ip_tables.c

linux 内核源代码

/*
 * Packet matching code.
 *
 * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
 * Copyright (C) 2000-2005 Netfilter Core Team <[e-mail]>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/cache.h>
#include <linux/capability.h>
#include <linux/skbuff.h>
#include <linux/kmod.h>
#include <linux/vmalloc.h>
#include <linux/netdevice.h>
#include <linux/module.h>
#include <linux/icmp.h>
#include <net/ip.h>
#include <net/compat.h>
#include <asm/uaccess.h>
#include <linux/mutex.h>
#include <linux/proc_fs.h>
#include <linux/err.h>
#include <linux/cpumask.h>

#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <[e-mail]>");
MODULE_DESCRIPTION("IPv4 packet filter");

/*#define DEBUG_IP_FIREWALL*/
/*#define DEBUG_ALLOW_ALL*/ /* Useful for remote debugging */
/*#define DEBUG_IP_FIREWALL_USER*/

#ifdef DEBUG_IP_FIREWALL
#define dprintf(format, args...)  printk(format , ## args)
#else
#define dprintf(format, args...)
#endif

#ifdef DEBUG_IP_FIREWALL_USER
#define duprintf(format, args...) printk(format , ## args)
#else
#define duprintf(format, args...)
#endif

#ifdef CONFIG_NETFILTER_DEBUG
#define IP_NF_ASSERT(x)						\
do {								\
	if (!(x))						\
		printk("IP_NF_ASSERT: %s:%s:%u\n",		\
		       __FUNCTION__, __FILE__, __LINE__);	\
} while(0)
#else
#define IP_NF_ASSERT(x)
#endif

#if 0
/* All the better to debug you with... */
#define static
#define inline
#endif

/*
   We keep a set of rules for each CPU, so we can avoid write-locking
   them in the softirq when updating the counters and therefore
   only need to read-lock in the softirq; doing a write_lock_bh() in user
   context stops packets coming through and allows user context to read
   the counters or update the rules.

   Hence the start of any table is given by get_table() below.  */

/* Returns whether matches rule or not. */
static inline int
ip_packet_match(const struct iphdr *ip,
		const char *indev,
		const char *outdev,
		const struct ipt_ip *ipinfo,
		int isfrag)
{
	size_t i;
	unsigned long ret;

#define FWINV(bool,invflg) ((bool) ^ !!(ipinfo->invflags & invflg))

	if (FWINV((ip->saddr&ipinfo->smsk.s_addr) != ipinfo->src.s_addr,
		  IPT_INV_SRCIP)
	    || FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr,
		     IPT_INV_DSTIP)) {
		dprintf("Source or dest mismatch.\n");

		dprintf("SRC: %u.%u.%u.%u. Mask: %u.%u.%u.%u. Target: %u.%u.%u.%u.%s\n",
			NIPQUAD(ip->saddr),
			NIPQUAD(ipinfo->smsk.s_addr),
			NIPQUAD(ipinfo->src.s_addr),
			ipinfo->invflags & IPT_INV_SRCIP ? " (INV)" : "");
		dprintf("DST: %u.%u.%u.%u Mask: %u.%u.%u.%u Target: %u.%u.%u.%u.%s\n",
			NIPQUAD(ip->daddr),
			NIPQUAD(ipinfo->dmsk.s_addr),
			NIPQUAD(ipinfo->dst.s_addr),
			ipinfo->invflags & IPT_INV_DSTIP ? " (INV)" : "");
		return 0;
	}

	/* Look for ifname matches; this should unroll nicely. */
	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
		ret |= (((const unsigned long *)indev)[i]
			^ ((const unsigned long *)ipinfo->iniface)[i])
			& ((const unsigned long *)ipinfo->iniface_mask)[i];
	}

	if (FWINV(ret != 0, IPT_INV_VIA_IN)) {
		dprintf("VIA in mismatch (%s vs %s).%s\n",
			indev, ipinfo->iniface,
			ipinfo->invflags&IPT_INV_VIA_IN ?" (INV)":"");
		return 0;
	}

	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
		ret |= (((const unsigned long *)outdev)[i]
			^ ((const unsigned long *)ipinfo->outiface)[i])
			& ((const unsigned long *)ipinfo->outiface_mask)[i];
	}

	if (FWINV(ret != 0, IPT_INV_VIA_OUT)) {
		dprintf("VIA out mismatch (%s vs %s).%s\n",
			outdev, ipinfo->outiface,
			ipinfo->invflags&IPT_INV_VIA_OUT ?" (INV)":"");
		return 0;
	}

