Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Conflicts:
net/netfilter/nf_log.c

The conflict in nf_log.c is that in 'net' we added CONFIG_PROC_FS
protection around foo_proc_entry() calls to fix a build failure,
whereas in Pablo's tree a guard if() test around a call is
remove_proc_entry() was removed. Trivially resolved.

Pablo Neira Ayuso says:

====================
The following patchset contains the first batch of
Netfilter/IPVS updates for your net-next tree, they are:

* Three patches with improvements and code refactorization
for nfnetlink_queue, from Florian Westphal.

* FTP helper now parses replies without brackets, as RFC1123
recommends, from Jeff Mahoney.

* Rise a warning to tell everyone about ULOG deprecation,
NFLOG has been already in the kernel tree for long time
and supersedes the old logging over netlink stub, from
myself.

* Don't panic if we fail to load netfilter core framework,
just bail out instead, from myself.

* Add cond_resched_rcu, used by IPVS to allow rescheduling
while walking over big hashtables, from Simon Horman.

* Change type of IPVS sysctl_sync_qlen_max sysctl to avoid
possible overflow, from Zhang Yanfei.

* Use strlcpy instead of strncpy to skip zeroing of already
initialized area to write the extension names in ebtables,
from Chen Gang.

* Use already existing per-cpu notrack object from xt_CT,
from Eric Dumazet.

* Save explicit socket lookup in xt_socket now that we have
early demux, also from Eric Dumazet.
====================

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

include/linux/netfilter.h

···
 	result->all[3] = a1->all[3] & mask->all[3];
 }
 
-extern void netfilter_init(void);
+extern int netfilter_init(void);
 
 /* Largest hook number + 1 */
 #define NF_MAX_HOOKS 8

include/linux/sched.h

···
 	__cond_resched_softirq();					\
 })
 
+static inline void cond_resched_rcu(void)
+{
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
+	rcu_read_unlock();
+	cond_resched();
+	rcu_read_lock();
+#endif
+}
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPT,

include/net/ip_vs.h

···
 struct ipvs_master_sync_state {
 	struct list_head	sync_queue;
 	struct ip_vs_sync_buff	*sync_buff;
-	int			sync_queue_len;
+	unsigned long		sync_queue_len;
 	unsigned int		sync_queue_delay;
 	struct task_struct	*master_thread;
 	struct delayed_work	master_wakeup_work;
···
 	int			sysctl_snat_reroute;
 	int			sysctl_sync_ver;
 	int			sysctl_sync_ports;
-	int			sysctl_sync_qlen_max;
+	unsigned long		sysctl_sync_qlen_max;
 	int			sysctl_sync_sock_size;
 	int			sysctl_cache_bypass;
 	int			sysctl_expire_nodest_conn;
···
 	return ACCESS_ONCE(ipvs->sysctl_sync_ports);
 }
 
-static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
 {
 	return ipvs->sysctl_sync_qlen_max;
 }
···
 	return 1;
 }
 
-static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
 {
 	return IPVS_SYNC_QLEN_MAX;
 }

include/net/netns/x_tables.h

···
 	struct ebt_table *frame_filter;
 	struct ebt_table *frame_nat;
 #endif
+#if IS_ENABLED(CONFIG_IP_NF_TARGET_ULOG)
+	bool ulog_warn_deprecated;
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_EBT_ULOG)
+	bool ebt_ulog_warn_deprecated;
+#endif
 };
 #endif

net/bridge/netfilter/ebt_ulog.c

···
 {
 	struct ebt_ulog_info *uloginfo = par->targinfo;
 
+	if (!par->net->xt.ebt_ulog_warn_deprecated) {
+		pr_info("ebt_ulog is deprecated and it will be removed soon, "
+			"use ebt_nflog instead\n");
+		par->net->xt.ebt_ulog_warn_deprecated = true;
+	}
+
 	if (uloginfo->nlgroup > 31)
 		return -EINVAL;
 

net/bridge/netfilter/ebtables.c

···
 
 	/* ebtables expects 32 bytes long names but xt_match names are 29 bytes
 	   long. Copy 29 bytes and fill remaining bytes with zeroes. */
-	strncpy(name, m->u.match->name, sizeof(name));
+	strlcpy(name, m->u.match->name, sizeof(name));
 	if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
 		return -EFAULT;
 	return 0;
···
 	char __user *hlp = ubase + ((char *)w - base);
 	char name[EBT_FUNCTION_MAXNAMELEN] = {};
 
