1 files changed, 73 insertions, 40 deletions

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index c613900c3811..dea411e132db 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -2,6 +2,9 @@
 /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
  */
 
+#include <net/flow.h>
+#include <net/ip.h>
+
 #include "ipvlan.h"
 
 static u32 ipvlan_jhash_secret __read_mostly;
@@ -19,10 +22,10 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 
 		pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
 		u64_stats_update_begin(&pcptr->syncp);
-		pcptr->rx_pkts++;
-		pcptr->rx_bytes += len;
+		u64_stats_inc(&pcptr->rx_pkts);
+		u64_stats_add(&pcptr->rx_bytes, len);
 		if (mcast)
-			pcptr->rx_mcast++;
+			u64_stats_inc(&pcptr->rx_mcast);
 		u64_stats_update_end(&pcptr->syncp);
 	} else {
 		this_cpu_inc(ipvlan->pcpu_stats->rx_errs);
@@ -49,8 +52,8 @@ static u8 ipvlan_get_v4_hash(const void *iaddr)
 {
 	const struct in_addr *ip4_addr = iaddr;
 
-	return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) &
-	       IPVLAN_HASH_MASK;
+	return jhash_1word((__force u32)ip4_addr->s_addr, ipvlan_jhash_secret) &
+			   IPVLAN_HASH_MASK;
 }
 
 static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr)
@@ -157,7 +160,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type)
 			return NULL;
 
 		ip4h = ip_hdr(skb);
-		pktlen = ntohs(ip4h->tot_len);
+		pktlen = skb_ip_totlen(skb);
 		if (ip4h->ihl < 5 || ip4h->version != 4)
 			return NULL;
 		if (skb->len < pktlen || pktlen < (ip4h->ihl * 4))
@@ -216,7 +219,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type)
 
 unsigned int ipvlan_mac_hash(const unsigned char *addr)
 {
-	u32 hash = jhash_1word(__get_unaligned_cpu32(addr+2),
+	u32 hash = jhash_1word(get_unaligned((u32 *)(addr + 2)),
 			       ipvlan_jhash_secret);
 
 	return hash & IPVLAN_MAC_FILTER_MASK;
@@ -411,22 +414,27 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 	return addr;
 }
 
-static int ipvlan_process_v4_outbound(struct sk_buff *skb)
+static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 {
-	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net_device *dev = skb->dev;
 	struct net *net = dev_net(dev);
-	struct rtable *rt;
 	int err, ret = NET_XMIT_DROP;
+	const struct iphdr *ip4h;
+	struct rtable *rt;
 	struct flowi4 fl4 = {
 		.flowi4_oif = dev->ifindex,
-		.flowi4_tos = RT_TOS(ip4h->tos),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC,
 		.flowi4_mark = skb->mark,
-		.daddr = ip4h->daddr,
-		.saddr = ip4h->saddr,
 	};
 
