Get the ingress interface and increment ICMP counters based on that instead of skb->dev when the the dev is a VRF device.
This is a follow up on the following message: https://www.spinics.net/lists/netdev/msg560268.html v2: Avoid changing skb->dev since it has unintended effect for local delivery (David Ahern). Signed-off-by: Stephen Suryaputra <ssuryae...@gmail.com> --- include/net/addrconf.h | 16 ++++++++++++++++ net/ipv6/icmp.c | 17 +++++++++++------ net/ipv6/reassembly.c | 4 ++-- 3 files changed, 29 insertions(+), 8 deletions(-) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 269ec27385e9..2e36e29f9f54 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -356,6 +356,22 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->ip6_ptr); } +/** + * __in6_dev_stats_get - get inet6_dev pointer for stats + * @dev: network device + * @skb: skb for original incoming interface if neeeded + * + * Caller must hold rcu_read_lock or RTNL, because this function + * does not take a reference on the inet6_dev. + */ +static inline struct inet6_dev *__in6_dev_stats_get(const struct net_device *dev, + const struct sk_buff *skb) +{ + if (netif_is_l3_master(dev)) + dev = dev_get_by_index_rcu(dev_net(dev), inet6_iif(skb)); + return __in6_dev_get(dev); +} + /** * __in6_dev_get_safely - get inet6_dev pointer from netdevice * @dev: network device diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 802faa2fcc0e..f54191cd1d7b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -398,23 +398,28 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, return ERR_PTR(err); } -static int icmp6_iif(const struct sk_buff *skb) +static struct net_device *icmp6_dev(const struct sk_buff *skb) { - int iif = skb->dev->ifindex; + struct net_device *dev = skb->dev; /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so * get the real device index. Same is needed for replies to a link * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { + if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); if (rt6) - iif = rt6->rt6i_idev->dev->ifindex; + dev = rt6->rt6i_idev->dev; } - return iif; + return dev; +} + +static int icmp6_iif(const struct sk_buff *skb) +{ + return icmp6_dev(skb)->ifindex; } /* @@ -801,7 +806,7 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) static int icmpv6_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - struct net_device *dev = skb->dev; + struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 1a832f5e190b..e219e669ac11 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -302,7 +302,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_network_header_len(skb)); rcu_read_lock(); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); + __IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS); rcu_read_unlock(); fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; @@ -316,7 +316,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n"); out_fail: rcu_read_lock(); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + __IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); inet_frag_kill(&fq->q); return -1; -- 2.17.1