-	strncpy(name, w->u.watcher->name, sizeof(name));
+	strlcpy(name, w->u.watcher->name, sizeof(name));
 	if (copy_to_user(hlp , name, EBT_FUNCTION_MAXNAMELEN))
 		return -EFAULT;
 	return 0;
···
 	ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase);
 	if (ret != 0)
 		return ret;
-	strncpy(name, t->u.target->name, sizeof(name));
+	strlcpy(name, t->u.target->name, sizeof(name));
 	if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
 		return -EFAULT;
 	return 0;

net/ipv4/netfilter/Kconfig

···
 	  To compile it as a module, choose M here.  If unsure, say N.
 
 config IP_NF_TARGET_ULOG
-	tristate "ULOG target support"
+	tristate "ULOG target support (obsolete)"
 	default m if NETFILTER_ADVANCED=n
 	---help---
 

net/ipv4/netfilter/ipt_ULOG.c

···
 {
 	const struct ipt_ulog_info *loginfo = par->targinfo;
 
+	if (!par->net->xt.ulog_warn_deprecated) {
+		pr_info("ULOG is deprecated and it will be removed soon, "
+			"use NFLOG instead\n");
+		par->net->xt.ulog_warn_deprecated = true;
+	}
+
 	if (loginfo->prefix[sizeof(loginfo->prefix) - 1] != '\0') {
 		pr_debug("prefix not null-terminated\n");
 		return -EINVAL;

net/netfilter/core.c

···
 	.exit = netfilter_net_exit,
 };
 
-void __init netfilter_init(void)
+int __init netfilter_init(void)
 {
-	int i, h;
+	int i, h, ret;
+
 	for (i = 0; i < ARRAY_SIZE(nf_hooks); i++) {
 		for (h = 0; h < NF_MAX_HOOKS; h++)
 			INIT_LIST_HEAD(&nf_hooks[i][h]);
 	}
 
-	if (register_pernet_subsys(&netfilter_net_ops) < 0)
-		panic("cannot create netfilter proc entry");
+	ret = register_pernet_subsys(&netfilter_net_ops);
+	if (ret < 0)
+		goto err;
 
-	if (netfilter_log_init() < 0)
-		panic("cannot initialize nf_log");
+	ret = netfilter_log_init();
+	if (ret < 0)
+		goto err_pernet;
+
+	return 0;
+err_pernet:
+	unregister_pernet_subsys(&netfilter_net_ops);
+err:
+	return ret;
 }

net/netfilter/ipvs/ip_vs_conn.c

···
 				return cp;
 			}
 		}
-		rcu_read_unlock();
-		rcu_read_lock();
+		cond_resched_rcu();
 	}
 
 	return NULL;
···
 			iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 		}
-		rcu_read_unlock();
-		rcu_read_lock();
+		cond_resched_rcu();
 	}
 	iter->l = NULL;
 	return NULL;
···
 	int idx;
 	struct ip_vs_conn *cp, *cp_c;
 
+	rcu_read_lock();
 	/*
 	 * Randomly scan 1/32 of the whole table every second
 	 */
 	for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) {
 		unsigned int hash = net_random() & ip_vs_conn_tab_mask;
-
-		/*
-		 *  Lock is actually needed in this loop.
-		 */
-		rcu_read_lock();
 
 		hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
···
 				__ip_vs_conn_put(cp);
 			}
 		}
-		rcu_read_unlock();
+		cond_resched_rcu();
 	}
+	rcu_read_unlock();
 }
 