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		goto err;
+
+	ip4h = ip_hdr(skb);
+	fl4.daddr = ip4h->daddr;
+	fl4.saddr = ip4h->saddr;
+	fl4.flowi4_dscp = ip4h_dscp(ip4h);
+
 	rt = ip_route_output_flow(net, &fl4, NULL);
 	if (IS_ERR(rt))
 		goto err;
@@ -436,27 +444,28 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb)
 		goto err;
 	}
 	skb_dst_set(skb, &rt->dst);
-	err = ip_local_out(net, skb->sk, skb);
+
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
+	err = ip_local_out(net, NULL, skb);
 	if (unlikely(net_xmit_eval(err)))
-		dev->stats.tx_errors++;
+		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
 	goto out;
 err:
-	dev->stats.tx_errors++;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 out:
 	return ret;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+
+static noinline_for_stack int
+ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	struct net_device *dev = skb->dev;
-	struct net *net = dev_net(dev);
-	struct dst_entry *dst;
-	int err, ret = NET_XMIT_DROP;
 	struct flowi6 fl6 = {
 		.flowi6_oif = dev->ifindex,
 		.daddr = ip6h->daddr,
@@ -466,24 +475,44 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = ip6h->nexthdr,
 	};
+	struct dst_entry *dst;
+	int err;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst->error) {
-		ret = dst->error;
+	dst = ip6_route_output(dev_net(dev), NULL, &fl6);
+	err = dst->error;
+	if (err) {
 		dst_release(dst);
-		goto err;
+		return err;
 	}
 	skb_dst_set(skb, dst);
-	err = ip6_local_out(net, skb->sk, skb);
+	return 0;
+}
+
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	int err, ret = NET_XMIT_DROP;
+
+	if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return ret;
+	}
+
+	err = ipvlan_route_v6_outbound(dev, skb);
+	if (unlikely(err)) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return err;
+	}
+
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+	err = ip6_local_out(dev_net(dev), NULL, skb);
 	if (unlikely(net_xmit_eval(err)))
-		dev->stats.tx_errors++;
+		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
-	goto out;
-err:
-	dev->stats.tx_errors++;
-	kfree_skb(skb);
-out:
 	return ret;
 }
 #else
@@ -495,7 +524,6 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 
 static int ipvlan_process_outbound(struct sk_buff *skb)
 {
-	struct ethhdr *ethh = eth_hdr(skb);
 	int ret = NET_XMIT_DROP;
 
 	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
@@ -505,6 +533,8 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 	if (skb_mac_header_was_set(skb)) {
 		/* In this mode we dont care about
 		 * multicast and broadcast traffic */
+		struct ethhdr *ethh = eth_hdr(skb);
+
 		if (is_multicast_ether_addr(ethh->h_dest)) {
 			pr_debug_ratelimited(
 				"Dropped {multi|broad}cast of type=[%x]\n",
@@ -548,14 +578,13 @@ static void ipvlan_multicast_enqueue(struct ipvl_port *port,
 
 	spin_lock(&port->backlog.lock);
 	if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
-		if (skb->dev)
-			dev_hold(skb->dev);
+		dev_hold(skb->dev);
 		__skb_queue_tail(&port->backlog, skb);
 		spin_unlock(&port->backlog.lock);
 		schedule_work(&port->wq);
 	} else {
 		spin_unlock(&port->backlog.lock);
-		atomic_long_inc(&skb->dev->rx_dropped);
+		dev_core_stats_rx_dropped_inc(skb->dev);
 		kfree_skb(skb);
 	}
 }
@@ -578,7 +607,8 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev)
 				consume_skb(skb);
 				return NET_XMIT_DROP;
 			}
-			return ipvlan_rcv_frame(addr, &skb, true);
+			ipvlan_rcv_frame(addr, &skb, true);
+			return NET_XMIT_SUCCESS;
 		}
 	}
 out:
@@ -589,7 +619,7 @@ out:
 static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct ethhdr *eth = eth_hdr(skb);
+	struct ethhdr *eth = skb_eth_hdr(skb);
 	struct ipvl_addr *addr;
 	void *lyr3h;
 	int addr_type;
@@ -604,7 +634,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 					consume_skb(skb);
 					return NET_XMIT_DROP;
 				}
-				return ipvlan_rcv_frame(addr, &skb, true);
+				ipvlan_rcv_frame(addr, &skb, true);
+				return NET_XMIT_SUCCESS;
 			}
 		}
 		skb = skb_share_check(skb, GFP_ATOMIC);
@@ -616,9 +647,11 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 		 * the skb for the main-dev. At the RX side we just return
 		 * RX_PASS for it to be processed further on the stack.
 		 */
-		return dev_forward_skb(ipvlan->phy_dev, skb);
+		dev_forward_skb(ipvlan->phy_dev, skb);
+		return NET_XMIT_SUCCESS;
 
 	} else if (is_multicast_ether_addr(eth->h_dest)) {
+		skb_reset_mac_header(skb);
 		ipvlan_skb_crossing_ns(skb, NULL);
 		ipvlan_multicast_enqueue(ipvlan->port, skb, true);
 		return NET_XMIT_SUCCESS;