*/
#include <linux/kernel.h>
+#include <linux/kmemcheck.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/ip.h>
+
+/**
+ * inet_twsk_unhash - unhash a timewait socket from established hash
+ * @tw: timewait socket
+ *
+ * unhash a timewait socket from established hash, if hashed.
+ * ehash lock must be held by caller.
+ * Returns 1 if caller should call inet_twsk_put() after lock release.
+ */
+int inet_twsk_unhash(struct inet_timewait_sock *tw)
+{
+ if (hlist_nulls_unhashed(&tw->tw_node))
+ return 0;
+
+ hlist_nulls_del_rcu(&tw->tw_node);
+ sk_nulls_node_init(&tw->tw_node);
+ /*
+ * We cannot call inet_twsk_put() ourself under lock,
+ * caller must call it for us.
+ */
+ return 1;
+}
+
+/**
+ * inet_twsk_bind_unhash - unhash a timewait socket from bind hash
+ * @tw: timewait socket
+ * @hashinfo: hashinfo pointer
+ *
+ * unhash a timewait socket from bind hash, if hashed.
+ * bind hash lock must be held by caller.
+ * Returns 1 if caller should call inet_twsk_put() after lock release.
+ */
+int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
+ struct inet_hashinfo *hashinfo)
+{
+ struct inet_bind_bucket *tb = tw->tw_tb;
+
+ if (!tb)
+ return 0;
+
+ __hlist_del(&tw->tw_bind_node);
+ tw->tw_tb = NULL;
+ inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+ /*
+ * We cannot call inet_twsk_put() ourself under lock,
+ * caller must call it for us.
+ */
+ return 1;
+}
+
/* Must be called with locally disabled BHs. */
static void __inet_twsk_kill(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
struct inet_bind_hashbucket *bhead;
- struct inet_bind_bucket *tb;
+ int refcnt;
/* Unlink from established hashes. */
- rwlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
- write_lock(lock);
- if (hlist_unhashed(&tw->tw_node)) {
- write_unlock(lock);
- return;
- }
- __hlist_del(&tw->tw_node);
- sk_node_init(&tw->tw_node);
- write_unlock(lock);
+ spin_lock(lock);
+ refcnt = inet_twsk_unhash(tw);
+ spin_unlock(lock);
/* Disassociate with bind bucket. */
- bhead = &hashinfo->bhash[inet_bhashfn(tw->tw_num, hashinfo->bhash_size)];
+ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
+ hashinfo->bhash_size)];
+
spin_lock(&bhead->lock);
- tb = tw->tw_tb;
- __hlist_del(&tw->tw_bind_node);
- tw->tw_tb = NULL;
- inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+ refcnt += inet_twsk_bind_unhash(tw, hashinfo);
spin_unlock(&bhead->lock);
+
#ifdef SOCK_REFCNT_DEBUG
if (atomic_read(&tw->tw_refcnt) != 1) {
printk(KERN_DEBUG "%s timewait_sock %p refcnt=%d\n",
tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt));
}
#endif
- inet_twsk_put(tw);
+ while (refcnt) {
+ inet_twsk_put(tw);
+ refcnt--;
+ }
+}
+
+static noinline void inet_twsk_free(struct inet_timewait_sock *tw)
+{
+ struct module *owner = tw->tw_prot->owner;
+ twsk_destructor((struct 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);
}
+void inet_twsk_put(struct inet_timewait_sock *tw)
+{
+ if (atomic_dec_and_test(&tw->tw_refcnt))
+ inet_twsk_free(tw);
+}
+EXPORT_SYMBOL_GPL(inet_twsk_put);
+
/*
* Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
- rwlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
struct inet_bind_hashbucket *bhead;
/* Step 1: Put TW into bind hash. Original socket stays there too.
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
- bhead = &hashinfo->bhash[inet_bhashfn(inet->num, hashinfo->bhash_size)];
+ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
+ hashinfo->bhash_size)];
spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
- BUG_TRAP(icsk->icsk_bind_hash);
+ WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
spin_unlock(&bhead->lock);
- write_lock(lock);
-
- /* Step 2: Remove SK from established hash. */
- if (__sk_del_node_init(sk))
- sock_prot_dec_use(sk->sk_prot);
+ spin_lock(lock);
- /* Step 3: Hash TW into TIMEWAIT chain. */
- inet_twsk_add_node(tw, &ehead->twchain);
- atomic_inc(&tw->tw_refcnt);
+ /*
+ * Step 2: Hash TW into TIMEWAIT chain.
+ * Should be done before removing sk from established chain
+ * because readers are lockless and search established first.
+ */
+ inet_twsk_add_node_rcu(tw, &ehead->twchain);
+
+ /* Step 3: Remove SK from established hash. */
+ if (__sk_nulls_del_node_init_rcu(sk))
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+
+ /*
+ * Notes :
+ * - We initially set tw_refcnt to 0 in inet_twsk_alloc()
+ * - We add one reference for the bhash link
+ * - We add one reference for the ehash link
+ * - We want this refcnt update done before allowing other
+ * threads to find this tw in ehash chain.