	/* Check specific protocol */
	if (ipinfo->proto
	    && FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) {
		dprintf("Packet protocol %hi does not match %hi.%s\n",
			ip->protocol, ipinfo->proto,
			ipinfo->invflags&IPT_INV_PROTO ? " (INV)":"");
		return 0;
	}

	/* If we have a fragment rule but the packet is not a fragment
	 * then we return zero */
	if (FWINV((ipinfo->flags&IPT_F_FRAG) && !isfrag, IPT_INV_FRAG)) {
		dprintf("Fragment rule but not fragment.%s\n",
			ipinfo->invflags & IPT_INV_FRAG ? " (INV)" : "");
		return 0;
	}

	return 1;
}

static inline bool
ip_checkentry(const struct ipt_ip *ip)
{
	if (ip->flags & ~IPT_F_MASK) {
		duprintf("Unknown flag bits set: %08X\n",
			 ip->flags & ~IPT_F_MASK);
		return false;
	}
	if (ip->invflags & ~IPT_INV_MASK) {
		duprintf("Unknown invflag bits set: %08X\n",
			 ip->invflags & ~IPT_INV_MASK);
		return false;
	}
	return true;
}

static unsigned int
ipt_error(struct sk_buff *skb,
	  const struct net_device *in,
	  const struct net_device *out,
	  unsigned int hooknum,
	  const struct xt_target *target,
	  const void *targinfo)
{
	if (net_ratelimit())
		printk("ip_tables: error: `%s'\n", (char *)targinfo);

	return NF_DROP;
}

static inline
bool do_match(struct ipt_entry_match *m,
	      const struct sk_buff *skb,
	      const struct net_device *in,
	      const struct net_device *out,
	      int offset,
	      bool *hotdrop)
{
	/* Stop iteration if it doesn't match */
	if (!m->u.kernel.match->match(skb, in, out, m->u.kernel.match, m->data,
				      offset, ip_hdrlen(skb), hotdrop))
		return true;
	else
		return false;
}

static inline struct ipt_entry *
get_entry(void *base, unsigned int offset)
{
	return (struct ipt_entry *)(base + offset);
}

/* All zeroes == unconditional rule. */
static inline int
unconditional(const struct ipt_ip *ip)
{
	unsigned int i;

	for (i = 0; i < sizeof(*ip)/sizeof(__u32); i++)
		if (((__u32 *)ip)[i])
			return 0;

	return 1;
}

#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
static const char *hooknames[] = {
	[NF_IP_PRE_ROUTING]		= "PREROUTING",
	[NF_IP_LOCAL_IN]		= "INPUT",
	[NF_IP_FORWARD]			= "FORWARD",
	[NF_IP_LOCAL_OUT]		= "OUTPUT",
	[NF_IP_POST_ROUTING]		= "POSTROUTING",
};

enum nf_ip_trace_comments {
	NF_IP_TRACE_COMMENT_RULE,
	NF_IP_TRACE_COMMENT_RETURN,
	NF_IP_TRACE_COMMENT_POLICY,
};

static const char *comments[] = {
	[NF_IP_TRACE_COMMENT_RULE]	= "rule",
	[NF_IP_TRACE_COMMENT_RETURN]	= "return",
	[NF_IP_TRACE_COMMENT_POLICY]	= "policy",
};

static struct nf_loginfo trace_loginfo = {
	.type = NF_LOG_TYPE_LOG,
	.u = {
		.log = {
			.level = 4,
			.logflags = NF_LOG_MASK,
		},
	},
};

static inline int
get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
		      char *hookname, char **chainname,
		      char **comment, unsigned int *rulenum)
{
	struct ipt_standard_target *t = (void *)ipt_get_target(s);

	if (strcmp(t->target.u.kernel.target->name, IPT_ERROR_TARGET) == 0) {
		/* Head of user chain: ERROR target with chainname */
		*chainname = t->target.data;
		(*rulenum) = 0;
	} else if (s == e) {
		(*rulenum)++;

		if (s->target_offset == sizeof(struct ipt_entry)
		   && strcmp(t->target.u.kernel.target->name,
			     IPT_STANDARD_TARGET) == 0
		   && t->verdict < 0
		   && unconditional(&s->ip)) {
			/* Tail of chains: STANDARD target (return/policy) */
			*comment = *chainname == hookname
				? (char *)comments[NF_IP_TRACE_COMMENT_POLICY]
				: (char *)comments[NF_IP_TRACE_COMMENT_RETURN];
		}
		return 1;
	} else
		(*rulenum)++;

	return 0;
}

static void trace_packet(struct sk_buff *skb,
			 unsigned int hook,
			 const struct net_device *in,
			 const struct net_device *out,
			 char *tablename,
			 struct xt_table_info *private,
			 struct ipt_entry *e)
{
	void *table_base;
	struct ipt_entry *root;
	char *hookname, *chainname, *comment;
	unsigned int rulenum = 0;

	table_base = (void *)private->entries[smp_processor_id()];
	root = get_entry(table_base, private->hook_entry[hook]);

	hookname = chainname = (char *)hooknames[hook];
	comment = (char *)comments[NF_IP_TRACE_COMMENT_RULE];

