Skip to content

Commit

Permalink
Merge branch 'disable-neigh-update-for-tunnels-during-pmtu-update'
Browse files Browse the repository at this point in the history 
Hangbin Liu says:

====================
disable neigh update for tunnels during pmtu update

When we setup a pair of gretap, ping each other and create neighbour cache.
Then delete and recreate one side. We will never be able to ping6 to the new
created gretap.

The reason is when we ping6 remote via gretap, we will call like

gre_tap_xmit()
 - ip_tunnel_xmit()
   - tnl_update_pmtu()
     - skb_dst_update_pmtu()
       - ip6_rt_update_pmtu()
         - __ip6_rt_update_pmtu()
           - dst_confirm_neigh()
             - ip6_confirm_neigh()
               - __ipv6_confirm_neigh()
                 - n->confirmed = now

As the confirmed time updated, in neigh_timer_handler() the check for
NUD_DELAY confirm time will pass and the neigh state will back to
NUD_REACHABLE. So the old/wrong mac address will be used again.

If we do not update the confirmed time, the neigh state will go to
neigh->nud_state = NUD_PROBE; then go to NUD_FAILED and re-create the
neigh later, which is what IPv4 does.

We couldn't remove the ip6_confirm_neigh() directly as we still need it
for TCP flows. To fix it, we have to pass a bool parameter to
dst_ops.update_pmtu() and only disable neighbor update for tunnels.

v5: No code change, upate some commits description
v4: No code change, upate some commits description
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
  • Loading branch information
David S. Miller committed Dec 25, 2019
2 parents ff43ae4 + f081042 commit 47d0b2f
Show file tree
Hide file tree
Showing 19 changed files with 58 additions and 32 deletions.
2 changes: 1 addition & 1 deletion drivers/net/gtp.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -540,7 +540,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
mtu = dst_mtu(&rt->dst);
}

rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false);

if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
mtu < ntohs(iph->tot_len)) {
Expand Down
13 changes: 11 additions & 2 deletions include/net/dst.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -516,7 +516,16 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
struct dst_entry *dst = skb_dst(skb);

if (dst && dst->ops->update_pmtu)
dst->ops->update_pmtu(dst, NULL, skb, mtu);
dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
}

/* update dst pmtu but not do neighbor confirm */
static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
{
struct dst_entry *dst = skb_dst(skb);

if (dst && dst->ops->update_pmtu)
dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
}

static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
Expand All @@ -526,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
u32 encap_mtu = dst_mtu(encap_dst);

if (skb->len > encap_mtu - headroom)
skb_dst_update_pmtu(skb, encap_mtu - headroom);
skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
}

#endif /* _NET_DST_H */
3 changes: 2 additions & 1 deletion include/net/dst_ops.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,8 @@ struct dst_ops {
struct dst_entry * (*negative_advice)(struct dst_entry *);
void (*link_failure)(struct sk_buff *);
void (*update_pmtu)(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
void (*redirect)(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
Expand Down
3 changes: 2 additions & 1 deletion net/bridge/br_nf_core.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,8 @@
#endif

static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
}

Expand Down
6 changes: 4 additions & 2 deletions net/decnet/dn_route.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how);
static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
static void dn_dst_link_failure(struct sk_buff *);
static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb , u32 mtu);
struct sk_buff *skb , u32 mtu,
bool confirm_neigh);
static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,
Expand Down Expand Up @@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops)
* advertise to the other end).
*/
static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
struct dn_route *rt = (struct dn_route *) dst;
struct neighbour *n = rt->n;
Expand Down
2 changes: 1 addition & 1 deletion net/ipv4/inet_connection_sock.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
if (!dst)
goto out;
}
dst->ops->update_pmtu(dst, sk, NULL, mtu);
dst->ops->update_pmtu(dst, sk, NULL, mtu, true);

dst = __sk_dst_check(sk, 0);
if (!dst)
Expand Down
2 changes: 1 addition & 1 deletion net/ipv4/ip_tunnel.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;

if (skb_valid_dst(skb))
skb_dst_update_pmtu(skb, mtu);
skb_dst_update_pmtu_no_confirm(skb, mtu);

if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
Expand Down
2 changes: 1 addition & 1 deletion net/ipv4/ip_vti.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,

mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst_update_pmtu(skb, mtu);
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
Expand Down
9 changes: 6 additions & 3 deletions net/ipv4/route.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static void ipv4_dst_destroy(struct dst_entry *dst);
Expand Down Expand Up @@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
}

static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
struct rtable *rt = (struct rtable *) dst;
struct flowi4 fl4;
Expand Down Expand Up @@ -2687,7 +2689,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
}

static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
}

Expand Down
5 changes: 3 additions & 2 deletions net/ipv4/xfrm4_policy.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
}

static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;

path->ops->update_pmtu(path, sk, skb, mtu);
path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
}

static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
Expand Down
2 changes: 1 addition & 1 deletion net/ipv6/inet6_connection_sock.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)

if (IS_ERR(dst))
return NULL;
dst->ops->update_pmtu(dst, sk, NULL, mtu);
dst->ops->update_pmtu(dst, sk, NULL, mtu, true);

dst = inet6_csk_route_socket(sk, &fl6);
return IS_ERR(dst) ? NULL : dst;
Expand Down
2 changes: 1 addition & 1 deletion net/ipv6/ip6_gre.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,

/* TooBig packet may have updated dst->dev's mtu */
if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false);

err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
NEXTHDR_GRE);
Expand Down
4 changes: 2 additions & 2 deletions net/ipv6/ip6_tunnel.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (rel_info > dst_mtu(skb_dst(skb2)))
goto out;

skb_dst_update_pmtu(skb2, rel_info);
skb_dst_update_pmtu_no_confirm(skb2, rel_info);
}

icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
Expand Down Expand Up @@ -1132,7 +1132,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
IPV6_MIN_MTU : IPV4_MIN_MTU);

skb_dst_update_pmtu(skb, mtu);
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
*pmtu = mtu;
err = -EMSGSIZE;
Expand Down
2 changes: 1 addition & 1 deletion net/ipv6/ip6_vti.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)

mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst_update_pmtu(skb, mtu);
skb_dst_update_pmtu_no_confirm(skb, mtu);

if (skb->protocol == htons(ETH_P_IPV6)) {
if (mtu < IPV6_MIN_MTU)
Expand Down
22 changes: 15 additions & 7 deletions net/ipv6/route.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,8 @@ static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
Expand Down Expand Up @@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
}

static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
}

Expand Down Expand Up @@ -2692,7 +2694,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
}

static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
const struct ipv6hdr *iph, u32 mtu)
const struct ipv6hdr *iph, u32 mtu,
bool confirm_neigh)
{
const struct in6_addr *daddr, *saddr;
struct rt6_info *rt6 = (struct rt6_info *)dst;
Expand All @@ -2710,7 +2713,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
daddr = NULL;
saddr = NULL;
}
dst_confirm_neigh(dst, daddr);

if (confirm_neigh)
dst_confirm_neigh(dst, daddr);

mtu = max_t(u32, mtu, IPV6_MIN_MTU);
if (mtu >= dst_mtu(dst))
return;
Expand Down Expand Up @@ -2764,9 +2770,11 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
}

static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu,
confirm_neigh);
}

void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
Expand All @@ -2785,7 +2793,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,

dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true);
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
Expand Down
2 changes: 1 addition & 1 deletion net/ipv6/sit.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
}

if (tunnel->parms.iph.daddr)
skb_dst_update_pmtu(skb, mtu);
skb_dst_update_pmtu_no_confirm(skb, mtu);

if (skb->len > mtu && !skb_is_gso(skb)) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
Expand Down
5 changes: 3 additions & 2 deletions net/ipv6/xfrm6_policy.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
}

static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;

path->ops->update_pmtu(path, sk, skb, mtu);
path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
}

static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
Expand Down
2 changes: 1 addition & 1 deletion net/netfilter/ipvs/ip_vs_xmit.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
struct rtable *ort = skb_rtable(skb);

if (!skb->dev && sk && sk_fullsock(sk))
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true);
}

static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,
Expand Down
2 changes: 1 addition & 1 deletion net/sctp/transport.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)

pf->af->from_sk(&addr, sk);
pf->to_sk_daddr(&t->ipaddr, sk);
dst->ops->update_pmtu(dst, sk, NULL, pmtu);
dst->ops->update_pmtu(dst, sk, NULL, pmtu, true);
pf->to_sk_daddr(&addr, sk);

dst = sctp_transport_dst_check(t);
Expand Down

0 comments on commit 47d0b2f

Please sign in to comment.