summaryrefslogtreecommitdiff
path: root/net/ipv4/inet_hashtables.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/inet_hashtables.c')
-rw-r--r--net/ipv4/inet_hashtables.c125
1 files changed, 62 insertions, 63 deletions
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index a532f749e477..93e9193df544 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -76,7 +76,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
- INIT_HLIST_HEAD(&tb->owners);
+ INIT_HLIST_HEAD(&tb->bhash2);
hlist_add_head(&tb->node, &head->chain);
}
return tb;
@@ -87,7 +87,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
*/
void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb)
{
- if (hlist_empty(&tb->owners)) {
+ if (hlist_empty(&tb->bhash2)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
@@ -100,47 +100,52 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net
tb->l3mdev == l3mdev;
}
-static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
+static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
struct net *net,
struct inet_bind_hashbucket *head,
- unsigned short port, int l3mdev,
+ struct inet_bind_bucket *tb,
const struct sock *sk)
{
- write_pnet(&tb->ib_net, net);
- tb->l3mdev = l3mdev;
- tb->port = port;
+ write_pnet(&tb2->ib_net, net);
+ tb2->l3mdev = tb->l3mdev;
+ tb2->port = tb->port;
#if IS_ENABLED(CONFIG_IPV6)
- tb->family = sk->sk_family;
- if (sk->sk_family == AF_INET6)
- tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
- else
+ BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED));
+ if (sk->sk_family == AF_INET6) {
+ tb2->addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
+ tb2->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+ } else {
+ tb2->addr_type = IPV6_ADDR_MAPPED;
+ ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb2->v6_rcv_saddr);
+ }
+#else
+ tb2->rcv_saddr = sk->sk_rcv_saddr;
#endif
- tb->rcv_saddr = sk->sk_rcv_saddr;
- INIT_HLIST_HEAD(&tb->owners);
- INIT_HLIST_HEAD(&tb->deathrow);
- hlist_add_head(&tb->node, &head->chain);
+ INIT_HLIST_HEAD(&tb2->owners);
+ hlist_add_head(&tb2->node, &head->chain);
+ hlist_add_head(&tb2->bhash_node, &tb->bhash2);
}
struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
- unsigned short port,
- int l3mdev,
+ struct inet_bind_bucket *tb,
const struct sock *sk)
{
- struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
+ struct inet_bind2_bucket *tb2 = kmem_cache_alloc(cachep, GFP_ATOMIC);
- if (tb)
- inet_bind2_bucket_init(tb, net, head, port, l3mdev, sk);
+ if (tb2)
+ inet_bind2_bucket_init(tb2, net, head, tb, sk);
- return tb;
+ return tb2;
}
/* Caller must hold hashbucket lock for this tb with local BH disabled */
void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
{
- if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
+ if (hlist_empty(&tb->owners)) {
__hlist_del(&tb->node);
+ __hlist_del(&tb->bhash_node);
kmem_cache_free(cachep, tb);
}
}
@@ -149,18 +154,11 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb2->family) {
- if (sk->sk_family == AF_INET)
- return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) &&
- tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
-
- return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
- sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr;
- }
-
if (sk->sk_family == AF_INET6)
- return ipv6_addr_equal(&tb2->v6_rcv_saddr,
- &sk->sk_v6_rcv_saddr);
+ return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
+
+ if (tb2->addr_type != IPV6_ADDR_MAPPED)
+ return false;
#endif
return tb2->rcv_saddr == sk->sk_rcv_saddr;
}
@@ -169,10 +167,9 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
struct inet_bind2_bucket *tb2, unsigned short port)
{
inet_sk(sk)->inet_num = port;
- sk_add_bind_node(sk, &tb->owners);
inet_csk(sk)->icsk_bind_hash = tb;
- sk_add_bind2_node(sk, &tb2->owners);
inet_csk(sk)->icsk_bind2_hash = tb2;
+ sk_add_bind_node(sk, &tb2->owners);
}
/*
@@ -192,21 +189,20 @@ static void __inet_put_port(struct sock *sk)
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
- __sk_del_bind_node(sk);
inet_csk(sk)->icsk_bind_hash = NULL;
inet_sk(sk)->inet_num = 0;
- inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
