X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Fnetfilter%2Fip_tables.c;h=5bf7c3f185da576d37ca0c0271ca2df71a61a1f9;hb=f87fb666bb00a7afcbd7992d236e42ac544996f9;hp=e5294aec967d45762cf15e1aaed577b83455a8c5;hpb=08361aa807ae5e5007cd226ca9e34287512de737;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index e5294ae..5bf7c3f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -74,25 +74,6 @@ do {								\
 
    Hence the start of any table is given by get_table() below.  */
 
-static unsigned long ifname_compare(const char *_a, const char *_b,
-				    const unsigned char *_mask)
-{
-	const unsigned long *a = (const unsigned long *)_a;
-	const unsigned long *b = (const unsigned long *)_b;
-	const unsigned long *mask = (const unsigned long *)_mask;
-	unsigned long ret;
-
-	ret = (a[0] ^ b[0]) & mask[0];
-	if (IFNAMSIZ > sizeof(unsigned long))
-		ret |= (a[1] ^ b[1]) & mask[1];
-	if (IFNAMSIZ > 2 * sizeof(unsigned long))
-		ret |= (a[2] ^ b[2]) & mask[2];
-	if (IFNAMSIZ > 3 * sizeof(unsigned long))
-		ret |= (a[3] ^ b[3]) & mask[3];
-	BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long));
-	return ret;
-}
-
 /* Returns whether matches rule or not. */
 /* Performance critical - called for every packet */
 static inline bool
@@ -121,7 +102,7 @@ ip_packet_match(const struct iphdr *ip,
 		return false;
 	}
 
-	ret = ifname_compare(indev, ipinfo->iniface, ipinfo->iniface_mask);
+	ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask);
 
 	if (FWINV(ret != 0, IPT_INV_VIA_IN)) {
 		dprintf("VIA in mismatch (%s vs %s).%s\n",
@@ -130,7 +111,7 @@ ip_packet_match(const struct iphdr *ip,
 		return false;
 	}
 
-	ret = ifname_compare(outdev, ipinfo->outiface, ipinfo->outiface_mask);
+	ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask);
 
 	if (FWINV(ret != 0, IPT_INV_VIA_OUT)) {
 		dprintf("VIA out mismatch (%s vs %s).%s\n",
@@ -257,8 +238,8 @@ static struct nf_loginfo trace_loginfo = {
 /* Mildly perf critical (only if packet tracing is on) */
 static inline int
 get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
-		      char *hookname, char **chainname,
-		      char **comment, unsigned int *rulenum)
+		      const char *hookname, const char **chainname,
+		      const char **comment, unsigned int *rulenum)
 {
 	struct ipt_standard_target *t = (void *)ipt_get_target(s);
 
@@ -276,8 +257,8 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
 		   && 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];
+				? comments[NF_IP_TRACE_COMMENT_POLICY]
+				: comments[NF_IP_TRACE_COMMENT_RETURN];
 		}
 		return 1;
 	} else
@@ -296,14 +277,14 @@ static void trace_packet(struct sk_buff *skb,
 {
 	void *table_base;
 	const struct ipt_entry *root;
-	char *hookname, *chainname, *comment;
+	const char *hookname, *chainname, *comment;
 	unsigned int rulenum = 0;
 
-	table_base = (void *)private->entries[smp_processor_id()];
+	table_base = 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];
+	hookname = chainname = hooknames[hook];
+	comment = comments[NF_IP_TRACE_COMMENT_RULE];
 
 	IPT_ENTRY_ITERATE(root,
 			  private->size - private->hook_entry[hook],
@@ -316,6 +297,12 @@ static void trace_packet(struct sk_buff *skb,
 }
 #endif
 
+static inline __pure
+struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry)
+{
+	return (void *)entry + entry->next_offset;
+}
+
 /* Returns one of the generic firewall policies, like NF_ACCEPT. */
 unsigned int
 ipt_do_table(struct sk_buff *skb,
@@ -324,6 +311,8 @@ ipt_do_table(struct sk_buff *skb,
 	     const struct net_device *out,
 	     struct xt_table *table)
 {
+#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom
+
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	const struct iphdr *ip;
 	u_int16_t datalen;
@@ -354,13 +343,12 @@ ipt_do_table(struct sk_buff *skb,
 	mtpar.in      = tgpar.in  = in;
 	mtpar.out     = tgpar.out = out;
 	mtpar.family  = tgpar.family = NFPROTO_IPV4;
-	tgpar.hooknum = hook;
+	mtpar.hooknum = tgpar.hooknum = hook;
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
-
-	rcu_read_lock();
-	private = rcu_dereference(table->private);
-	table_base = rcu_dereference(private->entries[smp_processor_id()]);
+	xt_info_rdlock_bh();
+	private = table->private;
+	table_base = private->entries[smp_processor_id()];
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
@@ -368,95 +356,86 @@ ipt_do_table(struct sk_buff *skb,
 	back = get_entry(table_base, private->underflow[hook]);
 
 	do {
+		struct ipt_entry_target *t;
+
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
-		if (ip_packet_match(ip, indev, outdev,
-		    &e->ip, mtpar.fragoff)) {
-			struct ipt_entry_target *t;
-
-			if (IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0)
-				goto no_match;
+		if (!ip_packet_match(ip, indev, outdev,
+		    &e->ip, mtpar.fragoff) ||
+		    IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) {
+			e = ipt_next_entry(e);
+			continue;
+		}
 
