From 0ddcf43d5d4a03ded1ee3f6b3b72a0cbed4e90b1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 6 Mar 2015 13:47:00 -0800 Subject: ipv4: FIB Local/MAIN table collapse This patch is meant to collapse local and main into one by converting tb_data from an array to a pointer. Doing this allows us to point the local table into the main while maintaining the same variables in the table. As such the tb_data was converted from an array to a pointer, and a new array called data is added in order to still provide an object for tb_data to point to. In order to track the origin of the fib aliases a tb_id value was added in a hole that existed on 64b systems. Using this we can also reverse the merge in the event that custom FIB rules are enabled. With this patch I am seeing an improvement of 20ns to 30ns for routing lookups as long as custom rules are not enabled, with custom rules enabled we fall back to split tables and the original behavior. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/fib_rules.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/core/fib_rules.c') diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 44706e81b2e0..b55677fed1c8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -492,6 +492,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) goto errout; } + if (ops->delete) { + err = ops->delete(rule); + if (err) + goto errout; + } + list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { @@ -517,8 +523,6 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); - if (ops->delete) - ops->delete(rule); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); -- cgit v1.2.3 From efd7ef1c1929d7a0329d4349252863c04d6f1729 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 11 Mar 2015 23:04:08 -0500 Subject: net: Kill hold_net release_net hold_net and release_net were an idea that turned out to be useless. The code has been disabled since 2008. Kill the code it is long past due. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- include/net/fib_rules.h | 9 +-------- include/net/net_namespace.h | 29 ----------------------------- include/net/sock.h | 2 +- net/core/dev.c | 2 -- net/core/fib_rules.c | 17 +++-------------- net/core/neighbour.c | 9 ++------- net/core/net_namespace.c | 11 ----------- net/core/sock.c | 1 - net/ipv4/fib_semantics.c | 3 +-- net/ipv4/inet_hashtables.c | 3 +-- net/ipv4/inet_timewait_sock.c | 3 +-- net/ipv6/addrlabel.c | 5 +---- net/ipv6/ip6_flowlabel.c | 3 +-- net/openvswitch/datapath.c | 4 +--- 15 files changed, 14 insertions(+), 90 deletions(-) (limited to 'net/core/fib_rules.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1354ae83efc8..cede40d9cac9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1864,8 +1864,7 @@ static inline void dev_net_set(struct net_device *dev, struct net *net) { #ifdef CONFIG_NET_NS - release_net(dev->nd_net); - dev->nd_net = hold_net(net); + dev->nd_net = net; #endif } diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 88d2ae526961..6d67383a5114 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -95,17 +95,10 @@ static inline void fib_rule_get(struct fib_rule *rule) atomic_inc(&rule->refcnt); } -static inline void fib_rule_put_rcu(struct rcu_head *head) -{ - struct fib_rule *rule = container_of(head, struct fib_rule, rcu); - release_net(rule->fr_net); - kfree(rule); -} - static inline void fib_rule_put(struct fib_rule *rule) { if (atomic_dec_and_test(&rule->refcnt)) - call_rcu(&rule->rcu, fib_rule_put_rcu); + kfree_rcu(rule, rcu); } static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index e086f4030dd2..fab51ceeabf3 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -49,11 +49,6 @@ struct net { atomic_t count; /* To decided when the network * namespace should be shut down. */ -#ifdef NETNS_REFCNT_DEBUG - atomic_t use_count; /* To track references we - * destroy on demand - */ -#endif spinlock_t rules_mod_lock; atomic64_t cookie_gen; @@ -236,30 +231,6 @@ int net_eq(const struct net *net1, const struct net *net2) #endif -#ifdef NETNS_REFCNT_DEBUG -static inline struct net *hold_net(struct net *net) -{ - if (net) - atomic_inc(&net->use_count); - return net; -} - -static inline void release_net(struct net *net) -{ - if (net) - atomic_dec(&net->use_count); -} -#else -static inline struct net *hold_net(struct net *net) -{ - return net; -} - -static inline void release_net(struct net *net) -{ -} -#endif - #ifdef CONFIG_NET_NS static inline void write_pnet(struct net **pnet, struct net *net) diff --git a/include/net/sock.h b/include/net/sock.h index d996c633bec2..95b2c1c220f9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2204,7 +2204,7 @@ static inline void sk_change_net(struct sock *sk, struct net *net) if (!net_eq(current_net, net)) { put_net(current_net); - sock_net_set(sk, hold_net(net)); + sock_net_set(sk, net); } } diff --git a/net/core/dev.c b/net/core/dev.c index 962ee9d71964..39fe369b46ad 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6841,8 +6841,6 @@ void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; - release_net(dev_net(dev)); - netif_free_tx_queues(dev); #ifdef CONFIG_SYSFS kvfree(dev->_rx); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index b55677fed1c8..68ea6950cad1 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -31,7 +31,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->pref = pref; r->table = table; r->flags = flags; - r->fr_net = hold_net(ops->fro_net); + r->fr_net = ops->fro_net; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; @@ -116,7 +116,6 @@ static int __fib_rules_register(struct fib_rules_ops *ops) if (ops->family == o->family) goto errout; - hold_net(net); list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0; errout: @@ -160,15 +159,6 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) } } -static void fib_rules_put_rcu(struct rcu_head *head) -{ - struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); - struct net *net = ops->fro_net; - - release_net(net); - kfree(ops); -} - void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; @@ -178,7 +168,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops) fib_rules_cleanup_ops(ops); spin_unlock(&net->rules_mod_lock); - call_rcu(&ops->rcu, fib_rules_put_rcu); + kfree_rcu(ops, rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); @@ -303,7 +293,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) err = -ENOMEM; goto