udp: introduce struct udp_table and multiple spinlocks

UDP sockets are hashed in a 128 slots hash table.

This hash table is protected by *one* rwlock.

This rwlock is readlocked each time an incoming UDP message is handled.

This rwlock is writelocked each time a socket must be inserted in
hash table (bind time), or deleted from this table (close time)

This is not scalable on SMP machines :

1) Even in read mode, lock() and unlock() are atomic operations and
 must dirty a contended cache line, shared by all cpus.

2) A writer might be starved if many readers are 'in flight'. This can
 happen on a machine with some NIC receiving many UDP messages. User
 process can be delayed a long time at socket creation/dismantle time.

This patch prepares RCU migration, by introducing 'struct udp_table
and struct udp_hslot', and using one spinlock per chain, to reduce
contention on central rwlock.

Introducing one spinlock per chain reduces latencies, for port
randomization on heavily loaded UDP servers. This also speedup
bindings to specific ports.

udp_lib_unhash() was uninlined, becoming to big.

Some cleanups were done to ease review of following patch
(RCUification of UDP Unicast lookups)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 68 insertions, 56 deletions

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e51da8c092fa..ccee7244ca0f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -54,62 +54,73 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
         return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal);
 }
 
+static inline int compute_score(struct sock *sk, struct net *net,
+                                unsigned short hnum,
+                                struct in6_addr *saddr, __be16 sport,
+                                struct in6_addr *daddr, __be16 dport,
+                                int dif)
+{
+        int score = -1;
+
+        if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
+                        sk->sk_family == PF_INET6) {
+                struct ipv6_pinfo *np = inet6_sk(sk);
+                struct inet_sock *inet = inet_sk(sk);
+
+                score = 0;
+                if (inet->dport) {
+                        if (inet->dport != sport)
+                                return -1;
+                        score++;
+                }
+                if (!ipv6_addr_any(&np->rcv_saddr)) {
+                        if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+                                return -1;
+                        score++;
+                }
+                if (!ipv6_addr_any(&np->daddr)) {
+                        if (!ipv6_addr_equal(&np->daddr, saddr))
+                                return -1;
+                        score++;
+                }
+                if (sk->sk_bound_dev_if) {
+                        if (sk->sk_bound_dev_if != dif)
+                                return -1;
+                        score++;
+                }
+        }
+        return score;
+}
+
 static struct sock *__udp6_lib_lookup(struct net *net,
                                       struct in6_addr *saddr, __be16 sport,
                                       struct in6_addr *daddr, __be16 dport,
-                                      int dif, struct hlist_head udptable[])
+                                      int dif, struct udp_table *udptable)
 {
         struct sock *sk, *result = NULL;
         struct hlist_node *node;
         unsigned short hnum = ntohs(dport);
-        int badness = -1;
-
-        read_lock(&udp_hash_lock);
-        sk_for_each(sk, node, &udptable[udp_hashfn(net, hnum)]) {
-                struct inet_sock *inet = inet_sk(sk);
-
-                if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
-                                sk->sk_family == PF_INET6) {
-                        struct ipv6_pinfo *np = inet6_sk(sk);
-                        int score = 0;
-                        if (inet->dport) {
-                                if (inet->dport != sport)
-                                        continue;
-                                score++;
-                        }
-                        if (!ipv6_addr_any(&np->rcv_saddr)) {
-                                if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
-                                        continue;
-                                score++;
-                        }
-                        if (!ipv6_addr_any(&np->daddr)) {
-                                if (!ipv6_addr_equal(&np->daddr, saddr))
-                                        continue;
-                                score++;
-                        }
-                        if (sk->sk_bound_dev_if) {
-                                if (sk->sk_bound_dev_if != dif)
-                                        continue;
-                                score++;
-                        }
-                        if (score == 4) {
-                                result = sk;
-                                break;
-                        } else if (score > badness) {
-                                result = sk;
-                                badness = score;
-                        }
+        unsigned int hash = udp_hashfn(net, hnum);
+        struct udp_hslot *hslot = &udptable->hash[hash];
+        int score, badness = -1;
+
+        spin_lock(&hslot->lock);
+        sk_for_each(sk, node, &hslot->head) {
+                score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
+                if (score > badness) {
+                        result = sk;
+                        badness = score;
                 }
         }
         if (result)
                 sock_hold(result);
-        read_unlock(&udp_hash_lock);
+        spin_unlock(&hslot->lock);
         return result;
 }
 
 static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
                                           __be16 sport, __be16 dport,
-                                          struct hlist_head udptable[])
+                                          struct udp_table *udptable)
 {
         struct sock *sk;
         struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -239,7 +250,7 @@ csum_copy_err:
 