+ */
+ atomic_add(1 + 1 + 1, &tw->tw_refcnt);
- write_unlock(lock);
+ spin_unlock(lock);
}
-
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state)
if (tw != NULL) {
const struct inet_sock *inet = inet_sk(sk);
+ kmemcheck_annotate_bitfield(tw, flags);
+
/* Give us an identity. */
- tw->tw_daddr = inet->daddr;
- tw->tw_rcv_saddr = inet->rcv_saddr;
+ tw->tw_daddr = inet->inet_daddr;
+ tw->tw_rcv_saddr = inet->inet_rcv_saddr;
tw->tw_bound_dev_if = sk->sk_bound_dev_if;
- tw->tw_num = inet->num;
+ tw->tw_num = inet->inet_num;
tw->tw_state = TCP_TIME_WAIT;
tw->tw_substate = state;
- tw->tw_sport = inet->sport;
- tw->tw_dport = inet->dport;
+ tw->tw_sport = inet->inet_sport;
+ tw->tw_dport = inet->inet_dport;
tw->tw_family = sk->sk_family;
tw->tw_reuse = sk->sk_reuse;
tw->tw_hash = sk->sk_hash;
tw->tw_ipv6only = 0;
+ tw->tw_transparent = inet->transparent;
tw->tw_prot = sk->sk_prot_creator;
- atomic_set(&tw->tw_refcnt, 1);
+ twsk_net_set(tw, hold_net(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
+ * timewait socket.
+ */
+ atomic_set(&tw->tw_refcnt, 0);
inet_twsk_dead_node_init(tw);
__module_get(tw->tw_prot->owner);
}
return tw;
}
-
EXPORT_SYMBOL_GPL(inet_twsk_alloc);
/* Returns non-zero if quota exceeded. */
__inet_twsk_del_dead_node(tw);
spin_unlock(&twdr->death_lock);
__inet_twsk_kill(tw, twdr->hashinfo);
+#ifdef CONFIG_NET_NS
+ NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED);
+#endif
inet_twsk_put(tw);
killed++;
spin_lock(&twdr->death_lock);
}
twdr->tw_count -= killed;
- NET_ADD_STATS_BH(LINUX_MIB_TIMEWAITED, killed);
-
+#ifndef CONFIG_NET_NS
+ NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITED, killed);
+#endif
return ret;
}
/* We purged the entire slot, anything left? */
if (twdr->tw_count)
need_timer = 1;
+ twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1));
}
- twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1));
if (need_timer)
mod_timer(&twdr->tw_timer, jiffies + twdr->period);
out:
spin_unlock(&twdr->death_lock);
}
-
EXPORT_SYMBOL_GPL(inet_twdr_hangman);
void inet_twdr_twkill_work(struct work_struct *work)
spin_unlock_bh(&twdr->death_lock);
}
}
-
EXPORT_SYMBOL_GPL(inet_twdr_twkill_work);
/* These are always called from BH context. See callers in
spin_unlock(&twdr->death_lock);
__inet_twsk_kill(tw, twdr->hashinfo);
}
-
EXPORT_SYMBOL(inet_twsk_deschedule);
void inet_twsk_schedule(struct inet_timewait_sock *tw,
mod_timer(&twdr->tw_timer, jiffies + twdr->period);
spin_unlock(&twdr->death_lock);
}
-
EXPORT_SYMBOL_GPL(inet_twsk_schedule);
void inet_twdr_twcal_tick(unsigned long data)
&twdr->twcal_row[slot]) {
__inet_twsk_del_dead_node(tw);
__inet_twsk_kill(tw, twdr->hashinfo);
+#ifdef CONFIG_NET_NS
+ NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
+#endif
inet_twsk_put(tw);
killed++;
}
out:
if ((twdr->tw_count -= killed) == 0)
del_timer(&twdr->tw_timer);
- NET_ADD_STATS_BH(LINUX_MIB_TIMEWAITKILLED, killed);
+#ifndef CONFIG_NET_NS
+ NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITKILLED, killed);
+#endif
spin_unlock(&twdr->death_lock);
}
-
EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick);
+
+void inet_twsk_purge(struct inet_hashinfo *hashinfo,
+ struct inet_timewait_death_row *twdr, int family)
+{
+ struct inet_timewait_sock *tw;
+ struct sock *sk;
+ struct hlist_nulls_node *node;
+ unsigned int slot;
+
+ for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
+ struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
+restart_rcu:
+ rcu_read_lock();
+restart:
+ sk_nulls_for_each_rcu(sk, node, &head->twchain) {
+ tw = inet_twsk(sk);
+ if ((tw->tw_family != family) ||
+ atomic_read(&twsk_net(tw)->count))
+ continue;
+
+ if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt)))
+ continue;
+
+ if (unlikely((tw->tw_family != family) ||
+ atomic_read(&twsk_net(tw)->count))) {
+ inet_twsk_put(tw);
+ goto restart;
+ }
+
+ rcu_read_unlock();
+ inet_twsk_deschedule(tw, twdr);
+ inet_twsk_put(tw);
+ goto restart_rcu;
+ }
+ /* If the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(node) != slot)
+ goto restart;
+ rcu_read_unlock();
+ }
+}
+EXPORT_SYMBOL_GPL(inet_twsk_purge);