linux_dsm_epyc7002/include/net/dst_ops.h
Hangbin Liu bd085ef678 net: add bool confirm_neigh parameter for dst_ops.update_pmtu
The MTU update code is supposed to be invoked in response to real
networking events that update the PMTU. In IPv6 PMTU update function
__ip6_rt_update_pmtu() we called dst_confirm_neigh() to update neighbor
confirmed time.

But for tunnel code, it will call pmtu before xmit, like:
  - tnl_update_pmtu()
    - skb_dst_update_pmtu()
      - ip6_rt_update_pmtu()
        - __ip6_rt_update_pmtu()
          - dst_confirm_neigh()

If the tunnel remote dst mac address changed and we still do the neigh
confirm, we will not be able to update neigh cache and ping6 remote
will failed.

So for this ip_tunnel_xmit() case, _EVEN_ if the MTU is changed, we
should not be invoking dst_confirm_neigh() as we have no evidence
of successful two-way communication at this point.

On the other hand it is also important to keep the neigh reachability fresh
for TCP flows, so we cannot remove this dst_confirm_neigh() call.

To fix the issue, we have to add a new bool parameter for dst_ops.update_pmtu
to choose whether we should do neigh update or not. I will add the parameter
in this patch and set all the callers to true to comply with the previous
way, and fix the tunnel code one by one on later patches.

v5: No change.
v4: No change.
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.

Suggested-by: David Miller <davem@davemloft.net>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-24 22:28:54 -08:00

72 lines
2.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _NET_DST_OPS_H
#define _NET_DST_OPS_H
#include <linux/types.h>
#include <linux/percpu_counter.h>
#include <linux/cache.h>
struct dst_entry;
struct kmem_cachep;
struct net_device;
struct sk_buff;
struct sock;
struct net;
struct dst_ops {
unsigned short family;
unsigned int gc_thresh;
int (*gc)(struct dst_ops *ops);
struct dst_entry * (*check)(struct dst_entry *, __u32 cookie);
unsigned int (*default_advmss)(const struct dst_entry *);
unsigned int (*mtu)(const struct dst_entry *);
u32 * (*cow_metrics)(struct dst_entry *, unsigned long);
void (*destroy)(struct dst_entry *);
void (*ifdown)(struct dst_entry *,
struct net_device *dev, int how);
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,
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);
struct neighbour * (*neigh_lookup)(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr);
void (*confirm_neigh)(const struct dst_entry *dst,
const void *daddr);
struct kmem_cache *kmem_cachep;
struct percpu_counter pcpuc_entries ____cacheline_aligned_in_smp;
};
static inline int dst_entries_get_fast(struct dst_ops *dst)
{
return percpu_counter_read_positive(&dst->pcpuc_entries);
}
static inline int dst_entries_get_slow(struct dst_ops *dst)
{
return percpu_counter_sum_positive(&dst->pcpuc_entries);
}
static inline void dst_entries_add(struct dst_ops *dst, int val)
{
percpu_counter_add(&dst->pcpuc_entries, val);
}
static inline int dst_entries_init(struct dst_ops *dst)
{
return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
}
static inline void dst_entries_destroy(struct dst_ops *dst)
{
percpu_counter_destroy(&dst->pcpuc_entries);
}
#endif