	IPT_ENTRY_ITERATE(root,
			  private->size - private->hook_entry[hook],
			  get_chainname_rulenum,
			  e, hookname, &chainname, &comment, &rulenum);

	nf_log_packet(AF_INET, hook, skb, in, out, &trace_loginfo,
		      "TRACE: %s:%s:%s:%u ",
		      tablename, chainname, comment, rulenum);
}
#endif

/* Returns one of the generic firewall policies, like NF_ACCEPT. */
unsigned int
ipt_do_table(struct sk_buff *skb,
	     unsigned int hook,
	     const struct net_device *in,
	     const struct net_device *out,
	     struct xt_table *table)
{
	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
	u_int16_t offset;
	struct iphdr *ip;
	u_int16_t datalen;
	bool hotdrop = false;
	/* Initializing verdict to NF_DROP keeps gcc happy. */
	unsigned int verdict = NF_DROP;
	const char *indev, *outdev;
	void *table_base;
	struct ipt_entry *e, *back;
	struct xt_table_info *private;

	/* Initialization */
	ip = ip_hdr(skb);
	datalen = skb->len - ip->ihl * 4;
	indev = in ? in->name : nulldevname;
	outdev = out ? out->name : nulldevname;
	/* We handle fragments by dealing with the first fragment as
	 * if it was a normal packet.  All other fragments are treated
	 * normally, except that they will NEVER match rules that ask
	 * things we don't know, ie. tcp syn flag or ports).  If the
	 * rule is also a fragment-specific rule, non-fragments won't
	 * match it. */
	offset = ntohs(ip->frag_off) & IP_OFFSET;

	read_lock_bh(&table->lock);
	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
	private = table->private;
	table_base = (void *)private->entries[smp_processor_id()];
	e = get_entry(table_base, private->hook_entry[hook]);

	/* For return from builtin chain */
	back = get_entry(table_base, private->underflow[hook]);

	do {
		IP_NF_ASSERT(e);
		IP_NF_ASSERT(back);
		if (ip_packet_match(ip, indev, outdev, &e->ip, offset)) {
			struct ipt_entry_target *t;

			if (IPT_MATCH_ITERATE(e, do_match,
					      skb, in, out,
					      offset, &hotdrop) != 0)
				goto no_match;

			ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);

			t = ipt_get_target(e);
			IP_NF_ASSERT(t->u.kernel.target);

#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
			/* The packet is traced: log it */
			if (unlikely(skb->nf_trace))
				trace_packet(skb, hook, in, out,
					     table->name, private, e);
#endif
			/* Standard target? */
			if (!t->u.kernel.target->target) {
				int v;

				v = ((struct ipt_standard_target *)t)->verdict;
				if (v < 0) {
					/* Pop from stack? */
					if (v != IPT_RETURN) {
						verdict = (unsigned)(-v) - 1;
						break;
					}
					e = back;
					back = get_entry(table_base,
							 back->comefrom);
					continue;
				}
				if (table_base + v != (void *)e + e->next_offset
				    && !(e->ip.flags & IPT_F_GOTO)) {
					/* Save old back ptr in next entry */
					struct ipt_entry *next
						= (void *)e + e->next_offset;
					next->comefrom
						= (void *)back - table_base;
					/* set back pointer to next entry */
					back = next;
				}

				e = get_entry(table_base, v);
			} else {
				/* Targets which reenter must return
				   abs. verdicts */
#ifdef CONFIG_NETFILTER_DEBUG
				((struct ipt_entry *)table_base)->comefrom
					= 0xeeeeeeec;
#endif
				verdict = t->u.kernel.target->target(skb,
								     in, out,
								     hook,
								     t->u.kernel.target,
								     t->data);