-			ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
+		ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
 
-			t = ipt_get_target(e);
-			IP_NF_ASSERT(t->u.kernel.target);
+		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);
+		/* 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;
+		/* 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 != ipt_next_entry(e)
+			    && !(e->ip.flags & IPT_F_GOTO)) {
+				/* Save old back ptr in next entry */
+				struct ipt_entry *next = ipt_next_entry(e);
+				next->comefrom = (void *)back - table_base;
+				/* set back pointer to next entry */
+				back = next;
+			}
+
+			e = get_entry(table_base, v);
+			continue;
+		}
+
+		/* Targets which reenter must return
+		   abs. verdicts */
+		tgpar.target   = t->u.kernel.target;
+		tgpar.targinfo = t->data;
+
 
-				e = get_entry(table_base, v);
-			} else {
-				/* Targets which reenter must return
-				   abs. verdicts */
-				tgpar.target   = t->u.kernel.target;
-				tgpar.targinfo = t->data;
 #ifdef CONFIG_NETFILTER_DEBUG
-				((struct ipt_entry *)table_base)->comefrom
-					= 0xeeeeeeec;
+		tb_comefrom = 0xeeeeeeec;
 #endif
-				verdict = t->u.kernel.target->target(skb,
-								     &tgpar);
+		verdict = t->u.kernel.target->target(skb, &tgpar);
 #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;
+		if (comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) {
+			printk("Target %s reentered!\n",
+			       t->u.kernel.target->name);
+			verdict = NF_DROP;
+		}
+		tb_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 {
+		/* Target might have changed stuff. */
+		ip = ip_hdr(skb);
+		datalen = skb->len - ip->ihl * 4;
 
-		no_match:
-			e = (void *)e + e->next_offset;
-		}
+		if (verdict == IPT_CONTINUE)
+			e = ipt_next_entry(e);
+		else
+			/* Verdict */
+			break;
 	} while (!hotdrop);
-
-	rcu_read_unlock();
+	xt_info_rdunlock_bh();
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
@@ -465,6 +444,8 @@ ipt_do_table(struct sk_buff *skb,
 		return NF_DROP;
 	else return verdict;
 #endif
+
+#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -507,7 +488,9 @@ mark_source_chains(struct xt_table_info *newinfo,
 			    && unconditional(&e->ip)) || visited) {
 				unsigned int oldpos, size;
 
-				if (t->verdict < -NF_MAX_VERDICT - 1) {
+				if ((strcmp(t->target.u.user.name,
+			    		    IPT_STANDARD_TARGET) == 0) &&
+				    t->verdict < -NF_MAX_VERDICT - 1) {
 					duprintf("mark_source_chains: bad "
 						"negative verdict (%i)\n",
 								t->verdict);
@@ -913,10 +896,13 @@ get_counters(const struct xt_table_info *t,
 
 	/* Instead of clearing (by a previous call to memset())
 	 * the counters and using adds, we set the counters
-	 * with data used by 'current' CPU
-	 * We dont care about preemption here.
+	 * with data used by 'current' CPU.
+	 *
+	 * Bottom half has to be disabled to prevent deadlock
+	 * if new softirq were to run and call ipt_do_table
 	 */
-	curcpu = raw_smp_processor_id();
+	local_bh_disable();
+	curcpu = smp_processor_id();
 
 	i = 0;
 	IPT_ENTRY_ITERATE(t->entries[curcpu],
@@ -929,74 +915,22 @@ get_counters(const struct xt_table_info *t,
 		if (cpu == curcpu)
 			continue;
 		i = 0;
+		xt_info_wrlock(cpu);
 		IPT_ENTRY_ITERATE(t->entries[cpu],
 				  t->size,
 				  add_entry_to_counter,
 				  counters,
 				  &i);
+		xt_info_wrunlock(cpu);
 	}
-
-}
-
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct ipt_entry *e,
-		     const struct xt_counters addme[],
-		     unsigned int *i)
-{
-	ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
-	(*i)++;
-	return 0;
-}
-
-/* Take values from counters and add them back onto the current cpu */
-static void put_counters(struct xt_table_info *t,
-			 const struct xt_counters counters[])
-{
-	unsigned int i, cpu;
-
-	local_bh_disable();
-	cpu = smp_processor_id();
-	i = 0;
-	IPT_ENTRY_ITERATE(t->entries[cpu],
-			  t->size,
-			  add_counter_to_entry,
-			  counters,
-			  &i);
 	local_bh_enable();
 }
 
