Merge commit 'v2.6.30-rc5' into sched/core

Merge reason: sched/core was on .30-rc1 before, update to latest fixes

Signed-off-by: Ingo Molnar <mingo@elte.hu>

8 files changed, 83 insertions, 197 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 5ba533d234db..831fe1879dc0 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -253,9 +253,9 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	indev = in ? in->name : nulldevname;
 	outdev = out ? out->name : nulldevname;
 
-	rcu_read_lock_bh();
-	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]);
 	back = get_entry(table_base, private->underflow[hook]);
@@ -273,6 +273,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 
 			hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
 				(2 * skb->dev->addr_len);
+
 			ADD_COUNTER(e->counters, hdr_len, 1);
 
 			t = arpt_get_target(e);
@@ -328,8 +329,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 			e = (void *)e + e->next_offset;
 		}
 	} while (!hotdrop);
-
-	rcu_read_unlock_bh();
+	xt_info_rdunlock_bh();
 
 	if (hotdrop)
 		return NF_DROP;
@@ -711,9 +711,12 @@ static void 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.
+	 *
+	 * 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;
 	ARPT_ENTRY_ITERATE(t->entries[curcpu],
@@ -726,73 +729,22 @@ static void get_counters(const struct xt_table_info *t,
 		if (cpu == curcpu)
 			continue;
 		i = 0;
+		xt_info_wrlock(cpu);
 		ARPT_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 arpt_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;
-	ARPT_ENTRY_ITERATE(t->entries[cpu],
-			  t->size,
-			  add_counter_to_entry,
-			  counters,
-			  &i);
 	local_bh_enable();
 }
 
-static inline int
-zero_entry_counter(struct arpt_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);
-		ARPT_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
@@ -802,30 +754,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table)
 	counters = vmalloc_node(countersize, numa_node_id());
 
 	if (counters == NULL)
-		goto nomem;
-
-	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 */
+		return ERR_PTR(-ENOMEM);
 
-	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 copy_entries_to_user(unsigned int total_size,
@@ -1094,8 +1027,9 @@ static int __do_replace(struct net *net, const char *name,
 	    (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()];
 	ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
@@ -1165,10 +1099,23 @@ static int 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 arpt_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;
@@ -1224,26 +1171,26 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
 		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[smp_processor_id()];
+	curcpu = smp_processor_id();
+	loc_cpu_entry = private->entries[curcpu];
+	xt_info_wrlock(curcpu);
 	ARPT_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:
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 810c0b62c7d4..2ec8d7290c40 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -338,10 +338,9 @@ ipt_do_table(struct sk_buff *skb,
 	tgpar.hooknum = hook;
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
-
-	rcu_read_lock_bh();
-	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]);
 
@@ -436,8 +435,7 @@ ipt_do_table(struct sk_buff *skb,
 			e = (void *)e + e->next_offset;
 		}
 	} while (!hotdrop);
-
-	rcu_read_unlock_bh();
+	xt_info_rdunlock_bh();
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
@@ -896,10 +894,13 @@ 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],
@@ -912,74 +913,22 @@ 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
@@ -988,30 +937,11 @@ 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
@@ -1306,8 +1236,9 @@ __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,
@@ -1377,11 +1308,23 @@ 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;
@@ -1437,25 +1380,26 @@ 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:
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index fe65187810f0..3229e0a81ba6 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -211,7 +211,8 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple,
 	minip = ntohl(range->min_ip);
 	maxip = ntohl(range->max_ip);
 	j = jhash_2words((__force u32)tuple->src.u3.ip,
-			 (__force u32)tuple->dst.u3.ip, 0);
+			 range->flags & IP_NAT_RANGE_PERSISTENT ?
+				(__force u32)tuple->dst.u3.ip : 0, 0);
 	j = ((u64)j * (maxip - minip + 1)) >> 32;
 	*var_ipp = htonl(minip + j);
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c40debe51b38..c4c60e9f068a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3397,7 +3397,7 @@ int __init ip_rt_init(void)
 					0,
 					&rt_hash_log,
 					&rt_hash_mask,
-					0);
+					rhash_entries ? 0 : 512 * 1024);
 	memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
 	rt_hash_lock_init();
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fafbec8b073e..1d7f49c6f0ca 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2511,6 +2511,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	struct sk_buff *p;
 	struct tcphdr *th;
 	struct tcphdr *th2;
+	unsigned int len;
 	unsigned int thlen;
 	unsigned int flags;
 	unsigned int mss = 1;
@@ -2531,6 +2532,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 	skb_gro_pull(skb, thlen);
 
+	len = skb_gro_len(skb);
 	flags = tcp_flag_word(th);
 
 	for (; (p = *head); head = &p->next) {
@@ -2561,7 +2563,7 @@ found:
 
 	mss = skb_shinfo(p)->gso_size;
 
-	flush |= (skb_gro_len(skb) > mss) | !skb_gro_len(skb);
+	flush |= (len > mss) | !len;
 	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
 
 	if (flush || skb_gro_receive(head, skb)) {
@@ -2574,7 +2576,7 @@ found:
 	tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
 
 out_check_final:
-	flush = skb_gro_len(skb) < mss;
+	flush = len < mss;
 	flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
 			  TCP_FLAG_SYN | TCP_FLAG_FIN);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2bc8e27a163d..eec3e6f9956c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -597,16 +597,6 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 		tcp_grow_window(sk, skb);
 }
 
-static u32 tcp_rto_min(struct sock *sk)
-{
-	struct dst_entry *dst = __sk_dst_get(sk);
-	u32 rto_min = TCP_RTO_MIN;
-
-	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
-		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
-	return rto_min;
-}
-
 /* Called to compute a smoothed rtt estimate. The data fed to this
  * routine either comes from timestamps, or from segments that were
  * known _not_ to have been retransmitted [see Karn/Partridge
@@ -928,6 +918,8 @@ static void tcp_init_metrics(struct sock *sk)
 	tcp_set_rto(sk);
 	if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
 		goto reset;
+
+cwnd:
 	tp->snd_cwnd = tcp_init_cwnd(tp, dst);
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 	return;
@@ -942,6 +934,7 @@ reset:
 		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
 		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
 	}
+	goto cwnd;
 }
 
 static void tcp_update_reordering(struct sock *sk, const int metric,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 53300fa2359f..59aec609cec6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -778,7 +778,7 @@ static void tcp_adjust_pcount(struct sock *sk, struct sk_buff *skb, int decr)
 
 	if (tp->lost_skb_hint &&
 	    before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
-	    (tcp_is_fack(tp) || TCP_SKB_CB(skb)->sacked))
+	    (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)))
 		tp->lost_cnt_hint -= decr;
 
 	tcp_verify_left_out(tp);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bda08a09357d..7a1d1ce22e66 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -222,7 +222,7 @@ fail:
 	return error;
 }
 
-int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
 {
 	struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
 
@@ -1823,7 +1823,6 @@ EXPORT_SYMBOL(udp_lib_getsockopt);
 EXPORT_SYMBOL(udp_lib_setsockopt);
 EXPORT_SYMBOL(udp_poll);
 EXPORT_SYMBOL(udp_lib_get_port);
-EXPORT_SYMBOL(ipv4_rcv_saddr_equal);
 
 #ifdef CONFIG_PROC_FS
 EXPORT_SYMBOL(udp_proc_register);