#ifdef CONFIG_NETFILTER_DEBUG
				if (((struct ipt_entry *)table_base)->comefrom
				    != 0xeeeeeeec
				    && verdict == IPT_CONTINUE) {
					printk("Target %s reentered!\n",
					       t->u.kernel.target->name);
					verdict = NF_DROP;
				}
				((struct ipt_entry *)table_base)->comefrom
					= 0x57acc001;
#endif
				/* Target might have changed stuff. */
				ip = ip_hdr(skb);
				datalen = skb->len - ip->ihl * 4;

				if (verdict == IPT_CONTINUE)
					e = (void *)e + e->next_offset;
				else
					/* Verdict */
					break;
			}
		} else {

		no_match:
			e = (void *)e + e->next_offset;
		}
	} while (!hotdrop);

	read_unlock_bh(&table->lock);

#ifdef DEBUG_ALLOW_ALL
	return NF_ACCEPT;
#else
	if (hotdrop)
		return NF_DROP;
	else return verdict;
#endif
}

/* Figures out from what hook each rule can be called: returns 0 if
   there are loops.  Puts hook bitmask in comefrom. */
static int
mark_source_chains(struct xt_table_info *newinfo,
		   unsigned int valid_hooks, void *entry0)
{
	unsigned int hook;

	/* No recursion; use packet counter to save back ptrs (reset
	   to 0 as we leave), and comefrom to save source hook bitmask */
	for (hook = 0; hook < NF_IP_NUMHOOKS; hook++) {
		unsigned int pos = newinfo->hook_entry[hook];
		struct ipt_entry *e
			= (struct ipt_entry *)(entry0 + pos);

		if (!(valid_hooks & (1 << hook)))
			continue;

		/* Set initial back pointer. */
		e->counters.pcnt = pos;

		for (;;) {
			struct ipt_standard_target *t
				= (void *)ipt_get_target(e);
			int visited = e->comefrom & (1 << hook);

			if (e->comefrom & (1 << NF_IP_NUMHOOKS)) {
				printk("iptables: loop hook %u pos %u %08X.\n",
				       hook, pos, e->comefrom);
				return 0;
			}
			e->comefrom
				|= ((1 << hook) | (1 << NF_IP_NUMHOOKS));

			/* Unconditional return/END. */
			if ((e->target_offset == sizeof(struct ipt_entry)
			    && (strcmp(t->target.u.user.name,
				       IPT_STANDARD_TARGET) == 0)
			    && t->verdict < 0
			    && unconditional(&e->ip)) || visited) {
				unsigned int oldpos, size;

				if (t->verdict < -NF_MAX_VERDICT - 1) {
					duprintf("mark_source_chains: bad "
						"negative verdict (%i)\n",
								t->verdict);
					return 0;
				}

				/* Return: backtrack through the last
				   big jump. */
				do {
					e->comefrom ^= (1<<NF_IP_NUMHOOKS);
#ifdef DEBUG_IP_FIREWALL_USER
					if (e->comefrom
					    & (1 << NF_IP_NUMHOOKS)) {
						duprintf("Back unset "
							 "on hook %u "
							 "rule %u\n",
							 hook, pos);
					}
#endif
					oldpos = pos;
					pos = e->counters.pcnt;
					e->counters.pcnt = 0;

					/* We're at the start. */
					if (pos == oldpos)
						goto next;

					e = (struct ipt_entry *)
						(entry0 + pos);
				} while (oldpos == pos + e->next_offset);

				/* Move along one */
				size = e->next_offset;
				e = (struct ipt_entry *)
					(entry0 + pos + size);
				e->counters.pcnt = pos;
				pos += size;
			} else {
				int newpos = t->verdict;

				if (strcmp(t->target.u.user.name,
					   IPT_STANDARD_TARGET) == 0
				    && newpos >= 0) {
					if (newpos > newinfo->size -
						sizeof(struct ipt_entry)) {
						duprintf("mark_source_chains: "
							"bad verdict (%i)\n",
								newpos);
						return 0;
					}
					/* This a jump; chase it. */
					duprintf("Jump rule %u -> %u\n",
						 pos, newpos);
				} else {
					/* ... this is a fallthru */
					newpos = pos + e->next_offset;
				}
				e = (struct ipt_entry *)
					(entry0 + newpos);
				e->counters.pcnt = pos;
				pos = newpos;
			}
		}
		next:
		duprintf("Finished chain %u\n", hook);
	}
	return 1;
}

static inline int
cleanup_match(struct ipt_entry_match *m, unsigned int *i)
{
	if (i && (*i)-- == 0)
		return 1;

	if (m->u.kernel.match->destroy)
		m->u.kernel.match->destroy(m->u.kernel.match, m->data);
	module_put(m->u.kernel.match->me);
	return 0;
}

static inline int
check_entry(struct ipt_entry *e, const char *name)
{