 
···
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 flush_again:
+	rcu_read_lock();
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
-		/*
-		 *  Lock is actually needed in this loop.
-		 */
-		rcu_read_lock();
 
 		hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
 			if (!ip_vs_conn_net_eq(cp, net))
···
 				__ip_vs_conn_put(cp);
 			}
 		}
-		rcu_read_unlock();
+		cond_resched_rcu();
 	}
+	rcu_read_unlock();
 
 	/* the counter may be not NULL, because maybe some conn entries
 	   are run by slow timer handler or unhashed but still referred */

net/netfilter/ipvs/ip_vs_ctl.c

···
 	},
 	{
 		.procname	= "sync_qlen_max",
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "sync_sock_size",

net/netfilter/nf_conntrack_ftp.c

···
 				struct nf_conntrack_expect *exp);
 EXPORT_SYMBOL_GPL(nf_nat_ftp_hook);
 
-static int try_rfc959(const char *, size_t, struct nf_conntrack_man *, char);
-static int try_eprt(const char *, size_t, struct nf_conntrack_man *, char);
+static int try_rfc959(const char *, size_t, struct nf_conntrack_man *,
+		      char, unsigned int *);
+static int try_rfc1123(const char *, size_t, struct nf_conntrack_man *,
+		       char, unsigned int *);
+static int try_eprt(const char *, size_t, struct nf_conntrack_man *,
+		    char, unsigned int *);
 static int try_epsv_response(const char *, size_t, struct nf_conntrack_man *,
-			     char);
+			     char, unsigned int *);
 
 static struct ftp_search {
 	const char *pattern;
···
 	char skip;
 	char term;
 	enum nf_ct_ftp_type ftptype;
-	int (*getnum)(const char *, size_t, struct nf_conntrack_man *, char);
+	int (*getnum)(const char *, size_t, struct nf_conntrack_man *, char, unsigned int *);
 } search[IP_CT_DIR_MAX][2] = {
 	[IP_CT_DIR_ORIGINAL] = {
 		{
···
 		{
 			.pattern	= "227 ",
 			.plen		= sizeof("227 ") - 1,
-			.skip		= '(',
-			.term		= ')',
 			.ftptype	= NF_CT_FTP_PASV,
-			.getnum		= try_rfc959,
+			.getnum		= try_rfc1123,
 		},
 		{
 			.pattern	= "229 ",
···
 			i++;
 		else {
 			/* Unexpected character; true if it's the
-			   terminator and we're finished. */
-			if (*data == term && i == array_size - 1)
+			   terminator (or we don't care about one)
+			   and we're finished. */
+			if ((*data == term || !term) && i == array_size - 1)
 				return len;
 
 			pr_debug("Char %u (got %u nums) `%u' unexpected\n",
···
 
 /* Returns 0, or length of numbers: 192,168,1,1,5,6 */
 static int try_rfc959(const char *data, size_t dlen,
-		      struct nf_conntrack_man *cmd, char term)
+		      struct nf_conntrack_man *cmd, char term,
+		      unsigned int *offset)
 {
 	int length;
 	u_int32_t array[6];
···
 				    (array[2] << 8) | array[3]);
 	cmd->u.tcp.port = htons((array[4] << 8) | array[5]);
 	return length;
+}
+
+/*
+ * From RFC 1123:
+ * The format of the 227 reply to a PASV command is not
+ * well standardized.  In particular, an FTP client cannot
+ * assume that the parentheses shown on page 40 of RFC-959
+ * will be present (and in fact, Figure 3 on page 43 omits
+ * them).  Therefore, a User-FTP program that interprets
+ * the PASV reply must scan the reply for the first digit
+ * of the host and port numbers.
+ */
+static int try_rfc1123(const char *data, size_t dlen,
+		       struct nf_conntrack_man *cmd, char term,
+		       unsigned int *offset)
+{
+	int i;
+	for (i = 0; i < dlen; i++)
+		if (isdigit(data[i]))
+			break;
+
+	if (i == dlen)
+		return 0;
+
+	*offset += i;
+
+	return try_rfc959(data + i, dlen - i, cmd, 0, offset);
 }
 