spin_lock(&head2->lock);
if (inet_csk(sk)->icsk_bind2_hash) {
struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash;
- __sk_del_bind2_node(sk);
+ __sk_del_bind_node(sk);
inet_csk(sk)->icsk_bind2_hash = NULL;
inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
}
spin_unlock(&head2->lock);
+ inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
spin_unlock(&head->lock);
}
@@ -275,8 +271,7 @@ bhash2_find:
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child);
if (!tb2) {
tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep,
- net, head2, port,
- l3mdev, child);
+ net, head2, tb, child);
if (!tb2)
goto error;
}
@@ -836,16 +831,15 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const
return false;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb->family) {
- if (sk->sk_family == AF_INET)
- return ipv6_addr_any(&tb->v6_rcv_saddr) ||
- ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr);
+ if (tb->addr_type == IPV6_ADDR_ANY)
+ return true;
+ if (tb->addr_type != IPV6_ADDR_MAPPED)
return false;
- }
- if (sk->sk_family == AF_INET6)
- return ipv6_addr_any(&tb->v6_rcv_saddr);
+ if (sk->sk_family == AF_INET6 &&
+ !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ return false;
#endif
return tb->rcv_saddr == 0;
}
@@ -942,7 +936,7 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
spin_lock_bh(&head->lock);
spin_lock(&head2->lock);
- __sk_del_bind2_node(sk);
+ __sk_del_bind_node(sk);
inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
spin_unlock(&head2->lock);
@@ -957,10 +951,10 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
if (!tb2) {
tb2 = new_tb2;
- inet_bind2_bucket_init(tb2, net, head2, port, l3mdev, sk);
+ inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk);
}
- sk_add_bind2_node(sk, &tb2->owners);
inet_csk(sk)->icsk_bind2_hash = tb2;
+ sk_add_bind_node(sk, &tb2->owners);
spin_unlock(&head2->lock);
spin_unlock_bh(&head->lock);
@@ -1012,7 +1006,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
bool tb_created = false;
u32 remaining, offset;
int ret, i, low, high;
- int l3mdev;
+ bool local_ports;
+ int step, l3mdev;
u32 index;
if (port) {
@@ -1024,10 +1019,12 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
l3mdev = inet_sk_bound_l3mdev(sk);
- inet_sk_get_local_port_range(sk, &low, &high);
+ local_ports = inet_sk_get_local_port_range(sk, &low, &high);
+ step = local_ports ? 1 : 2;
+
high++; /* [32768, 60999] -> [32768, 61000[ */
remaining = high - low;
- if (likely(remaining > 1))
+ if (!local_ports && remaining > 1)
remaining &= ~1U;
get_random_sleepable_once(table_perturb,
@@ -1040,10 +1037,11 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
/* In first pass we try ports of @low parity.
* inet_csk_get_port() does the opposite choice.
*/
- offset &= ~1U;
+ if (!local_ports)
+ offset &= ~1U;
other_parity_scan:
port = low + offset;
- for (i = 0; i < remaining; i += 2, port += 2) {
+ for (i = 0; i < remaining; i += step, port += step) {
if (unlikely(port >= high))
port -= remaining;
if (inet_is_local_reserved_port(net, port))
@@ -1060,7 +1058,7 @@ other_parity_scan:
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
- WARN_ON(hlist_empty(&tb->owners));
+ WARN_ON(hlist_empty(&tb->bhash2));
if (!check_established(death_row, sk,
port, &tw))
goto ok;
@@ -1083,10 +1081,11 @@ next_port:
cond_resched();
}
- offset++;
- if ((offset & 1) && remaining > 1)
- goto other_parity_scan;
-
+ if (!local_ports) {
+ offset++;
+ if ((offset & 1) && remaining > 1)
+ goto other_parity_scan;
+ }
return -EADDRNOTAVAIL;
ok:
@@ -1099,7 +1098,7 @@ ok:
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
if (!tb2) {
tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net,
- head2, port, l3mdev, sk);
+ head2, tb, sk);
if (!tb2)
goto error;
}
@@ -1109,8 +1108,8 @@ ok:
* on low contention the randomness is maximal and on high contention
* it may be inexistent.
*/
- i = max_t(int, i, get_random_u32_below(8) * 2);
- WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
+ i = max_t(int, i, get_random_u32_below(8) * step);
+ WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + step);
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, tb2, port);