linux-stable/include/net/dst_ops.h
Jon Maxwell af6d10345c ipv6: remove max_size check inline with ipv4
In ip6_dst_gc() replace:

  if (entries > gc_thresh)

With:

  if (entries > ops->gc_thresh)

Sending Ipv6 packets in a loop via a raw socket triggers an issue where a
route is cloned by ip6_rt_cache_alloc() for each packet sent. This quickly
consumes the Ipv6 max_size threshold which defaults to 4096 resulting in
these warnings:

[1]   99.187805] dst_alloc: 7728 callbacks suppressed
[2] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.
.
.
[300] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.

When this happens the packet is dropped and sendto() gets a network is
unreachable error:

remaining pkt 200557 errno 101
remaining pkt 196462 errno 101
.
.
remaining pkt 126821 errno 101

Implement David Aherns suggestion to remove max_size check seeing that Ipv6
has a GC to manage memory usage. Ipv4 already does not check max_size.

Here are some memory comparisons for Ipv4 vs Ipv6 with the patch:

Test by running 5 instances of a program that sends UDP packets to a raw
socket 5000000 times. Compare Ipv4 and Ipv6 performance with a similar
program.

Ipv4:

Before test:

MemFree:        29427108 kB
Slab:             237612 kB

ip6_dst_cache       1912   2528    256   32    2 : tunables    0    0    0
xfrm_dst_cache         0      0    320   25    2 : tunables    0    0    0
ip_dst_cache        2881   3990    192   42    2 : tunables    0    0    0

During test:

MemFree:        29417608 kB
Slab:             247712 kB

ip6_dst_cache       1912   2528    256   32    2 : tunables    0    0    0
xfrm_dst_cache         0      0    320   25    2 : tunables    0    0    0
ip_dst_cache       44394  44394    192   42    2 : tunables    0    0    0

After test:

MemFree:        29422308 kB
Slab:             238104 kB

ip6_dst_cache       1912   2528    256   32    2 : tunables    0    0    0
xfrm_dst_cache         0      0    320   25    2 : tunables    0    0    0
ip_dst_cache        3048   4116    192   42    2 : tunables    0    0    0

Ipv6 with patch:

Errno 101 errors are not observed anymore with the patch.

Before test:

MemFree:        29422308 kB
Slab:             238104 kB

ip6_dst_cache       1912   2528    256   32    2 : tunables    0    0    0
xfrm_dst_cache         0      0    320   25    2 : tunables    0    0    0
ip_dst_cache        3048   4116    192   42    2 : tunables    0    0    0

During Test:

MemFree:        29431516 kB
Slab:             240940 kB

ip6_dst_cache      11980  12064    256   32    2 : tunables    0    0    0
xfrm_dst_cache         0      0    320   25    2 : tunables    0    0    0
ip_dst_cache        3048   4116    192   42    2 : tunables    0    0    0

After Test:

MemFree:        29441816 kB
Slab:             238132 kB

ip6_dst_cache       1902   2432    256   32    2 : tunables    0    0    0
xfrm_dst_cache         0      0    320   25    2 : tunables    0    0    0
ip_dst_cache        3048   4116    192   42    2 : tunables    0    0    0

Tested-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230112012532.311021-1-jmaxwell37@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-01-13 20:59:14 -08:00

73 lines
2.1 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;
void (*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);
}
#define DST_PERCPU_COUNTER_BATCH 32
static inline void dst_entries_add(struct dst_ops *dst, int val)
{
percpu_counter_add_batch(&dst->pcpuc_entries, val,
DST_PERCPU_COUNTER_BATCH);
}
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