#include <asm/byteorder.h>
/* This is for all connections with a full identity, no wildcards.
- * One chain is dedicated to TIME_WAIT sockets.
- * I'll experiment with dynamic table growth later.
+ * The 'e' prefix stands for Establish, but we really put all sockets
+ * but LISTEN ones.
*/
struct inet_ehash_bucket {
struct hlist_nulls_head chain;
- struct hlist_nulls_head twchain;
};
/* There are a few simple rules, which allow for local port reuse by
*
* TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
*
- * TIME_WAIT sockets use a separate chain (twchain).
*/
struct inet_ehash_bucket *ehash;
spinlock_t *ehash_locks;
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */
-#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)\
- INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)
-
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
* not check it for lookups anymore, thanks Alexey. -DaveM
};
#define tw_tclass tw_tos
-static inline void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
- struct hlist_nulls_head *list)
-{
- hlist_nulls_add_head_rcu(&tw->tw_node, list);
-}
-
-static inline void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
- struct hlist_head *list)
-{
- hlist_add_head(&tw->tw_bind_node, list);
-}
-
static inline int inet_twsk_dead_hashed(const struct inet_timewait_sock *tw)
{
return !hlist_unhashed(&tw->tw_death_node);
return (struct inet_timewait_sock *)sk;
}
+void inet_twsk_free(struct inet_timewait_sock *tw);
void inet_twsk_put(struct inet_timewait_sock *tw);
int inet_twsk_unhash(struct inet_timewait_sock *tw);
*/
struct sock_common {
/* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
- * address on 64bit arches : cf INET_MATCH() and INET_TW_MATCH()
+ * address on 64bit arches : cf INET_MATCH()
*/
union {
__addrpair skc_addrpair;
#define sk_dontcopy_end __sk_common.skc_dontcopy_end
#define sk_hash __sk_common.skc_hash
#define sk_portpair __sk_common.skc_portpair
+#define sk_num __sk_common.skc_num
+#define sk_dport __sk_common.skc_dport
#define sk_addrpair __sk_common.skc_addrpair
#define sk_daddr __sk_common.skc_daddr
#define sk_rcv_saddr __sk_common.skc_rcv_saddr
if (atomic_dec_and_test(&sk->sk_refcnt))
sk_free(sk);
}
+/* Generic version of sock_put(), dealing with all sockets
+ * (TCP_TIMEWAIT, ESTABLISHED...)
+ */
+void sock_gen_put(struct sock *sk);
int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
TCP_SEQ_STATE_LISTENING,
TCP_SEQ_STATE_OPENREQ,
TCP_SEQ_STATE_ESTABLISHED,
- TCP_SEQ_STATE_TIME_WAIT,
};
int tcp_seq_open(struct inode *inode, struct file *file);
goto out_free_bind_bucket_cachep;
}
- for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) {
+ for (i = 0; i <= dccp_hashinfo.ehash_mask; i++)
INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i);
- INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].twchain, i);
- }
if (inet_ehash_locks_alloc(&dccp_hashinfo))
goto out_free_dccp_ehash;
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
-static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
+static int inet_twsk_diag_dump(struct sock *sk,
struct sk_buff *skb,
struct netlink_callback *cb,
struct inet_diag_req_v2 *r,
const struct nlattr *bc)
{
+ struct inet_timewait_sock *tw = inet_twsk(sk);
+
if (bc != NULL) {
struct inet_diag_entry entry;
num = 0;
- if (hlist_nulls_empty(&head->chain) &&
- hlist_nulls_empty(&head->twchain))
+ if (hlist_nulls_empty(&head->chain))
continue;
if (i > s_i)
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &head->chain) {
- struct inet_sock *inet = inet_sk(sk);
+ int res;
if (!net_eq(sock_net(sk), net))
continue;
if (!(r->idiag_states & (1 << sk->sk_state)))
goto next_normal;
if (r->sdiag_family != AF_UNSPEC &&
- sk->sk_family != r->sdiag_family)
+ sk->sk_family != r->sdiag_family)
goto next_normal;
- if (r->id.idiag_sport != inet->inet_sport &&
+ if (r->id.idiag_sport != htons(sk->sk_num) &&
r->id.idiag_sport)
goto next_normal;
- if (r->id.idiag_dport != inet->inet_dport &&
+ if (r->id.idiag_dport != sk->sk_dport &&
r->id.idiag_dport)
goto next_normal;
- if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
+ if (sk->sk_state == TCP_TIME_WAIT)
+ res = inet_twsk_diag_dump(sk, skb, cb, r, bc);
+ else
+ res = inet_csk_diag_dump(sk, skb, cb, r, bc);
+ if (res < 0) {
