Merge tag 'ipvs-fixes-for-v4.5' of https://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs

Simon Horman says:

====================
please consider these IPVS fixes for v4.5 or
if it is too late please consider them for v4.6.

* Arnd Bergman has corrected an error whereby the SIP persistence engine
  may incorrectly access protocol fields
* Julian Anastasov has corrected a problem reported by Jiri Bohac with the
  connection rescheduling mechanism added in 3.10 when new SYNs in
  connection to dead real server can be redirected to another real server.
* Marco Angaroni resolved a problem in the SIP persistence engine
  whereby the Call-ID could not be found if it was at the beginning of a
  SIP message.
====================

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

4 files changed, 52 insertions, 12 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 0816c872b689..a6cc576fd467 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1588,6 +1588,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 }
 #endif /* CONFIG_IP_VS_NFCT */
 
+/* Really using conntrack? */
+static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
+					     struct sk_buff *skb)
+{
+#ifdef CONFIG_IP_VS_NFCT
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	if (!(cp->flags & IP_VS_CONN_F_NFCT))
+		return false;
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct && !nf_ct_is_untracked(ct))
+		return true;
+#endif
+	return false;
+}
+
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index f57b4dcdb233..b9a4082afa3a 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1089,6 +1089,7 @@ static inline bool is_new_conn_expected(const struct ip_vs_conn *cp,
 	switch (cp->protocol) {
 	case IPPROTO_TCP:
 		return (cp->state == IP_VS_TCP_S_TIME_WAIT) ||
+		       (cp->state == IP_VS_TCP_S_CLOSE) ||
 			((conn_reuse_mode & 2) &&
 			 (cp->state == IP_VS_TCP_S_FIN_WAIT) &&
 			 (cp->flags & IP_VS_CONN_F_NOOUTPUT));
@@ -1757,15 +1758,34 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	cp = pp->conn_in_get(ipvs, af, skb, &iph);
 
 	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs &&
-	    is_new_conn(skb, &iph) && cp &&
-	    ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
-	      unlikely(!atomic_read(&cp->dest->weight))) ||
-	     unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) {
-		if (!atomic_read(&cp->n_control))
-			ip_vs_conn_expire_now(cp);
-		__ip_vs_conn_put(cp);
-		cp = NULL;
+	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+		bool uses_ct = false, resched = false;
+
+		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
+		    unlikely(!atomic_read(&cp->dest->weight))) {
+			resched = true;
+			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			if (!atomic_read(&cp->n_control)) {
+				resched = true;
+			} else {
+				/* Do not reschedule controlling connection
+				 * that uses conntrack while it is still
+				 * referenced by controlled connection(s).
+				 */
+				resched = !uses_ct;
+			}
+		}
+
+		if (resched) {
+			if (!atomic_read(&cp->n_control))
+				ip_vs_conn_expire_now(cp);
+			__ip_vs_conn_put(cp);
+			if (uses_ct)
+				return NF_DROP;
+			cp = NULL;
+		}
 	}
 
 	if (unlikely(!cp)) {
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 1b8d594e493a..0a6eb5c0d9e9 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -70,10 +70,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	const char *dptr;
 	int retc;
 
-	ip_vs_fill_iph_skb(p->af, skb, false, &iph);
+	retc = ip_vs_fill_iph_skb(p->af, skb, false, &iph);
 
 	/* Only useful with UDP */
-	if (iph.protocol != IPPROTO_UDP)
+	if (!retc || iph.protocol != IPPROTO_UDP)
 		return -EINVAL;
 	/* todo: IPv6 fragments:
 	 *       I think this only should be done for the first fragment. /HS
@@ -88,7 +88,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	dptr = skb->data + dataoff;
 	datalen = skb->len - dataoff;
 
-	if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
+	if (get_callid(dptr, 0, datalen, &matchoff, &matchlen))
 		return -EINVAL;
 
 	/* N.B: pe_data is only set on success,
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 5274b04c42a6..4c2b4c0c4d5f 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -242,6 +242,9 @@ nfacct_filter_alloc(const struct nlattr * const attr)
 	if (err < 0)
 		return ERR_PTR(err);
 
+	if (!tb[NFACCT_FILTER_MASK] || !tb[NFACCT_FILTER_VALUE])
+		return ERR_PTR(-EINVAL);
+
 	filter = kzalloc(sizeof(struct nfacct_filter), GFP_KERNEL);
 	if (!filter)
 		return ERR_PTR(-ENOMEM);