 /* Grab port: number up to delimiter */
···
 
 /* Returns 0, or length of numbers: |1|132.235.1.2|6275| or |2|3ffe::1|6275| */
 static int try_eprt(const char *data, size_t dlen, struct nf_conntrack_man *cmd,
-		    char term)
+		    char term, unsigned int *offset)
 {
 	char delim;
 	int length;
···
 
 /* Returns 0, or length of numbers: |||6446| */
 static int try_epsv_response(const char *data, size_t dlen,
-			     struct nf_conntrack_man *cmd, char term)
+			     struct nf_conntrack_man *cmd, char term,
+			     unsigned int *offset)
 {
 	char delim;
 
···
 			unsigned int *numlen,
 			struct nf_conntrack_man *cmd,
 			int (*getnum)(const char *, size_t,
-				      struct nf_conntrack_man *, char))
+				      struct nf_conntrack_man *, char,
+				      unsigned int *))
 {
-	size_t i;
+	size_t i = plen;
 
 	pr_debug("find_pattern `%s': dlen = %Zu\n", pattern, dlen);
 	if (dlen == 0)
···
 	pr_debug("Pattern matches!\n");
 	/* Now we've found the constant string, try to skip
 	   to the 'skip' character */
-	for (i = plen; data[i] != skip; i++)
-		if (i == dlen - 1) return -1;
+	if (skip) {
+		for (i = plen; data[i] != skip; i++)
+			if (i == dlen - 1) return -1;
 
-	/* Skip over the last character */
-	i++;
+		/* Skip over the last character */
+		i++;
+	}
 
 	pr_debug("Skipped up to `%c'!\n", skip);
 
 	*numoff = i;
-	*numlen = getnum(data + i, dlen - i, cmd, term);
+	*numlen = getnum(data + i, dlen - i, cmd, term, numoff);
 	if (!*numlen)
 		return -1;
 

net/netfilter/nf_log.c

···
 
 out_sysctl:
 #ifdef CONFIG_PROC_FS
-	/* For init_net: errors will trigger panic, don't unroll on error. */
-	if (!net_eq(net, &init_net))
-		remove_proc_entry("nf_log", net->nf.proc_netfilter);
+	remove_proc_entry("nf_log", net->nf.proc_netfilter);
 #endif
 	return ret;
 }

net/netfilter/nfnetlink_queue_core.c

···
 
 #define NFQNL_QMAX_DEFAULT 1024
 
+/* We're using struct nlattr which has 16bit nla_len. Note that nla_len
+ * includes the header length. Thus, the maximum packet length that we
+ * support is 65531 bytes. We send truncated packets if the specified length
+ * is larger than that.  Userspace can check for presence of NFQA_CAP_LEN
+ * attribute to detect truncation.
+ */
+#define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN)
+
 struct nfqnl_instance {
 	struct hlist_node hlist;		/* global list of queues */
 	struct rcu_head rcu;
···
 	inst->queue_num = queue_num;
 	inst->peer_portid = portid;
 	inst->queue_maxlen = NFQNL_QMAX_DEFAULT;
-	inst->copy_range = 0xffff;
+	inst->copy_range = NFQNL_MAX_COPY_RANGE;
 	inst->copy_mode = NFQNL_COPY_NONE;
 	spin_lock_init(&inst->lock);
 	INIT_LIST_HEAD(&inst->queue_list);
···
 			return NULL;
 
 		data_len = ACCESS_ONCE(queue->copy_range);
-		if (data_len == 0 || data_len > entskb->len)
+		if (data_len > entskb->len)
 			data_len = entskb->len;
-
 
 		if (!entskb->head_frag ||
 		    skb_headlen(entskb) < L1_CACHE_BYTES ||
···
 	if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
 		goto nla_put_failure;
 
-	if (cap_len > 0 && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
+	if (cap_len > data_len &&
+	    nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
 		goto nla_put_failure;
 
 	if (nfqnl_put_packet_info(skb, entskb))
···
 	}
 	spin_lock_bh(&queue->lock);
 