spin_unlock_bh(lock);
goto done;
}
++num;
}
- if (r->idiag_states & TCPF_TIME_WAIT) {
- struct inet_timewait_sock *tw;
-
- inet_twsk_for_each(tw, node,
- &head->twchain) {
- if (!net_eq(twsk_net(tw), net))
- continue;
-
- if (num < s_num)
- goto next_dying;
- if (r->sdiag_family != AF_UNSPEC &&
- tw->tw_family != r->sdiag_family)
- goto next_dying;
- if (r->id.idiag_sport != tw->tw_sport &&
- r->id.idiag_sport)
- goto next_dying;
- if (r->id.idiag_dport != tw->tw_dport &&
- r->id.idiag_dport)
- goto next_dying;
- if (inet_twsk_diag_dump(tw, skb, cb, r, bc) < 0) {
- spin_unlock_bh(lock);
- goto done;
- }
-next_dying:
- ++num;
- }
- }
spin_unlock_bh(lock);
}
}
EXPORT_SYMBOL_GPL(__inet_lookup_listener);
+/* All sockets share common refcount, but have different destructors */
+void sock_gen_put(struct sock *sk)
+{
+ if (!atomic_dec_and_test(&sk->sk_refcnt))
+ return;
+
+ if (sk->sk_state == TCP_TIME_WAIT)
+ inet_twsk_free(inet_twsk(sk));
+ else
+ sk_free(sk);
+}
+EXPORT_SYMBOL_GPL(sock_gen_put);
+
struct sock *__inet_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
if (likely(INET_MATCH(sk, net, acookie,
saddr, daddr, ports, dif))) {
if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
- goto begintw;
+ goto out;
if (unlikely(!INET_MATCH(sk, net, acookie,
saddr, daddr, ports, dif))) {
- sock_put(sk);
+ sock_gen_put(sk);
goto begin;
}
- goto out;
+ goto found;
}
}
/*
*/
if (get_nulls_value(node) != slot)
goto begin;
-
-begintw:
- /* Must check for a TIME_WAIT'er before going to listener hash. */
- sk_nulls_for_each_rcu(sk, node, &head->twchain) {
- if (sk->sk_hash != hash)
- continue;
- if (likely(INET_TW_MATCH(sk, net, acookie,
- saddr, daddr, ports,
- dif))) {
- if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
- sk = NULL;
- goto out;
- }
- if (unlikely(!INET_TW_MATCH(sk, net, acookie,
- saddr, daddr, ports,
- dif))) {
- inet_twsk_put(inet_twsk(sk));
- goto begintw;
- }
- goto out;
- }
- }
- /*
- * 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 begintw;
- sk = NULL;
out:
+ sk = NULL;
+found:
rcu_read_unlock();
return sk;
}
spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_nulls_node *node;
- struct inet_timewait_sock *tw;
+ struct inet_timewait_sock *tw = NULL;
int twrefcnt = 0;
spin_lock(lock);
- /* Check TIME-WAIT sockets first. */
- sk_nulls_for_each(sk2, node, &head->twchain) {
- if (sk2->sk_hash != hash)
- continue;
-
- if (likely(INET_TW_MATCH(sk2, net, acookie,
- saddr, daddr, ports, dif))) {
- tw = inet_twsk(sk2);
- if (twsk_unique(sk, sk2, twp))
- goto unique;
- else
- goto not_unique;
- }
- }
- tw = NULL;
-
- /* And established part... */
sk_nulls_for_each(sk2, node, &head->chain) {
if (sk2->sk_hash != hash)
continue;
+
if (likely(INET_MATCH(sk2, net, acookie,
- saddr, daddr, ports, dif)))
+ saddr, daddr, ports, dif))) {
+ if (sk2->sk_state == TCP_TIME_WAIT) {
+ tw = inet_twsk(sk2);
+ if (twsk_unique(sk, sk2, twp))
+ break;
+ }
goto not_unique;
+ }
}
-unique:
/* Must record num and sport now. Otherwise we will see
- * in hash table socket with a funny identity. */
+ * in hash table socket with a funny identity.
+ */
inet->inet_num = lport;
inet->inet_sport = htons(lport);
sk->sk_hash = hash;
refcnt += inet_twsk_bind_unhash(tw, hashinfo);
spin_unlock(&bhead->lock);
-#ifdef SOCK_REFCNT_DEBUG
- if (atomic_read(&tw->tw_refcnt) != 1) {
- pr_debug("%s timewait_sock %p refcnt=%d\n",
- tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt));
- }
-#endif
- while (refcnt) {
- inet_twsk_put(tw);
- refcnt--;
- }
+ BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt));
+ atomic_sub(refcnt, &tw->tw_refcnt);
}
-static noinline void inet_twsk_free(struct inet_timewait_sock *tw)
+void inet_twsk_free(struct inet_timewait_sock *tw)
{
struct module *owner = tw->tw_prot->owner;
twsk_destructor((struct sock *)tw);
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
+static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+ struct hlist_nulls_head *list)
+{
+ hlist_nulls_add_head_rcu(&tw->tw_node, list);
+}
+
+static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
+ struct hlist_head *list)
+{
+ hlist_add_head(&tw->tw_bind_node, list);
+}
+
/*
* 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
spin_lock(lock);
/*
- * Step 2: Hash TW into TIMEWAIT chain.
