summaryrefslogtreecommitdiff
path: root/net/ipv4/inet_timewait_sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/inet_timewait_sock.c')
-rw-r--r--net/ipv4/inet_timewait_sock.c63
1 files changed, 54 insertions, 9 deletions
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index e28075f0006e..337390ba85b4 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -92,13 +92,22 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
hlist_nulls_add_head_rcu(&tw->tw_node, list);
}
+static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+{
+ __inet_twsk_schedule(tw, timeo, false);
+}
+
/*
- * Enter the time wait state. This is called with locally disabled BH.
+ * Enter the time wait state.
* Essentially we whip up a timewait bucket, copy the relevant info into it
* from the SK, and mess with hash chains and list linkage.
+ *
+ * The caller must not access @tw anymore after this function returns.
*/
-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
- struct inet_hashinfo *hashinfo)
+void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
+ struct sock *sk,
+ struct inet_hashinfo *hashinfo,
+ int timeo)
{
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -114,6 +123,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
hashinfo->bhash_size)];
bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
+ local_bh_disable();
spin_lock(&bhead->lock);
spin_lock(&bhead2->lock);
@@ -129,26 +139,34 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
spin_lock(lock);
+ /* Step 2: Hash TW into tcp ehash chain */
inet_twsk_add_node_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- spin_unlock(lock);
+ /* Ensure above writes are committed into memory before updating the
+ * refcount.
+ * Provides ordering vs later refcount_inc().
+ */
+ smp_wmb();
/* tw_refcnt is set to 3 because we have :
* - one reference for bhash chain.
* - one reference for ehash chain.
* - one reference for timer.
- * We can use atomic_set() because prior spin_lock()/spin_unlock()
- * committed into memory all tw fields.
* Also note that after this point, we lost our implicit reference
* so we are not allowed to use tw anymore.
*/
refcount_set(&tw->tw_refcnt, 3);
+
+ inet_twsk_schedule(tw, timeo);
+
+ spin_unlock(lock);
+ local_bh_enable();
}
-EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
+EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule);
static void tw_timer_handler(struct timer_list *t)
{
@@ -192,7 +210,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
tw->tw_prot = sk->sk_prot_creator;
atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
twsk_net_set(tw, sock_net(sk));
- timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
+ timer_setup(&tw->tw_timer, tw_timer_handler, 0);
/*
* Because we use RCU lookups, we should not set tw_refcnt
* to a non null value before everything is setup for this
@@ -217,7 +235,34 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc);
*/
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
{
- if (del_timer_sync(&tw->tw_timer))
+ struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
+
+ /* inet_twsk_purge() walks over all sockets, including tw ones,
+ * and removes them via inet_twsk_deschedule_put() after a
+ * refcount_inc_not_zero().
+ *
+ * inet_twsk_hashdance_schedule() must (re)init the refcount before
+ * arming the timer, i.e. inet_twsk_purge can obtain a reference to
+ * a twsk that did not yet schedule the timer.
+ *
+ * The ehash lock synchronizes these two:
+ * After acquiring the lock, the timer is always scheduled (else
+ * timer_shutdown returns false), because hashdance_schedule releases
+ * the ehash lock only after completing the timer initialization.
+ *
+ * Without grabbing the ehash lock, we get:
+ * 1) cpu x sets twsk refcount to 3
+ * 2) cpu y bumps refcount to 4
+ * 3) cpu y calls inet_twsk_deschedule_put() and shuts timer down
+ * 4) cpu x tries to start timer, but mod_timer is a noop post-shutdown
+ * -> timer refcount is never decremented.
+ */
+ spin_lock(lock);
+ /* Makes sure hashdance_schedule() has completed */
+ spin_unlock(lock);
+
+ if (timer_shutdown_sync(&tw->tw_timer))
inet_twsk_kill(tw);
inet_twsk_put(tw);
}