-
-static inline int
-zero_entry_counter(struct ipt_entry *e, void *arg)
-{
-	e->counters.bcnt = 0;
-	e->counters.pcnt = 0;
-	return 0;
-}
-
-static void
-clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
-{
-	unsigned int cpu;
-	const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
-
-	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
-	for_each_possible_cpu(cpu) {
-		memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
-		IPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
-				  zero_entry_counter, NULL);
-	}
-}
-
 static struct xt_counters * alloc_counters(struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
 	struct xt_table_info *private = table->private;
-	struct xt_table_info *info;
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -1005,30 +939,11 @@ static struct xt_counters * alloc_counters(struct xt_table *table)
 	counters = vmalloc_node(countersize, numa_node_id());
 
 	if (counters == NULL)
-		goto nomem;
+		return ERR_PTR(-ENOMEM);
 
-	info = xt_alloc_table_info(private->size);
-	if (!info)
-		goto free_counters;
-
-	clone_counters(info, private);
-
-	mutex_lock(&table->lock);
-	xt_table_entry_swap_rcu(private, info);
-	synchronize_net();	/* Wait until smoke has cleared */
-
-	get_counters(info, counters);
-	put_counters(private, counters);
-	mutex_unlock(&table->lock);
-
-	xt_free_table_info(info);
+	get_counters(private, counters);
 
 	return counters;
-
- free_counters:
-	vfree(counters);
- nomem:
-	return ERR_PTR(-ENOMEM);
 }
 
 static int
@@ -1323,8 +1238,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	    (newinfo->number <= oldinfo->initial_entries))
 		module_put(t->me);
 
-	/* Get the old counters. */
+	/* Get the old counters, and synchronize with replace */
 	get_counters(oldinfo, counters);
+
 	/* Decrease module usage counts and free resource */
 	loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
 	IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
@@ -1394,11 +1310,23 @@ do_replace(struct net *net, void __user *user, unsigned int len)
 	return ret;
 }
 
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct ipt_entry *e,
+		     const struct xt_counters addme[],
+		     unsigned int *i)
+{
+	ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+	(*i)++;
+	return 0;
+}
 
 static int
 do_add_counters(struct net *net, void __user *user, unsigned int len, int compat)
 {
-	unsigned int i;
+	unsigned int i, curcpu;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
 	unsigned int num_counters;
@@ -1454,25 +1382,26 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat
 		goto free;
 	}
 
-	mutex_lock(&t->lock);
+	local_bh_disable();
 	private = t->private;
 	if (private->number != num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
 
-	preempt_disable();
 	i = 0;
 	/* Choose the copy that is on our node */
-	loc_cpu_entry = private->entries[raw_smp_processor_id()];
+	curcpu = smp_processor_id();
+	loc_cpu_entry = private->entries[curcpu];
+	xt_info_wrlock(curcpu);
 	IPT_ENTRY_ITERATE(loc_cpu_entry,
 			  private->size,
 			  add_counter_to_entry,
 			  paddc,
 			  &i);
-	preempt_enable();
+	xt_info_wrunlock(curcpu);
  unlock_up_free:
-	mutex_unlock(&t->lock);
+	local_bh_enable();
 	xt_table_unlock(t);
 	module_put(t->me);
  free:
@@ -2231,7 +2160,7 @@ static bool icmp_checkentry(const struct xt_mtchk_param *par)
 static struct xt_target ipt_standard_target __read_mostly = {
 	.name		= IPT_STANDARD_TARGET,
 	.targetsize	= sizeof(int),
-	.family		= AF_INET,
+	.family		= NFPROTO_IPV4,
 #ifdef CONFIG_COMPAT
 	.compatsize	= sizeof(compat_int_t),
 	.compat_from_user = compat_standard_from_user,
@@ -2243,7 +2172,7 @@ static struct xt_target ipt_error_target __read_mostly = {
 	.name		= IPT_ERROR_TARGET,
 	.target		= ipt_error,
 	.targetsize	= IPT_FUNCTION_MAXNAMELEN,
-	.family		= AF_INET,
+	.family		= NFPROTO_IPV4,
 };
 
 static struct nf_sockopt_ops ipt_sockopts = {
@@ -2269,17 +2198,17 @@ static struct xt_match icmp_matchstruct __read_mostly = {
 	.matchsize	= sizeof(struct ipt_icmp),
 	.checkentry	= icmp_checkentry,
 	.proto		= IPPROTO_ICMP,
-	.family		= AF_INET,
+	.family		= NFPROTO_IPV4,
 };
 
 static int __net_init ip_tables_net_init(struct net *net)
 {
-	return xt_proto_init(net, AF_INET);
+	return xt_proto_init(net, NFPROTO_IPV4);
 }
 
 static void __net_exit ip_tables_net_exit(struct net *net)
 {
-	xt_proto_fini(net, AF_INET);
+	xt_proto_fini(net, NFPROTO_IPV4);
 }
 
 static struct pernet_operations ip_tables_net_ops = {