Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

The netfilter conflicts were rather simple overlapping
changes.

However, the cls_tcindex.c stuff was a bit more complex.

On the 'net' side, Cong is fixing several races and memory
leaks.  Whilst on the 'net-next' side we have Vlad adding
the rtnl-ness support.

What I've decided to do, in order to resolve this, is revert the
conversion over to using a workqueue that Cong did, bringing us back
to pure RCU.  I did it this way because I believe that either Cong's
races don't apply with have Vlad did things, or Cong will have to
implement the race fix slightly differently.

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 22 insertions, 4 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 1a4e9ff02762..5731670c560b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		+ nla_total_size(1) /* INET_DIAG_TOS */
 		+ nla_total_size(1) /* INET_DIAG_TCLASS */
 		+ nla_total_size(4) /* INET_DIAG_MARK */
+		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
@@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
 		u32 classid = 0;
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
 		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 #endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
 
 		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
 			goto errout;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index d757b9642d0d..be778599bfed 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			atomic_set(&p->rid, 0);
 			p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 			p->rate_tokens = 0;
+			p->n_redirects = 0;
 			/* 60*HZ is arbitrary, but chosen enough high so that the first
 			 * calculation of tokens is at its maximum.
 			 */
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index e26165af45cb..4b07eb8a9b18 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -215,6 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 
 	/* Change outer to look like the reply to an incoming packet */
 	nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
+	target.dst.protonum = IPPROTO_ICMP;
 	if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip))
 		return 0;
 
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
index a0aa13bcabda..0a8a60c1bf9a 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
@@ -105,6 +105,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset)
 int snmp_version(void *context, size_t hdrlen, unsigned char tag,
 		 const void *data, size_t datalen)
 {
+	if (datalen != 1)
+		return -EINVAL;
 	if (*(unsigned char *)data > 1)
 		return -ENOTSUPP;
 	return 1;
@@ -114,8 +116,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag,
 		const void *data, size_t datalen)
 {
 	struct snmp_ctx *ctx = (struct snmp_ctx *)context;
-	__be32 *pdata = (__be32 *)data;
+	__be32 *pdata;
 
+	if (datalen != 4)
+		return -EINVAL;
+	pdata = (__be32 *)data;
 	if (*pdata == ctx->from) {
 		pr_debug("%s: %pI4 to %pI4\n", __func__,
 			 (void *)&ctx->from, (void *)&ctx->to);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 16259ea9df54..ecc12a768191 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* No redirected packets during ip_rt_redirect_silence;
 	 * reset the algorithm.
 	 */
-	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
 		peer->rate_tokens = 0;
+		peer->n_redirects = 0;
+	}
 
 	/* Too many ignored redirects; do not send anything
 	 * set dst.rate_last to the last seen redirected packet.
 	 */
-	if (peer->rate_tokens >= ip_rt_redirect_number) {
+	if (peer->n_redirects >= ip_rt_redirect_number) {
 		peer->rate_last = jiffies;
 		goto out_put_peer;
 	}
@@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
 		++peer->rate_tokens;
+		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
 		    peer->rate_tokens == ip_rt_redirect_number)