diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b27b8873415ae44c267af59f3191c65614a4fac6..a1f5d9efe9b431bb95c69eff53312b48522ba8b2 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -125,6 +125,9 @@ route/max_size - INTEGER From linux kernel 3.6 onwards, this is deprecated for ipv4 as route cache is no longer used. + From linux kernel 6.3 onwards, this is deprecated for ipv6 + as garbage collection manages cached route entries. + neigh/default/gc_thresh1 - INTEGER Minimum number of entries to keep. Garbage collector will not purge entries if there are fewer than this number. diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 250e2318885820358ccf143d453976e1f98a6c70..f3f5d02f2e734e77f064ab7a008f4e4075d64047 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -17,7 +17,7 @@ struct dst_ops { unsigned short family; unsigned int gc_thresh; - int (*gc)(struct dst_ops *ops); + KABI_REPLACE(int (*gc)(struct dst_ops *ops), 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 *); diff --git a/net/core/dst.c b/net/core/dst.c index fb3bcba87744d3f48fcfbdd229f3313c7520f196..453ec8aafc4aba32c2d56f6b849f49dcf08ea9f1 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -83,12 +83,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, if (ops->gc && !(flags & DST_NOCOUNT) && - dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) { - pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); - return NULL; - } - } + dst_entries_get_fast(ops) > ops->gc_thresh) + ops->gc(ops); dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 73a0a3908824bad2acf809d3096278cf330713fe..9603e009cd23075551e17a57e73699f08d360567 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -89,7 +89,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static int ip6_dst_gc(struct dst_ops *ops); +static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -3179,11 +3179,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, return dst; } -static int ip6_dst_gc(struct dst_ops *ops) +static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; - int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; @@ -3191,11 +3190,10 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries; entries = dst_entries_get_fast(ops); - if (entries > rt_max_size) + if (entries > ops->gc_thresh) entries = dst_entries_get_slow(ops); - if (time_after(rt_last_gc + rt_min_interval, jiffies) && - entries <= rt_max_size) + if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); @@ -3205,7 +3203,6 @@ static int ip6_dst_gc(struct dst_ops *ops) out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); - return entries > rt_max_size; } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, @@ -6358,7 +6355,7 @@ static int __net_init ip6_route_net_init(struct net *net) #endif net->ipv6.sysctl.flush_delay = 0; - net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;