Merge branch 'master' of git://1984.lsi.us.es/net-2.6

5 files changed, 49 insertions, 103 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 3fac340..e855fff 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -710,42 +710,25 @@ static void get_counters(const struct xt_table_info *t,
 	struct arpt_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu = get_cpu();
-
-	/* Instead of clearing (by a previous call to memset())
-	 * the counters and using adds, we set the counters
-	 * 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
-	 */
-	local_bh_disable();
-	i = 0;
-	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
-		SET_COUNTER(counters[i], iter->counters.bcnt,
-			    iter->counters.pcnt);
-		++i;
-	}
-	local_bh_enable();
-	/* Processing counters from other cpus, we can let bottom half enabled,
-	 * (preemption is disabled)
-	 */
 
 	for_each_possible_cpu(cpu) {
-		if (cpu == curcpu)
-			continue;
+		seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock;
+
 		i = 0;
-		local_bh_disable();
-		xt_info_wrlock(cpu);
 		xt_entry_foreach(iter, t->entries[cpu], t->size) {
-			ADD_COUNTER(counters[i], iter->counters.bcnt,
-				    iter->counters.pcnt);
+			u64 bcnt, pcnt;
+			unsigned int start;
+
+			do {
+				start = read_seqbegin(lock);
+				bcnt = iter->counters.bcnt;
+				pcnt = iter->counters.pcnt;
+			} while (read_seqretry(lock, start));
+
+			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i;
 		}
-		xt_info_wrunlock(cpu);
-		local_bh_enable();
 	}
-	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -759,7 +742,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	 * about).
 	 */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc(countersize);
+	counters = vzalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1007,7 +990,7 @@ static int __do_replace(struct net *net, const char *name,
 	struct arpt_entry *iter;
 
 	ret = 0;
-	counters = vmalloc(num_counters * sizeof(struct xt_counters));
+	counters = vzalloc(num_counters * sizeof(struct xt_counters));
 	if (!counters) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a846d63..652efea 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -884,42 +884,25 @@ get_counters(const struct xt_table_info *t,
 	struct ipt_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu = get_cpu();
-
-	/* Instead of clearing (by a previous call to memset())
-	 * the counters and using adds, we set the counters
-	 * 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
-	 */
-	local_bh_disable();
-	i = 0;
-	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
-		SET_COUNTER(counters[i], iter->counters.bcnt,
-			    iter->counters.pcnt);
-		++i;
-	}
-	local_bh_enable();
-	/* Processing counters from other cpus, we can let bottom half enabled,
-	 * (preemption is disabled)
-	 */
 
 	for_each_possible_cpu(cpu) {
-		if (cpu == curcpu)
-			continue;
+		seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock;
+
 		i = 0;
-		local_bh_disable();
-		xt_info_wrlock(cpu);
 		xt_entry_foreach(iter, t->entries[cpu], t->size) {
-			ADD_COUNTER(counters[i], iter->counters.bcnt,
-				    iter->counters.pcnt);
+			u64 bcnt, pcnt;
+			unsigned int start;
+
+			do {
+				start = read_seqbegin(lock);
+				bcnt = iter->counters.bcnt;
+				pcnt = iter->counters.pcnt;
+			} while (read_seqretry(lock, start));
+
+			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i; /* macro does multi eval of i */
 		}
-		xt_info_wrunlock(cpu);
-		local_bh_enable();
 	}
-	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -932,7 +915,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	   (other than comefrom, which userspace doesn't care
 	   about). */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc(countersize);
+	counters = vzalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1203,7 +1186,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	struct ipt_entry *iter;
 
 	ret = 0;
-	counters = vmalloc(num_counters * sizeof(struct xt_counters));
+	counters = vzalloc(num_counters * sizeof(struct xt_counters));
 	if (!counters) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 4555823..7d227c6 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -897,42 +897,25 @@ get_counters(const struct xt_table_info *t,
 	struct ip6t_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu = get_cpu();
-
-	/* Instead of clearing (by a previous call to memset())
-	 * the counters and using adds, we set the counters
-	 * 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
-	 */
-	local_bh_disable();
-	i = 0;
-	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
-		SET_COUNTER(counters[i], iter->counters.bcnt,
-			    iter->counters.pcnt);
-		++i;
-	}
-	local_bh_enable();
-	/* Processing counters from other cpus, we can let bottom half enabled,
-	 * (preemption is disabled)
-	 */
 
 	for_each_possible_cpu(cpu) {
-		if (cpu == curcpu)
-			continue;
+		seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock;
+
 		i = 0;
-		local_bh_disable();
-		xt_info_wrlock(cpu);
 		xt_entry_foreach(iter, t->entries[cpu], t->size) {
-			ADD_COUNTER(counters[i], iter->counters.bcnt,
-				    iter->counters.pcnt);
+			u64 bcnt, pcnt;
+			unsigned int start;
+
+			do {
+				start = read_seqbegin(lock);
+				bcnt = iter->counters.bcnt;
+				pcnt = iter->counters.pcnt;
+			} while (read_seqretry(lock, start));
+
+			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i;
 		}
-		xt_info_wrunlock(cpu);
-		local_bh_enable();
 	}
-	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -945,7 +928,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	   (other than comefrom, which userspace doesn't care
 	   about). */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc(countersize);
+	counters = vzalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1216,7 +1199,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	struct ip6t_entry *iter;
 
 	ret = 0;
-	counters = vmalloc(num_counters * sizeof(struct xt_counters));
+	counters = vzalloc(num_counters * sizeof(struct xt_counters));
 	if (!counters) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 7461402..5cb8d30 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -645,25 +645,23 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
 
-	rcu_read_lock();
+	spin_lock_bh(&nf_conntrack_lock);
 	last = (struct nf_conn *)cb->args[1];
 	for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
 restart:
-		hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[cb->args[0]],
+		hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]],
 					 hnnode) {
 			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
 				continue;
 			ct = nf_ct_tuplehash_to_ctrack(h);
-			if (!atomic_inc_not_zero(&ct->ct_general.use))
-				continue;
 			/* Dump entries of a given L3 protocol number.
 			 * If it is not specified, ie. l3proto == 0,
 			 * then dump everything. */
 			if (l3proto && nf_ct_l3num(ct) != l3proto)
-				goto releasect;
+				continue;
 			if (cb->args[1]) {
 				if (ct != last)
-					goto releasect;
+					continue;
 				cb->args[1] = 0;
 			}
 			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
@@ -681,8 +679,6 @@ restart:
 				if (acct)
 					memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]));
 			}
-releasect:
-		nf_ct_put(ct);
 		}
 		if (cb->args[1]) {
 			cb->args[1] = 0;
@@ -690,7 +686,7 @@ releasect:
 		}
 	}
 out:
-	rcu_read_unlock();
+	spin_unlock_bh(&nf_conntrack_lock);
 	if (last)
 		nf_ct_put(last);
 
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8046350..c942376 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1325,7 +1325,8 @@ static int __init xt_init(void)
 
 	for_each_possible_cpu(i) {
 		struct xt_info_lock *lock = &per_cpu(xt_info_locks, i);
-		spin_lock_init(&lock->lock);
+
+		seqlock_init(&lock->lock);
 		lock->readers = 0;
 	}