-	if (!queue->peer_portid) {
-		err = -EINVAL;
-		goto err_out_free_nskb;
-	}
 	if (queue->queue_total >= queue->queue_maxlen) {
 		if (queue->flags & NFQA_CFG_F_FAIL_OPEN) {
 			failopen = 1;
···
 
 	case NFQNL_COPY_PACKET:
 		queue->copy_mode = mode;
-		/* We're using struct nlattr which has 16bit nla_len. Note that
-		 * nla_len includes the header length. Thus, the maximum packet
-		 * length that we support is 65531 bytes. We send truncated
-		 * packets if the specified length is larger than that.
-		 */
-		if (range > 0xffff - NLA_HDRLEN)
-			queue->copy_range = 0xffff - NLA_HDRLEN;
+		if (range == 0 || range > NFQNL_MAX_COPY_RANGE)
+			queue->copy_range = NFQNL_MAX_COPY_RANGE;
 		else
 			queue->copy_range = range;
 		break;

net/netfilter/xt_CT.c

···
 	if (skb->nfct != NULL)
 		return XT_CONTINUE;
 
+	/* special case the untracked ct : we want the percpu object */
+	if (!ct)
+		ct = nf_ct_untracked_get();
 	atomic_inc(&ct->ct_general.use);
 	skb->nfct = &ct->ct_general;
 	skb->nfctinfo = IP_CT_NEW;
···
 	int ret = -EOPNOTSUPP;
 
 	if (info->flags & XT_CT_NOTRACK) {
-		ct = nf_ct_untracked_get();
-		atomic_inc(&ct->ct_general.use);
+		ct = NULL;
 		goto out;
 	}
 
···
 	struct nf_conn *ct = info->ct;
 	struct nf_conn_help *help;
 
-	if (!nf_ct_is_untracked(ct)) {
+	if (ct && !nf_ct_is_untracked(ct)) {
 		help = nfct_help(ct);
 		if (help)
 			module_put(help->helper->me);
···
 		nf_ct_l3proto_module_put(par->family);
 
 		xt_ct_destroy_timeout(ct);
+		nf_ct_put(info->ct);
 	}
-	nf_ct_put(info->ct);
 }
 
 static void xt_ct_tg_destroy_v0(const struct xt_tgdtor_param *par)

net/netfilter/xt_socket.c

···
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr _hdr, *hp = NULL;
-	struct sock *sk;
+	struct sock *sk = skb->sk;
 	__be32 uninitialized_var(daddr), uninitialized_var(saddr);
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
 	u8 uninitialized_var(protocol);
···
 	}
 #endif
 
-	sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
-				   saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
-	if (sk != NULL) {
+	if (!sk)
+		sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
+					   saddr, daddr, sport, dport,
+					   par->in, NFT_LOOKUP_ANY);
+	if (sk) {
 		bool wildcard;
 		bool transparent = true;
 
···
 				       (sk->sk_state == TCP_TIME_WAIT &&
 					inet_twsk(sk)->tw_transparent));
 
-		xt_socket_put_sk(sk);
+		if (sk != skb->sk)
+			xt_socket_put_sk(sk);
 
 		if (wildcard || !transparent)
 			sk = NULL;
···
 {
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct udphdr _hdr, *hp = NULL;
-	struct sock *sk;
+	struct sock *sk = skb->sk;
 	struct in6_addr *daddr = NULL, *saddr = NULL;
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
 	int thoff = 0, uninitialized_var(tproto);
···
 		return false;
 	}
 
-	sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
-				   saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
-	if (sk != NULL) {
+	if (!sk)
+		sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
+					   saddr, daddr, sport, dport,
+					   par->in, NFT_LOOKUP_ANY);
+	if (sk) {
 		bool wildcard;
 		bool transparent = true;
 
···
 				       (sk->sk_state == TCP_TIME_WAIT &&
 					inet_twsk(sk)->tw_transparent));
 
-		xt_socket_put_sk(sk);
+		if (sk != skb->sk)
+			xt_socket_put_sk(sk);
 
 		if (wildcard || !transparent)
 			sk = NULL;

net/socket.c

···
 	 */
 
 #ifdef CONFIG_NETFILTER
-	netfilter_init();
+	err = netfilter_init();
+	if (err)
+		goto out;
 #endif
 
 #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING