summaryrefslogtreecommitdiff
path: root/net/ipv4/udp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/udp.c')
-rw-r--r--net/ipv4/udp.c484
1 files changed, 381 insertions, 103 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0fa9f70e4b19..1f9534846ca9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -106,7 +106,7 @@
#include <net/xfrm.h>
#include "udp_impl.h"
-struct udp_table udp_table;
+struct udp_table udp_table __read_mostly;
EXPORT_SYMBOL(udp_table);
int sysctl_udp_mem[3] __read_mostly;
@@ -121,28 +121,30 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min);
atomic_t udp_memory_allocated;
EXPORT_SYMBOL(udp_memory_allocated);
-#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE)
+#define MAX_UDP_PORTS 65536
+#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN)
static int udp_lib_lport_inuse(struct net *net, __u16 num,
const struct udp_hslot *hslot,
unsigned long *bitmap,
struct sock *sk,
int (*saddr_comp)(const struct sock *sk1,
- const struct sock *sk2))
+ const struct sock *sk2),
+ unsigned int log)
{
struct sock *sk2;
struct hlist_nulls_node *node;
sk_nulls_for_each(sk2, node, &hslot->head)
- if (net_eq(sock_net(sk2), net) &&
- sk2 != sk &&
- (bitmap || sk2->sk_hash == num) &&
- (!sk2->sk_reuse || !sk->sk_reuse) &&
- (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
- || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ if (net_eq(sock_net(sk2), net) &&
+ sk2 != sk &&
+ (bitmap || udp_sk(sk2)->udp_port_hash == num) &&
+ (!sk2->sk_reuse || !sk->sk_reuse) &&
+ (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
+ sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
(*saddr_comp)(sk, sk2)) {
if (bitmap)
- __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE,
+ __set_bit(udp_sk(sk2)->udp_port_hash >> log,
bitmap);
else
return 1;
@@ -150,18 +152,51 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
return 0;
}
+/*
+ * Note: we still hold spinlock of primary hash chain, so no other writer
+ * can insert/delete a socket with local_port == num
+ */
+static int udp_lib_lport_inuse2(struct net *net, __u16 num,
+ struct udp_hslot *hslot2,
+ struct sock *sk,
+ int (*saddr_comp)(const struct sock *sk1,
+ const struct sock *sk2))
+{
+ struct sock *sk2;
+ struct hlist_nulls_node *node;
+ int res = 0;
+
+ spin_lock(&hslot2->lock);
+ udp_portaddr_for_each_entry(sk2, node, &hslot2->head)
+ if (net_eq(sock_net(sk2), net) &&
+ sk2 != sk &&
+ (udp_sk(sk2)->udp_port_hash == num) &&
+ (!sk2->sk_reuse || !sk->sk_reuse) &&
+ (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
+ sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ (*saddr_comp)(sk, sk2)) {
+ res = 1;
+ break;
+ }
+ spin_unlock(&hslot2->lock);
+ return res;
+}
+
/**
* udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6
*
* @sk: socket struct in question
* @snum: port number to look up
* @saddr_comp: AF-dependent comparison of bound local IP addresses
+ * @hash2_nulladdr: AF-dependant hash value in secondary hash chains,
+ * with NULL address
*/
int udp_lib_get_port(struct sock *sk, unsigned short snum,
int (*saddr_comp)(const struct sock *sk1,
- const struct sock *sk2))
+ const struct sock *sk2),
+ unsigned int hash2_nulladdr)
{
- struct udp_hslot *hslot;
+ struct udp_hslot *hslot, *hslot2;
struct udp_table *udptable = sk->sk_prot->h.udp_table;
int error = 1;
struct net *net = sock_net(sk);
@@ -180,13 +215,15 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
/*
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
- rand = (rand | 1) * UDP_HTABLE_SIZE;
- for (last = first + UDP_HTABLE_SIZE; first != last; first++) {
- hslot = &udptable->hash[udp_hashfn(net, first)];
+ rand = (rand | 1) * (udptable->mask + 1);
+ for (last = first + udptable->mask + 1;
+ first != last;
+ first++) {
+ hslot = udp_hashslot(udptable, net, first);
bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
- saddr_comp);
+ saddr_comp, udptable->log);
snum = first;
/*
@@ -196,7 +233,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
*/
do {
if (low <= snum && snum <= high &&
- !test_bit(snum / UDP_HTABLE_SIZE, bitmap))
+ !test_bit(snum >> udptable->log, bitmap))
goto found;
snum += rand;
} while (snum != first);
@@ -204,17 +241,51 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
}
goto fail;
} else {
- hslot = &udptable->hash[udp_hashfn(net, snum)];
+ hslot = udp_hashslot(udptable, net, snum);
spin_lock_bh(&hslot->lock);
- if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp))
+ if (hslot->count > 10) {
+ int exist;
+ unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
+
+ slot2 &= udptable->mask;
+ hash2_nulladdr &= udptable->mask;
+
+ hslot2 = udp_hashslot2(udptable, slot2);
+ if (hslot->count < hslot2->count)
+ goto scan_primary_hash;
+
+ exist = udp_lib_lport_inuse2(net, snum, hslot2,
+ sk, saddr_comp);
+ if (!exist && (hash2_nulladdr != slot2)) {
+ hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
+ exist = udp_lib_lport_inuse2(net, snum, hslot2,
+ sk, saddr_comp);
+ }
+ if (exist)
+ goto fail_unlock;
+ else
+ goto found;
+ }
+scan_primary_hash:
+ if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk,
+ saddr_comp, 0))
goto fail_unlock;
}
found:
- inet_sk(sk)->num = snum;
- sk->sk_hash = snum;
+ inet_sk(sk)->inet_num = snum;
+ udp_sk(sk)->udp_port_hash = snum;
+ udp_sk(sk)->udp_portaddr_hash ^= snum;
if (sk_unhashed(sk)) {
sk_nulls_add_node_rcu(sk, &hslot->head);
+ hslot->count++;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+
+ hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
+ spin_lock(&hslot2->lock);
+ hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+ &hslot2->head);
+ hslot2->count++;
+ spin_unlock(&hslot2->lock);
}
error = 0;
fail_unlock:
@@ -229,13 +300,26 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
return (!ipv6_only_sock(sk2) &&
- (!inet1->rcv_saddr || !inet2->rcv_saddr ||
- inet1->rcv_saddr == inet2->rcv_saddr));
+ (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr ||
+ inet1->inet_rcv_saddr == inet2->inet_rcv_saddr));
+}
+
+static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr,
+ unsigned int port)
+{
+ return jhash_1word(saddr, net_hash_mix(net)) ^ port;
}
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
- return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal);
+ unsigned int hash2_nulladdr =
+ udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum);
+ unsigned int hash2_partial =
+ udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
+
+ /* precompute partial secondary hash */
+ udp_sk(sk)->udp_portaddr_hash = hash2_partial;
+ return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr);
}
static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
@@ -244,23 +328,61 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
{
int score = -1;
- if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
+ if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
!ipv6_only_sock(sk)) {
struct inet_sock *inet = inet_sk(sk);
score = (sk->sk_family == PF_INET ? 1 : 0);
- if (inet->rcv_saddr) {
- if (inet->rcv_saddr != daddr)
+ if (inet->inet_rcv_saddr) {
+ if (inet->inet_rcv_saddr != daddr)
+ return -1;
+ score += 2;
+ }
+ if (inet->inet_daddr) {
+ if (inet->inet_daddr != saddr)
+ return -1;
+ score += 2;
+ }
+ if (inet->inet_dport) {
+ if (inet->inet_dport != sport)
+ return -1;
+ score += 2;
+ }
+ if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if != dif)
return -1;
score += 2;
}
- if (inet->daddr) {
- if (inet->daddr != saddr)
+ }
+ return score;
+}
+
+/*
+ * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num)
+ */
+#define SCORE2_MAX (1 + 2 + 2 + 2)
+static inline int compute_score2(struct sock *sk, struct net *net,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned int hnum, int dif)
+{
+ int score = -1;
+
+ if (net_eq(sock_net(sk), net) && !ipv6_only_sock(sk)) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (inet->inet_rcv_saddr != daddr)
+ return -1;
+ if (inet->inet_num != hnum)
+ return -1;
+
+ score = (sk->sk_family == PF_INET ? 1 : 0);
+ if (inet->inet_daddr) {
+ if (inet->inet_daddr != saddr)
return -1;
score += 2;
}
- if (inet->dport) {
- if (inet->dport != sport)
+ if (inet->inet_dport) {
+ if (inet->inet_dport != sport)
return -1;
score += 2;
}
@@ -273,6 +395,51 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
return score;
}
+
+/* called with read_rcu_lock() */
