dst.dev);
	struct sock *sk;
	struct inet_sock *inet;
	__be32 daddr;

	if (ip_options_echo(&icmp_param->replyopts, skb))
		return;

	sk = icmp_xmit_lock(net);
	if (sk == NULL)
		return;
	inet = inet_sk(sk);

	icmp_param->data.icmph.checksum = 0;

	inet->tos = ip_hdr(skb)->tos;
	daddr = ipc.addr = rt->rt_src;
	ipc.opt = NULL;
	ipc.shtx.flags = 0;
	if (icmp_param->replyopts.optlen) {
		ipc.opt = &icmp_param->replyopts;
		if (ipc.opt->srr)
			daddr = icmp_param->replyopts.faddr;
	}
	{
		struct flowi fl = { .nl_u = { .ip4_u =
					      { .daddr = daddr,
						.saddr = rt->rt_spec_dst,
						.tos = RT_TOS(ip_hdr(skb)->tos) } },
				    .proto = IPPROTO_ICMP };
		security_skb_classify_flow(skb, &fl);
		if (ip_route_output_key(net, &rt, &fl))
			goto out_unlock;
	}
	if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type,
			       icmp_param->data.icmph.code))
		icmp_push_reply(icmp_param, &ipc, &rt);
	ip_rt_put(rt);
out_unlock:
	icmp_xmit_unlock(sk);
}


/*
 *	Send an ICMP message in response to a situation
 *
 *	RFC 1122: 3.2.2	MUST send at least the IP header and 8 bytes of header.
 *		  MAY send more (we do).
 *			MUST NOT change this header information.
 *			MUST NOT reply to a multicast/broadcast IP address.
 *			MUST NOT reply to a multicast/broadcast MAC address.
 *			MUST reply to only the first fragment.
 */

void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
{
	struct iphdr *iph;
	int room;
	struct icmp_bxm icmp_param;
	struct rtable *rt = skb_rtable(skb_in);
	struct ipcm_cookie ipc;
	__be32 saddr;
	u8  tos;
	struct net *net;
	struct sock *sk;

	if (!rt)
		goto out;
	net = dev_net(rt->u.dst.dev);

	/*
	 *	Find the original header. It is expected to be valid, of course.
	 *	Check this, icmp_send is called from the most obscure devices
	 *	sometimes.
	 */
	iph = ip_hdr(skb_in);

	if ((u8 *)iph < skb_in->head ||
	    (skb_in->network_header + sizeof(*iph)) > skb_in->tail)
		goto out;

	/*
	 *	No replies to physical multicast/broadcast
	 */
	if (skb_in->pkt_type != PACKET_HOST)
		goto out;

	/*
	 *	Now check at the protocol level
	 */
	if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		goto out;

	/*
	 *	Only reply to fragment 0. We byte re-order the constant
	 *	mask for efficiency.
	 */
	if (iph->frag_off & htons(IP_OFFSET))
		goto out;

	/*
	 *	If we send an ICMP error to an ICMP error a mess would result..
	 */
	if (icmp_pointers[type].error) {
		/*
		 *	We are an error, check if we are replying to an
		 *	ICMP error
		 */
		if (iph->protocol == IPPROTO_ICMP) {
			u8 _inner_type, *itp;

			itp = skb_header_pointer(skb_in,
						 skb_network_header(skb_in) +
						 (iph->ihl << 2) +
						 offsetof(struct icmphdr,
							  type) -
						 skb_in->data,
						 sizeof(_inner_type),
						 &_inner_type);
			if (itp == NULL)
				goto out;

			/*
			 *	Assume any unknown ICMP type is an error. This
			 *	isn't specified by the RFC, but think about it..
			 */
			if (*itp > NR_ICMP_TYPES ||
			    icmp_pointers[*itp].error)
				goto out;
		}
	}

	sk = icmp_xmit_lock(net);
	if (sk == NULL)
		return;

	/*
	 *	Construct source address and options.
	 */

	saddr = iph->daddr;
	if (!(rt->rt_flags & RTCF_LOCAL)) {
		struct net_device *dev = NULL;

		if (rt->fl.iif &&
			net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
			dev = dev_get_by_index(net, rt->fl.iif);

		if (dev) {
			saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
			dev_put(dev);
		} else
			saddr = 0;
	}

	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
					   IPTOS_PREC_INTERNETCONTROL) :
					  iph->tos;

	if (ip_options_echo(&icmp_param.replyopts, skb_in))
		goto out_unlock;


	/*
	 *	Prepare data for ICMP header.
	 */

	icmp_param.data.icmph.type	 = type;
	icmp_param.data.icmph.code	 = code;
	icmp_param.data.icmph.un.gateway = info;


context:
space:
mode: