Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
netfilter updates for net-next

The following patchset contains netfilter updates for net-next, just a
bunch of cleanups and small enhancement to selectively flush conntracks
in ctnetlink, more specifically the patches are:

1) Rise default number of buckets in conntrack from 16384 to 65536 in
systems with >= 4GBytes, patch from Marcelo Leitner.

2) Small refactor to save one level on indentation in xt_osf, from
Joe Perches.

3) Remove unnecessary sizeof(char) in nf_log, from Fabian Frederick.

4) Another small cleanup to remove redundant variable in nfnetlink,
from Duan Jiong.

5) Fix compilation warning in nfnetlink_cthelper on parisc, from
Chen Gang.

6) Fix wrong format in debugging for ctseqadj, from Gao feng.

7) Selective conntrack flushing through the mark for ctnetlink, patch
from Kristian Evensen.

8) Remove nf_ct_conntrack_flush_report() exported symbol now that is
not required anymore after the selective flushing patch, again from
Kristian.
====================

Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/nf_conntrack-sysctl.txt

···
 	Size of hash table. If not specified as parameter during module
 	loading, the default size is calculated by dividing total memory
 	by 16384 to determine the number of buckets but the hash table will
-	never have fewer than 32 or more than 16384 buckets.
+	never have fewer than 32 and limited to 16384 buckets. For systems
+	with more than 4GB of memory it will be 65536 buckets.
 
 nf_conntrack_checksum - BOOLEAN
 	0 - disabled

include/net/netfilter/nf_conntrack.h

···
 int nf_conntrack_hash_check_insert(struct nf_conn *ct);
 bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report);
 
-void nf_conntrack_flush_report(struct net *net, u32 portid, int report);
-
 bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 		       u_int16_t l3num, struct nf_conntrack_tuple *tuple);
 bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,

net/netfilter/nf_conntrack_core.c

···
 }
 EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
-void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
-{
-	nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
-
 static int untrack_refs(void)
 {
 	int cnt = 0, cpu;
···
 	for (i = 0; i < CONNTRACK_LOCKS; i++)
 		spin_lock_init(&nf_conntrack_locks[i]);
 
-	/* Idea from tcp.c: use 1/16384 of memory.  On i386: 32MB
-	 * machine has 512 buckets. >= 1GB machines have 16384 buckets. */
 	if (!nf_conntrack_htable_size) {
+		/* Idea from tcp.c: use 1/16384 of memory.
+		 * On i386: 32MB machine has 512 buckets.
+		 * >= 1GB machines have 16384 buckets.
+		 * >= 4GB machines have 65536 buckets.
+		 */
 		nf_conntrack_htable_size
 			= (((totalram_pages << PAGE_SHIFT) / 16384)
 			   / sizeof(struct hlist_head));
-		if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
+		if (totalram_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
+			nf_conntrack_htable_size = 65536;
+		else if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
 			nf_conntrack_htable_size = 16384;
 		if (nf_conntrack_htable_size < 32)
 			nf_conntrack_htable_size = 32;

net/netfilter/nf_conntrack_netlink.c

···
 	return 0;
 }
 
-struct ctnetlink_dump_filter {
+struct ctnetlink_filter {
 	struct {
 		u_int32_t val;
 		u_int32_t mask;
 	} mark;
 };
+
+static struct ctnetlink_filter *
+ctnetlink_alloc_filter(const struct nlattr * const cda[])
+{
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	struct ctnetlink_filter *filter;
+
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (filter == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK]));
+	filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
+
+	return filter;
+#else
+	return ERR_PTR(-EOPNOTSUPP);
+#endif
+}
+
+static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
+{
+	struct ctnetlink_filter *filter = data;
+
+	if (filter == NULL)
+		return 1;
+
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	if ((ct->mark & filter->mark.mask) == filter->mark.val)
+		return 1;
+#endif
+
+	return 0;
+}
 
 static int
 ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
···
 	u_int8_t l3proto = nfmsg->nfgen_family;
 	int res;
 	spinlock_t *lockp;
-
-#ifdef CONFIG_NF_CONNTRACK_MARK
-	const struct ctnetlink_dump_filter *filter = cb->data;
-#endif
 
 	last = (struct nf_conn *)cb->args[1];
 