 void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
                     int type, int code, int offset, __be32 info,
-                    struct hlist_head udptable[]                    )
+                    struct udp_table *udptable)
 {
         struct ipv6_pinfo *np;
         struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
@@ -275,7 +286,7 @@ static __inline__ void udpv6_err(struct sk_buff *skb,
                                  struct inet6_skb_parm *opt, int type,
                                  int code, int offset, __be32 info     )
 {
-        __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash);
+        __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
 }
 
 int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
@@ -374,14 +385,15 @@ static struct sock *udp_v6_mcast_next(struct sock *sk,
  */
 static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
                 struct in6_addr *saddr, struct in6_addr *daddr,
-                struct hlist_head udptable[])
+                struct udp_table *udptable)
 {
         struct sock *sk, *sk2;
         const struct udphdr *uh = udp_hdr(skb);
+        struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))];
         int dif;
 
-        read_lock(&udp_hash_lock);
-        sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]);
+        spin_lock(&hslot->lock);
+        sk = sk_head(&hslot->head);
         dif = inet6_iif(skb);
         sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
         if (!sk) {
@@ -409,7 +421,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
                 sk_add_backlog(sk, skb);
         bh_unlock_sock(sk);
 out:
-        read_unlock(&udp_hash_lock);
+        spin_unlock(&hslot->lock);
         return 0;
 }
 
@@ -447,7 +459,7 @@ static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
         return 0;
 }
 
-int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
+int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
                    int proto)
 {
         struct sock *sk;
@@ -544,7 +556,7 @@ discard:
 
 static __inline__ int udpv6_rcv(struct sk_buff *skb)
 {
-        return __udp6_lib_rcv(skb, udp_hash, IPPROTO_UDP);
+        return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
 }
 
 /*
@@ -1008,7 +1020,7 @@ int udp6_seq_show(struct seq_file *seq, void *v)
 static struct udp_seq_afinfo udp6_seq_afinfo = {
         .name           = "udp6",
         .family         = AF_INET6,
-        .hashtable      = udp_hash,
+        .udp_table      = &udp_table,
         .seq_fops       = {
                 .owner  =       THIS_MODULE,
         },
@@ -1050,7 +1062,7 @@ struct proto udpv6_prot = {
         .sysctl_wmem       = &sysctl_udp_wmem_min,
         .sysctl_rmem       = &sysctl_udp_rmem_min,
         .obj_size          = sizeof(struct udp6_sock),
-        .h.udp_hash        = udp_hash,
+        .h.udp_table       = &udp_table,
 #ifdef CONFIG_COMPAT
         .compat_setsockopt = compat_udpv6_setsockopt,
         .compat_getsockopt = compat_udpv6_getsockopt,
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 92dd7da766d8..23779208c334 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -7,9 +7,9 @@
 #include <net/inet_common.h>
 #include <net/transp_v6.h>
 
-extern int      __udp6_lib_rcv(struct sk_buff *, struct hlist_head [], int );
+extern int      __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int );
 extern void     __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *,
-                               int , int , int , __be32 , struct hlist_head []);
+                               int , int , int , __be32 , struct udp_table *);
 
 extern int      udp_v6_get_port(struct sock *sk, unsigned short snum);
 
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 3cd1a1ac3d6c..f1e892a99e05 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -15,14 +15,14 @@
 
 static int udplitev6_rcv(struct sk_buff *skb)
 {
-        return __udp6_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE);
+        return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
 }
 
 static void udplitev6_err(struct sk_buff *skb,
                           struct inet6_skb_parm *opt,
                           int type, int code, int offset, __be32 info)
 {
-        __udp6_lib_err(skb, opt, type, code, offset, info, udplite_hash);
+        __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table);
 }
 
 static struct inet6_protocol udplitev6_protocol = {
@@ -49,7 +49,7 @@ struct proto udplitev6_prot = {
         .unhash            = udp_lib_unhash,
         .get_port          = udp_v6_get_port,
         .obj_size          = sizeof(struct udp6_sock),
-        .h.udp_hash        = udplite_hash,
+        .h.udp_table       = &udplite_table,
 #ifdef CONFIG_COMPAT
         .compat_setsockopt = compat_udpv6_setsockopt,
         .compat_getsockopt = compat_udpv6_getsockopt,
@@ -95,7 +95,7 @@ void udplitev6_exit(void)
 static struct udp_seq_afinfo udplite6_seq_afinfo = {
         .name           = "udplite6",
         .family         = AF_INET6,
-        .hashtable      = udplite_hash,
+        .udp_table      = &udplite_table,
         .seq_fops       = {
                 .owner  =       THIS_MODULE,
         },