- * Should be done before removing sk from established chain
- * because readers are lockless and search established first.
+ * Step 2: Hash TW into tcp ehash chain.
+ * Notes :
+ * - tw_refcnt is set to 3 because :
+ * - We have one reference from bhash chain.
+ * - We have one reference from ehash chain.
+ * We can use atomic_set() because prior spin_lock()/spin_unlock()
+ * committed into memory all tw fields.
*/
- inet_twsk_add_node_rcu(tw, &ehead->twchain);
+ atomic_set(&tw->tw_refcnt, 1 + 1 + 1);
+ inet_twsk_add_node_rcu(tw, &ehead->chain);
- /* Step 3: Remove SK from established hash. */
+ /* 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);
- /*
- * 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);
-
spin_unlock(lock);
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
restart_rcu:
rcu_read_lock();
restart:
- sk_nulls_for_each_rcu(sk, node, &head->twchain) {
+ sk_nulls_for_each_rcu(sk, node, &head->chain) {
+ if (sk->sk_state != TCP_TIME_WAIT)
+ continue;
tw = inet_twsk(sk);
if ((tw->tw_family != family) ||
atomic_read(&twsk_net(tw)->count))
&tcp_hashinfo.ehash_mask,
0,
thash_entries ? 0 : 512 * 1024);
- for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) {
+ for (i = 0; i <= tcp_hashinfo.ehash_mask; i++)
INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
- INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i);
- }
+
if (inet_ehash_locks_alloc(&tcp_hashinfo))
panic("TCP: failed to alloc ehash_locks");
tcp_hashinfo.bhash =
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */
-static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
-{
- return hlist_nulls_empty(head) ? NULL :
- list_entry(head->first, struct inet_timewait_sock, tw_node);
-}
-
-static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
-{
- return !is_a_nulls(tw->tw_node.next) ?
- hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
-}
-
/*
* Get next listener socket follow cur. If cur is NULL, get first socket
* starting from bucket given in st->bucket; when st->bucket is zero the
return rc;
}
-static inline bool empty_bucket(struct tcp_iter_state *st)
+static inline bool empty_bucket(const struct tcp_iter_state *st)
{
- return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
- hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
+ return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain);
}
/*
for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
struct sock *sk;
struct hlist_nulls_node *node;
- struct inet_timewait_sock *tw;
spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
/* Lockless fast path for the common case of empty buckets */
rc = sk;
goto out;
}
- st->state = TCP_SEQ_STATE_TIME_WAIT;
- inet_twsk_for_each(tw, node,
- &tcp_hashinfo.ehash[st->bucket].twchain) {
- if (tw->tw_family != st->family ||
- !net_eq(twsk_net(tw), net)) {
- continue;
- }
- rc = tw;
- goto out;
- }
spin_unlock_bh(lock);
- st->state = TCP_SEQ_STATE_ESTABLISHED;
}
out:
return rc;
static void *established_get_next(struct seq_file *seq, void *cur)
{
struct sock *sk = cur;
- struct inet_timewait_sock *tw;
struct hlist_nulls_node *node;
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
++st->num;
++st->offset;
- if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
- tw = cur;
- tw = tw_next(tw);
-get_tw:
- while (tw && (tw->tw_family != st->family || !net_eq(twsk_net(tw), net))) {
- tw = tw_next(tw);
- }
- if (tw) {
- cur = tw;
- goto out;
- }
- spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
- st->state = TCP_SEQ_STATE_ESTABLISHED;
-
- /* Look for next non empty bucket */
- st->offset = 0;
- while (++st->bucket <= tcp_hashinfo.ehash_mask &&
- empty_bucket(st))
- ;
- if (st->bucket > tcp_hashinfo.ehash_mask)
- return NULL;
-
- spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
- sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
- } else
- sk = sk_nulls_next(sk);
+ sk = sk_nulls_next(sk);
sk_nulls_for_each_from(sk, node) {
if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
- goto found;
+ return sk;
}
- st->state = TCP_SEQ_STATE_TIME_WAIT;
- tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
- goto get_tw;
-found:
- cur = sk;
-out:
- return cur;
+ spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+ ++st->bucket;
+ return established_get_first(seq);
}
static void *established_get_idx(struct seq_file *seq, loff_t pos)
if (rc)
break;
st->bucket = 0;
+ st->state = TCP_SEQ_STATE_ESTABLISHED;
/* Fallthrough */
case TCP_SEQ_STATE_ESTABLISHED:
- case TCP_SEQ_STATE_TIME_WAIT:
- st->state = TCP_SEQ_STATE_ESTABLISHED;
if (st->bucket > tcp_hashinfo.ehash_mask)
break;
rc = established_get_first(seq);
}
break;
case TCP_SEQ_STATE_ESTABLISHED:
- case TCP_SEQ_STATE_TIME_WAIT:
rc = established_get_next(seq, v);
break;
}
if (v != SEQ_START_TOKEN)
spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
break;
- case TCP_SEQ_STATE_TIME_WAIT:
case TCP_SEQ_STATE_ESTABLISHED:
if (v)
spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
static int tcp4_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st;
+ struct sock *sk = v;
int len;
if (v == SEQ_START_TOKEN) {
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
case TCP_SEQ_STATE_ESTABLISHED:
- get_tcp4_sock(v, seq, st->num, &len);
+ if (sk->sk_state == TCP_TIME_WAIT)
+ get_timewait4_sock(v, seq, st->num, &len);
+ else
+ get_tcp4_sock(v, seq, st->num, &len);
break;
case TCP_SEQ_STATE_OPENREQ:
get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid, &len);
break;
- case TCP_SEQ_STATE_TIME_WAIT:
- get_timewait4_sock(v, seq, st->num, &len);
- break;
}
seq_printf(seq, "%*s\n", TMPSZ - 1 - len, "");
out:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_hash != hash)
continue;
- if (likely(INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
- if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
- goto begintw;
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ if (!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))
+ continue;
+ } else {
+ if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+ continue;
+ }
+ if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
+ goto out;
+
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
+ ports, dif))) {
+ sock_gen_put(sk);
+ goto begin;
+ }
+ } else {
if (unlikely(!INET6_MATCH(sk, net, saddr, daddr,
ports, dif))) {
sock_put(sk);
goto begin;
}
- goto out;
+ goto found;
}
}
if (get_nulls_value(node) != slot)
goto begin;
-
-begintw:
- /* Must check for a TIME_WAIT'er before going to listener hash. */
- sk_nulls_for_each_rcu(sk, node, &head->twchain) {
- if (sk->sk_hash != hash)
- continue;
- if (likely(INET6_TW_MATCH(sk, net, saddr, daddr,
- ports, dif))) {
- if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
- sk = NULL;
- goto out;
- }
- if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
- ports, dif))) {
- inet_twsk_put(inet_twsk(sk));
- goto begintw;
- }
- goto out;
- }
- }
- if (get_nulls_value(node) != slot)
- goto begintw;
- sk = NULL;
out:
+ sk = NULL;
+found:
rcu_read_unlock();
return sk;
}
spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_nulls_node *node;
- struct inet_timewait_sock *tw;
+ struct inet_timewait_sock *tw = NULL;
int twrefcnt = 0;
spin_lock(lock);
- /* Check TIME-WAIT sockets first. */
- sk_nulls_for_each(sk2, node, &head->twchain) {
+ sk_nulls_for_each(sk2, node, &head->chain) {
if (sk2->sk_hash != hash)
continue;
- if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
- ports, dif))) {
- tw = inet_twsk(sk2);
- if (twsk_unique(sk, sk2, twp))
- goto unique;
- else
- goto not_unique;
+ if (sk2->sk_state == TCP_TIME_WAIT) {
+ if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
+ ports, dif))) {
+ tw = inet_twsk(sk2);
+ if (twsk_unique(sk, sk2, twp))
+ goto unique;
+ else
+ goto not_unique;
+ }
}
- }
- tw = NULL;
-
- /* And established part... */
- sk_nulls_for_each(sk2, node, &head->chain) {
- if (sk2->sk_hash != hash)
- continue;
if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif)))
goto not_unique;
}
static int tcp6_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st;
+ struct sock *sk = v;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
case TCP_SEQ_STATE_ESTABLISHED:
- get_tcp6_sock(seq, v, st->num);
+ if (sk->sk_state == TCP_TIME_WAIT)
+ get_timewait6_sock(seq, v, st->num);
+ else
+ get_tcp6_sock(seq, v, st->num);
break;
case TCP_SEQ_STATE_OPENREQ:
get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
break;
- case TCP_SEQ_STATE_TIME_WAIT:
- get_timewait6_sock(seq, v, st->num);
- break;
}
out:
return 0;
projects / ~andy / linux / commitdiff