···
 					continue;
 				cb->args[1] = 0;
 			}
-#ifdef CONFIG_NF_CONNTRACK_MARK
-			if (filter && !((ct->mark & filter->mark.mask) ==
-					filter->mark.val)) {
+			if (!ctnetlink_filter_match(ct, cb->data))
 				continue;
-			}
-#endif
+
 			rcu_read_lock();
 			res =
 			ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
···
 				    .len = NF_CT_LABELS_MAX_SIZE },
 };
 
+static int ctnetlink_flush_conntrack(struct net *net,
+				     const struct nlattr * const cda[],
+				     u32 portid, int report)
+{
+	struct ctnetlink_filter *filter = NULL;
+
+	if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
+		filter = ctnetlink_alloc_filter(cda);
+		if (IS_ERR(filter))
+			return PTR_ERR(filter);
+	}
+
+	nf_ct_iterate_cleanup(net, ctnetlink_filter_match, filter,
+			      portid, report);
+	kfree(filter);
+
+	return 0;
+}
+
 static int
 ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 			const struct nlmsghdr *nlh,
···
 	else if (cda[CTA_TUPLE_REPLY])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3);
 	else {
-		/* Flush the whole table */
-		nf_conntrack_flush_report(net,
-					 NETLINK_CB(skb).portid,
-					 nlmsg_report(nlh));
-		return 0;
+		return ctnetlink_flush_conntrack(net, cda,
+						 NETLINK_CB(skb).portid,
+						 nlmsg_report(nlh));
 	}
 
 	if (err < 0)
···
 			.dump = ctnetlink_dump_table,
 			.done = ctnetlink_done,
 		};
-#ifdef CONFIG_NF_CONNTRACK_MARK
+
 		if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
-			struct ctnetlink_dump_filter *filter;
+			struct ctnetlink_filter *filter;
 
-			filter = kzalloc(sizeof(struct ctnetlink_dump_filter),
-					 GFP_ATOMIC);
-			if (filter == NULL)
-				return -ENOMEM;
+			filter = ctnetlink_alloc_filter(cda);
+			if (IS_ERR(filter))
+				return PTR_ERR(filter);
 
-			filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK]));
-			filter->mark.mask =
-				ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
 			c.data = filter;
 		}
-#endif
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
 

net/netfilter/nf_conntrack_seqadj.c

···
 			new_end_seq = htonl(ntohl(sack->end_seq) -
 				      seq->offset_before);
 
-		pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n",
-			 ntohl(sack->start_seq), new_start_seq,
-			 ntohl(sack->end_seq), new_end_seq);
+		pr_debug("sack_adjust: start_seq: %u->%u, end_seq: %u->%u\n",
+			 ntohl(sack->start_seq), ntohl(new_start_seq),
+			 ntohl(sack->end_seq), ntohl(new_end_seq));
 
 		inet_proto_csum_replace4(&tcph->check, skb,
 					 sack->start_seq, new_start_seq, 0);

net/netfilter/nf_log.c

···
 			nf_log_sysctl_table[i].procname	=
 				nf_log_sysctl_fnames[i];
 			nf_log_sysctl_table[i].data = NULL;
-			nf_log_sysctl_table[i].maxlen =
-				NFLOGGER_NAME_LEN * sizeof(char);
+			nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN;
 			nf_log_sysctl_table[i].mode = 0644;
 			nf_log_sysctl_table[i].proc_handler =
 				nf_log_proc_dostring;

net/netfilter/nfnetlink.c

···
 static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 				u_int16_t subsys_id)
 {
-	struct sk_buff *nskb, *oskb = skb;
+	struct sk_buff *oskb = skb;
 	struct net *net = sock_net(skb->sk);
 	const struct nfnetlink_subsystem *ss;
 	const struct nfnl_callback *nc;
···
 	if (subsys_id >= NFNL_SUBSYS_COUNT)
 		return netlink_ack(skb, nlh, -EINVAL);
 replay:
-	nskb = netlink_skb_clone(oskb, GFP_KERNEL);
-	if (!nskb)
+	skb = netlink_skb_clone(oskb, GFP_KERNEL);
+	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM);
 