+static struct sock *udp4_lib_lookup2(struct net *net,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned int hnum, int dif,
+ struct udp_hslot *hslot2, unsigned int slot2)
+{
+ struct sock *sk, *result;
+ struct hlist_nulls_node *node;
+ int score, badness;
+
+begin:
+ result = NULL;
+ badness = -1;
+ udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+ score = compute_score2(sk, net, saddr, sport,
+ daddr, hnum, dif);
+ if (score > badness) {
+ result = sk;
+ badness = score;
+ if (score == SCORE2_MAX)
+ goto exact_match;
+ }
+ }
+ /*
+ * 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) != slot2)
+ goto begin;
+
+ if (result) {
+exact_match:
+ if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
+ result = NULL;
+ else if (unlikely(compute_score2(result, net, saddr, sport,
+ daddr, hnum, dif) < badness)) {
+ sock_put(result);
+ goto begin;
+ }
+ }
+ return result;
+}
+
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
@@ -283,11 +450,35 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
struct sock *sk, *result;
struct hlist_nulls_node *node;
unsigned short hnum = ntohs(dport);
- unsigned int hash = udp_hashfn(net, hnum);
- struct udp_hslot *hslot = &udptable->hash[hash];
+ unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
+ struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
int score, badness;
rcu_read_lock();
+ if (hslot->count > 10) {
+ hash2 = udp4_portaddr_hash(net, daddr, hnum);
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
+ if (hslot->count < hslot2->count)
+ goto begin;
+
+ result = udp4_lib_lookup2(net, saddr, sport,
+ daddr, hnum, dif,
+ hslot2, slot2);
+ if (!result) {
+ hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum);
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
+ if (hslot->count < hslot2->count)
+ goto begin;
+
+ result = udp4_lib_lookup2(net, INADDR_ANY, sport,
+ daddr, hnum, dif,
+ hslot2, slot2);
+ }
+ rcu_read_unlock();
+ return result;
+ }
begin:
result = NULL;
badness = -1;
@@ -304,7 +495,7 @@ begin:
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
- if (get_nulls_value(node) != hash)
+ if (get_nulls_value(node) != slot)
goto begin;
if (result) {
@@ -354,12 +545,13 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
sk_nulls_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
- if (!net_eq(sock_net(s), net) ||
- s->sk_hash != hnum ||
- (inet->daddr && inet->daddr != rmt_addr) ||
- (inet->dport != rmt_port && inet->dport) ||
- (inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
- ipv6_only_sock(s) ||
+ if (!net_eq(sock_net(s), net) ||
+ udp_sk(s)->udp_port_hash != hnum ||
+ (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
+ (inet->inet_dport != rmt_port && inet->inet_dport) ||
+ (inet->inet_rcv_saddr &&
+ inet->inet_rcv_saddr != loc_addr) ||
+ ipv6_only_sock(s) ||
(s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
continue;
if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
@@ -642,14 +834,14 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
- daddr = inet->daddr;
- dport = inet->dport;
+ daddr = inet->inet_daddr;
+ dport = inet->inet_dport;
/* Open fast path for connected socket.
Route will not be used, if at least one option is set.
*/
connected = 1;
}
- ipc.addr = inet->saddr;
+ ipc.addr = inet->inet_saddr;
ipc.oif = sk->sk_bound_dev_if;
err = sock_tx_timestamp(msg, sk, &ipc.shtx);
@@ -704,7 +896,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
.proto = sk->sk_protocol,
.flags = inet_sk_flowi_flags(sk),
.uli_u = { .ports =
- { .sport = inet->sport,
+ { .sport = inet->inet_sport,
.dport = dport } } };
struct net *net = sock_net(sk);
@@ -748,7 +940,7 @@ back_from_confirm:
inet->cork.fl.fl4_dst = daddr;
inet->cork.fl.fl_ip_dport = dport;
inet->cork.fl.fl4_src = saddr;
- inet->cork.fl.fl_ip_sport = inet->sport;
+ inet->cork.fl.fl_ip_sport = inet->inet_sport;
up->pending = AF_INET;
do_append_data:
@@ -862,6 +1054,7 @@ static unsigned int first_packet_length(struct sock *sk)
udp_lib_checksum_complete(skb)) {
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
IS_UDPLITE(sk));
+ atomic_inc(&sk->sk_drops);
__skb_unlink(skb, rcvq);
__skb_queue_tail(&list_kill, skb);
}
@@ -982,7 +1175,7 @@ try_again:
UDP_INC_STATS_USER(sock_net(sk),