errout; } - rule->fr_net = hold_net(net); + rule->fr_net = net; if (tb[FRA_PRIORITY]) rule->pref = nla_get_u32(tb[FRA_PRIORITY]); @@ -423,7 +413,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) return 0; errout_free: - release_net(rule->fr_net); kfree(rule); errout: rules_ops_put(ops); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ad07990e943d..0e8b32efc031 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -591,7 +591,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, if (!n) goto out; - write_pnet(&n->net, hold_net(net)); + write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; if (dev) @@ -600,7 +600,6 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, if (tbl->pconstructor && tbl->pconstructor(n)) { if (dev) dev_put(dev); - release_net(net); kfree(n); n = NULL; goto out; @@ -634,7 +633,6 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, tbl->pdestructor(n); if (n->dev) dev_put(n->dev); - release_net(pneigh_net(n)); kfree(n); return 0; } @@ -657,7 +655,6 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) tbl->pdestructor(n); if (n->dev) dev_put(n->dev); - release_net(pneigh_net(n)); kfree(n); continue; } @@ -1428,11 +1425,10 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; - write_pnet(&p->net, hold_net(net)); + write_pnet(&p->net, net); p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { - release_net(net); dev_put(dev); kfree(p); return NULL; @@ -1472,7 +1468,6 @@ EXPORT_SYMBOL(neigh_parms_release); static void neigh_parms_destroy(struct neigh_parms *parms) { - release_net(neigh_parms_net(parms)); kfree(parms); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb5290b8c428..e5e96b0f6717 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -236,10 +236,6 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) net->user_ns = user_ns; idr_init(&net->netns_ids); -#ifdef NETNS_REFCNT_DEBUG - atomic_set(&net->use_count, 0); -#endif - list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); if (error < 0) @@ -294,13 +290,6 @@ out_free: static void net_free(struct net *net) { -#ifdef NETNS_REFCNT_DEBUG - if (unlikely(atomic_read(&net->use_count) != 0)) { - pr_emerg("network namespace not free! Usage: %d\n", - atomic_read(&net->use_count)); - return; - } -#endif kfree(rcu_access_pointer(net->gen)); kmem_cache_free(net_cachep, net); } diff --git a/net/core/sock.c b/net/core/sock.c index a9a9c2ff9260..c8842f279f7a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1455,7 +1455,6 @@ void sk_release_kernel(struct sock *sk) sock_hold(sk); sock_release(sk->sk_socket); - release_net(sock_net(sk)); sock_net_set(sk, get_net(&init_net)); sock_put(sk); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c6d267442dac..66c1e4fbf884 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -213,7 +213,6 @@ static void free_fib_info_rcu(struct rcu_head *head) rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); - release_net(fi->fib_net); if (fi->fib_metrics != (u32 *) dst_default_metrics) kfree(fi->fib_metrics); kfree(fi); @@ -814,7 +813,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } else fi->fib_metrics = (u32 *) dst_default_metrics; - fi->fib_net = hold_net(net); + fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; fi->fib_flags = cfg->fc_flags; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9111a4e22155..f6a12b97d12b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -61,7 +61,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); if (tb != NULL) { - write_pnet(&tb->ib_net, hold_net(net)); + write_pnet(&tb->ib_net, net); tb->port = snum; tb->fastreuse = 0; tb->fastreuseport = 0; @@ -79,7 +79,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket { if (hlist_empty(&tb->owners)) { __hlist_del(&tb->node); - release_net(ib_net(tb)); kmem_cache_free(cachep, tb); } } diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2bd980526631..86ebf020925b 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -98,7 +98,6 @@ void inet_twsk_free(struct inet_timewait_sock *tw) #ifdef SOCK_REFCNT_DEBUG pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw); #endif - release_net(twsk_net(tw)); kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw); module_put(owner); } @@ -196,7 +195,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_transparent = inet->transparent; tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); - twsk_net_set(tw, hold_net(sock_net(sk))); + twsk_net_set(tw, sock_net(sk)); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index e43e79d0a612..59c793040498 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -129,9 +129,6 @@ static const __net_initconst struct ip6addrlbl_init_table /* Object management */ static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) { -#ifdef CONFIG_NET_NS - release_net(p->lbl_net); -#endif kfree(p); } @@ -241,7 +238,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->label = label; INIT_HLIST_NODE(&newp->list); #ifdef CONFIG_NET_NS - newp->lbl_net = hold_net(net); + newp->lbl_net = net; #endif atomic_set(&newp->refcnt, 1); return newp; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index f45d6db50a45..457303886fd4 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -100,7 +100,6 @@ static void fl_free(struct ip6_flowlabel *fl) if (fl) { if (fl->share == IPV6_FL_S_PROCESS) put_pid(fl->owner.pid); - release_net(fl->fl_net); kfree(fl->opt); kfree_rcu(fl, rcu); } @@ -403,7 +402,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, } } - fl->fl_net = hold_net(net); + fl->fl_net = net; fl->expires = jiffies; err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); if (err) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 5bae7243c577..096c6276e6b9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -203,7 +203,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu) ovs_flow_tbl_destroy(&dp->table); free_percpu(dp->stats_percpu); - release_net(ovs_dp_get_net(dp)); kfree(dp->ports); kfree(dp); } @@ -1501,7 +1500,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (dp == NULL) goto err_free_reply; - ovs_dp_set_net(dp, hold_net(sock_net(skb->sk))); + ovs_dp_set_net(dp, sock_net(skb->sk)); /* Allocate table. */ err = ovs_flow_tbl_init(&dp->table); @@ -1575,7 +1574,6 @@ err_destroy_percpu: err_destroy_table: ovs_flow_tbl_destroy(&dp->table); err_free_dp: - release_net(ovs_dp_get_net(dp)); kfree(dp); err_free_reply: kfree_skb(reply); -- cgit v1.2.3