-	nskb->sk = oskb->sk;
-	skb = nskb;
+	skb->sk = oskb->sk;
 
 	nfnl_lock(subsys_id);
 	ss = rcu_dereference_protected(table[subsys_id].subsys,
···
 		{
 			nfnl_unlock(subsys_id);
 			netlink_ack(skb, nlh, -EOPNOTSUPP);
-			return kfree_skb(nskb);
+			return kfree_skb(skb);
 		}
 	}
 
···
 				nfnl_err_reset(&err_list);
 				ss->abort(oskb);
 				nfnl_unlock(subsys_id);
-				kfree_skb(nskb);
+				kfree_skb(skb);
 				goto replay;
 			}
 		}
···
 
 	nfnl_err_deliver(&err_list, oskb);
 	nfnl_unlock(subsys_id);
-	kfree_skb(nskb);
+	kfree_skb(skb);
 }
 
 static void nfnetlink_rcv(struct sk_buff *skb)

net/netfilter/nfnetlink_cthelper.c

···
 static int
 nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 {
-	const struct nf_conn_help *help = nfct_help(ct);
+	struct nf_conn_help *help = nfct_help(ct);
 
 	if (attr == NULL)
 		return -EINVAL;
···
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	memcpy(&help->data, nla_data(attr), help->helper->data_len);
+	memcpy(help->data, nla_data(attr), help->helper->data_len);
 	return 0;
 }
 

net/netfilter/xt_osf.c

···
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) {
+		int foptsize, optnum;
+
 		f = &kf->finger;
 
 		if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre))
···
 		optp = _optp;
 		fmatch = FMATCH_WRONG;
 
-		if (totlen == f->ss && xt_osf_ttl(skb, info, f->ttl)) {
-			int foptsize, optnum;
+		if (totlen != f->ss || !xt_osf_ttl(skb, info, f->ttl))
+			continue;
 
-			/*
-			 * Should not happen if userspace parser was written correctly.
-			 */
-			if (f->wss.wc >= OSF_WSS_MAX)
-				continue;
+		/*
+		 * Should not happen if userspace parser was written correctly.
+		 */
+		if (f->wss.wc >= OSF_WSS_MAX)
+			continue;
 
-			/* Check options */
+		/* Check options */
 
-			foptsize = 0;
-			for (optnum = 0; optnum < f->opt_num; ++optnum)
-				foptsize += f->opt[optnum].length;
+		foptsize = 0;
+		for (optnum = 0; optnum < f->opt_num; ++optnum)
+			foptsize += f->opt[optnum].length;
 
-			if (foptsize > MAX_IPOPTLEN ||
-				optsize > MAX_IPOPTLEN ||
-				optsize != foptsize)
-				continue;
+		if (foptsize > MAX_IPOPTLEN ||
+		    optsize > MAX_IPOPTLEN ||
+		    optsize != foptsize)
+			continue;
 
-			check_WSS = f->wss.wc;
+		check_WSS = f->wss.wc;
 
-			for (optnum = 0; optnum < f->opt_num; ++optnum) {
-				if (f->opt[optnum].kind == (*optp)) {
-					__u32 len = f->opt[optnum].length;
-					const __u8 *optend = optp + len;
-					int loop_cont = 0;
+		for (optnum = 0; optnum < f->opt_num; ++optnum) {
+			if (f->opt[optnum].kind == (*optp)) {
+				__u32 len = f->opt[optnum].length;
+				const __u8 *optend = optp + len;
+				int loop_cont = 0;
 
-					fmatch = FMATCH_OK;
+				fmatch = FMATCH_OK;
 
-					switch (*optp) {
-					case OSFOPT_MSS:
-						mss = optp[3];
-						mss <<= 8;
-						mss |= optp[2];
+				switch (*optp) {
+				case OSFOPT_MSS:
+					mss = optp[3];
+					mss <<= 8;
+					mss |= optp[2];
 