UDP_MIB_INDATAGRAMS, is_udplite);
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
/* Copy the address. */
if (sin) {
@@ -1023,15 +1216,15 @@ int udp_disconnect(struct sock *sk, int flags)
*/
sk->sk_state = TCP_CLOSE;
- inet->daddr = 0;
- inet->dport = 0;
+ inet->inet_daddr = 0;
+ inet->inet_dport = 0;
sk->sk_bound_dev_if = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
sk->sk_prot->unhash(sk);
- inet->sport = 0;
+ inet->inet_sport = 0;
}
sk_dst_reset(sk);
return 0;
@@ -1042,13 +1235,22 @@ void udp_lib_unhash(struct sock *sk)
{
if (sk_hashed(sk)) {
struct udp_table *udptable = sk->sk_prot->h.udp_table;
- unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash);
- struct udp_hslot *hslot = &udptable->hash[hash];
+ struct udp_hslot *hslot, *hslot2;
+
+ hslot = udp_hashslot(udptable, sock_net(sk),
+ udp_sk(sk)->udp_port_hash);
+ hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
spin_lock_bh(&hslot->lock);
if (sk_nulls_del_node_init_rcu(sk)) {
- inet_sk(sk)->num = 0;
+ hslot->count--;
+ inet_sk(sk)->inet_num = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+
+ spin_lock(&hslot2->lock);
+ hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+ hslot2->count--;
+ spin_unlock(&hslot2->lock);
}
spin_unlock_bh(&hslot->lock);
}
@@ -1057,25 +1259,22 @@ EXPORT_SYMBOL(udp_lib_unhash);
static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
- int is_udplite = IS_UDPLITE(sk);
- int rc;
+ int rc = sock_queue_rcv_skb(sk, skb);
+
+ if (rc < 0) {
+ int is_udplite = IS_UDPLITE(sk);
- if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
- if (rc == -ENOMEM) {
+ if (rc == -ENOMEM)
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
- atomic_inc(&sk->sk_drops);
- }
- goto drop;
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
+ return -1;
}
return 0;
-drop:
- UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
- kfree_skb(skb);
- return -1;
}
/* returns:
@@ -1182,53 +1381,88 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
drop:
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ atomic_inc(&sk->sk_drops);
kfree_skb(skb);
return -1;
}
+
+static void flush_stack(struct sock **stack, unsigned int count,
+ struct sk_buff *skb, unsigned int final)
+{
+ unsigned int i;
+ struct sk_buff *skb1 = NULL;
+ struct sock *sk;
+
+ for (i = 0; i < count; i++) {
+ sk = stack[i];
+ if (likely(skb1 == NULL))
+ skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC);
+
+ if (!skb1) {
+ atomic_inc(&sk->sk_drops);
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+ IS_UDPLITE(sk));
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
+ IS_UDPLITE(sk));
+ }
+
+ if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0)
+ skb1 = NULL;
+ }
+ if (unlikely(skb1))
+ kfree_skb(skb1);
+}
+
/*
* Multicasts and broadcasts go to each listener.
*
- * Note: called only from the BH handler context,
- * so we don't need to lock the hashes.
+ * Note: called only from the BH handler context.
*/
static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct udphdr *uh,
__be32 saddr, __be32 daddr,
struct udp_table *udptable)
{
- struct sock *sk;
- struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))];
+ struct sock *sk, *stack[256 / sizeof(struct sock *)];
+ struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest));
int dif;
+ unsigned int i, count = 0;
spin_lock(&hslot->lock);
sk = sk_nulls_head(&hslot->head);
dif = skb->dev->ifindex;
sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
- if (sk) {
- struct sock *sknext = NULL;
-
- do {
- struct sk_buff *skb1 = skb;
-
- sknext = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest,
- daddr, uh->source, saddr,
- dif);
- if (sknext)
- skb1 = skb_clone(skb, GFP_ATOMIC);
-
- if (skb1) {
- int ret = udp_queue_rcv_skb(sk, skb1);
- if (ret > 0)
- /* we should probably re-process instead
- * of dropping packets here. */
- kfree_skb(skb1);
- }
- sk = sknext;
- } while (sknext);
- } else
- consume_skb(skb);
+ while (sk) {
+ stack[count++] = sk;
+ sk = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest,
+ daddr, uh->source, saddr, dif);
+ if (unlikely(count == ARRAY_SIZE(stack))) {
+ if (!sk)
+ break;
+ flush_stack(stack, count, skb, ~0);