-						mss = ntohs((__force __be16)mss);
-						break;
-					case OSFOPT_TS:
-						loop_cont = 1;
-						break;
-					}
-
-					optp = optend;
-				} else
-					fmatch = FMATCH_OPT_WRONG;
-
-				if (fmatch != FMATCH_OK)
+					mss = ntohs((__force __be16)mss);
 					break;
-			}
-
-			if (fmatch != FMATCH_OPT_WRONG) {
-				fmatch = FMATCH_WRONG;
-
-				switch (check_WSS) {
-				case OSF_WSS_PLAIN:
-					if (f->wss.val == 0 || window == f->wss.val)
-						fmatch = FMATCH_OK;
-					break;
-				case OSF_WSS_MSS:
-					/*
-					 * Some smart modems decrease mangle MSS to 
-					 * SMART_MSS_2, so we check standard, decreased
-					 * and the one provided in the fingerprint MSS
-					 * values.
-					 */
-#define SMART_MSS_1	1460
-#define SMART_MSS_2	1448
-					if (window == f->wss.val * mss ||
-					    window == f->wss.val * SMART_MSS_1 ||
-					    window == f->wss.val * SMART_MSS_2)
-						fmatch = FMATCH_OK;
-					break;
-				case OSF_WSS_MTU:
-					if (window == f->wss.val * (mss + 40) ||
-					    window == f->wss.val * (SMART_MSS_1 + 40) ||
-					    window == f->wss.val * (SMART_MSS_2 + 40))
-						fmatch = FMATCH_OK;
-					break;
-				case OSF_WSS_MODULO:
-					if ((window % f->wss.val) == 0)
-						fmatch = FMATCH_OK;
+				case OSFOPT_TS:
+					loop_cont = 1;
 					break;
 				}
-			}
+
+				optp = optend;
+			} else
+				fmatch = FMATCH_OPT_WRONG;
 
 			if (fmatch != FMATCH_OK)
-				continue;
-
-			fcount++;
-
-			if (info->flags & XT_OSF_LOG)
-				nf_log_packet(net, p->family, p->hooknum, skb,
-					p->in, p->out, NULL,
-					"%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
-					f->genre, f->version, f->subtype,
-					&ip->saddr, ntohs(tcp->source),
-					&ip->daddr, ntohs(tcp->dest),
-					f->ttl - ip->ttl);
-
-			if ((info->flags & XT_OSF_LOG) &&
-			    info->loglevel == XT_OSF_LOGLEVEL_FIRST)
 				break;
 		}
+
+		if (fmatch != FMATCH_OPT_WRONG) {
+			fmatch = FMATCH_WRONG;
+
+			switch (check_WSS) {
+			case OSF_WSS_PLAIN:
+				if (f->wss.val == 0 || window == f->wss.val)
+					fmatch = FMATCH_OK;
+				break;
+			case OSF_WSS_MSS:
+				/*
+				 * Some smart modems decrease mangle MSS to
+				 * SMART_MSS_2, so we check standard, decreased
+				 * and the one provided in the fingerprint MSS
+				 * values.
+				 */
+#define SMART_MSS_1	1460
+#define SMART_MSS_2	1448
+				if (window == f->wss.val * mss ||
+				    window == f->wss.val * SMART_MSS_1 ||
+				    window == f->wss.val * SMART_MSS_2)
+					fmatch = FMATCH_OK;
+				break;
+			case OSF_WSS_MTU:
+				if (window == f->wss.val * (mss + 40) ||
+				    window == f->wss.val * (SMART_MSS_1 + 40) ||
+				    window == f->wss.val * (SMART_MSS_2 + 40))
+					fmatch = FMATCH_OK;
+				break;
+			case OSF_WSS_MODULO:
+				if ((window % f->wss.val) == 0)
+					fmatch = FMATCH_OK;
+				break;
+			}
+		}
+
+		if (fmatch != FMATCH_OK)
+			continue;
+
+		fcount++;
+
+		if (info->flags & XT_OSF_LOG)
+			nf_log_packet(net, p->family, p->hooknum, skb,
+				      p->in, p->out, NULL,
+				      "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
+				      f->genre, f->version, f->subtype,
+				      &ip->saddr, ntohs(tcp->source),
+				      &ip->daddr, ntohs(tcp->dest),
+				      f->ttl - ip->ttl);
+
+		if ((info->flags & XT_OSF_LOG) &&
+		    info->loglevel == XT_OSF_LOGLEVEL_FIRST)
+			break;
 	}
 	rcu_read_unlock();