+ count = 0;
+ }
+ }
+ /*
+ * before releasing chain lock, we must take a reference on sockets
+ */
+ for (i = 0; i < count; i++)
+ sock_hold(stack[i]);
+
spin_unlock(&hslot->lock);
+
+ /*
+ * do the slow work with no lock held
+ */
+ if (count) {
+ flush_stack(stack, count, skb, count - 1);
+
+ for (i = 0; i < count; i++)
+ sock_put(stack[i]);
+ } else {
+ kfree_skb(skb);
+ }
return 0;
}
@@ -1620,9 +1854,14 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
- for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
+ for (state->bucket = start; state->bucket <= state->udp_table->mask;
+ ++state->bucket) {
struct hlist_nulls_node *node;
struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
+
+ if (hlist_nulls_empty(&hslot->head))
+ continue;
+
spin_lock_bh(&hslot->lock);
sk_nulls_for_each(sk, node, &hslot->head) {
if (!net_eq(sock_net(sk), net))
@@ -1647,7 +1886,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
} while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family));
if (!sk) {
- if (state->bucket < UDP_HTABLE_SIZE)
+ if (state->bucket <= state->udp_table->mask)
spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
return udp_get_first(seq, state->bucket + 1);
}
@@ -1667,7 +1906,7 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
struct udp_iter_state *state = seq->private;
- state->bucket = UDP_HTABLE_SIZE;
+ state->bucket = MAX_UDP_PORTS;
return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
@@ -1689,7 +1928,7 @@ static void udp_seq_stop(struct seq_file *seq, void *v)
{
struct udp_iter_state *state = seq->private;
- if (state->bucket < UDP_HTABLE_SIZE)
+ if (state->bucket <= state->udp_table->mask)
spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
}
@@ -1744,12 +1983,12 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
int bucket, int *len)
{
struct inet_sock *inet = inet_sk(sp);
- __be32 dest = inet->daddr;
- __be32 src = inet->rcv_saddr;
- __u16 destp = ntohs(inet->dport);
- __u16 srcp = ntohs(inet->sport);
+ __be32 dest = inet->inet_daddr;
+ __be32 src = inet->inet_rcv_saddr;
+ __u16 destp = ntohs(inet->inet_dport);
+ __u16 srcp = ntohs(inet->inet_sport);
- seq_printf(f, "%4d: %08X:%04X %08X:%04X"
+ seq_printf(f, "%5d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n",
bucket, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
@@ -1815,21 +2054,60 @@ void udp4_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
-void __init udp_table_init(struct udp_table *table)
+static __initdata unsigned long uhash_entries;
+static int __init set_uhash_entries(char *str)
{
- int i;
+ if (!str)
+ return 0;
+ uhash_entries = simple_strtoul(str, &str, 0);
+ if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN)
+ uhash_entries = UDP_HTABLE_SIZE_MIN;
+ return 1;
+}
+__setup("uhash_entries=", set_uhash_entries);
- for (i = 0; i < UDP_HTABLE_SIZE; i++) {
+void __init udp_table_init(struct udp_table *table, const char *name)
+{
+ unsigned int i;
+
+ if (!CONFIG_BASE_SMALL)
+ table->hash = alloc_large_system_hash(name,
+ 2 * sizeof(struct udp_hslot),
+ uhash_entries,
+ 21, /* one slot per 2 MB */
+ 0,
+ &table->log,
+ &table->mask,
+ 64 * 1024);
+ /*
+ * Make sure hash table has the minimum size
+ */
+ if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) {
+ table->hash = kmalloc(UDP_HTABLE_SIZE_MIN *
+ 2 * sizeof(struct udp_hslot), GFP_KERNEL);
+ if (!table->hash)
+ panic(name);
+ table->log = ilog2(UDP_HTABLE_SIZE_MIN);
+ table->mask = UDP_HTABLE_SIZE_MIN - 1;
+ }
+ table->hash2 = table->hash + (table->mask + 1);
+ for (i = 0; i <= table->mask; i++) {
INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i);
+ table->hash[i].count = 0;
spin_lock_init(&table->hash[i].lock);
}
+ for (i = 0; i <= table->mask; i++) {
+ INIT_HLIST_NULLS_HEAD(&table->hash2[i].head, i);
+ table->hash2[i].count = 0;
+ spin_lock_init(&table->hash2[i].lock);
+ }
}
void __init udp_init(void)
{
unsigned long nr_pages, limit;
- udp_table_init(&udp_table);
+ udp_table_init(&udp_table, "UDP");
/* Set the pressure threshold up by the same strategy of TCP. It is a
* fraction of global memory that is up to 1/2 at 256 MB, decreasing
* toward zero with the amount of memory, with a floor of 128 pages.