net: Use a percpu_counter for sockets_allocated

Instead of using one atomic_t per protocol, use a percpu_counter
for "sockets_allocated", to reduce cache line contention on
heavy duty network servers. 

Note : We revert commit (248969ae31e1b3276fc4399d67ce29a5d81e6fd9
net: af_unix can make unix_nr_socks visbile in /proc),
since it is not anymore used after sock_prot_inuse_add() addition

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

8 files changed, 26 insertions, 14 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index a4e840e5a053..7a081b647bf9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1071,7 +1071,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
                 newsk->sk_sleep  = NULL;
 
                 if (newsk->sk_prot->sockets_allocated)
-                        atomic_inc(newsk->sk_prot->sockets_allocated);
+                        percpu_counter_inc(newsk->sk_prot->sockets_allocated);
         }
 out:
         return newsk;
@@ -1463,8 +1463,12 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
         }
 
         if (prot->memory_pressure) {
-                if (!*prot->memory_pressure ||
-                    prot->sysctl_mem[2] > atomic_read(prot->sockets_allocated) *
+                int alloc;
+
+                if (!*prot->memory_pressure)
+                        return 1;
+                alloc = percpu_counter_read_positive(prot->sockets_allocated);
+                if (prot->sysctl_mem[2] > alloc *
                     sk_mem_pages(sk->sk_wmem_queued +
                                  atomic_read(&sk->sk_rmem_alloc) +
                                  sk->sk_forward_alloc))
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 731789bb499f..4944b47ad628 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -55,7 +55,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
         seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
                    sock_prot_inuse_get(net, &tcp_prot),
                    atomic_read(&tcp_orphan_count),
-                   tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated),
+                   tcp_death_row.tw_count,
+                   (int)percpu_counter_sum_positive(&tcp_sockets_allocated),
                    atomic_read(&tcp_memory_allocated));
         seq_printf(seq, "UDP: inuse %d mem %d\n",
                    sock_prot_inuse_get(net, &udp_prot),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 044224a341eb..e6fade9ebf62 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -290,9 +290,12 @@ EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
 atomic_t tcp_memory_allocated;  /* Current allocated memory. */
-atomic_t tcp_sockets_allocated; /* Current number of TCP sockets. */
-
 EXPORT_SYMBOL(tcp_memory_allocated);
+
+/*
+ * Current number of TCP sockets.
+ */
+struct percpu_counter tcp_sockets_allocated;
 EXPORT_SYMBOL(tcp_sockets_allocated);
 
 /*
@@ -2685,6 +2688,7 @@ void __init tcp_init(void)
 
         BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
+        percpu_counter_init(&tcp_sockets_allocated, 0);
         tcp_hashinfo.bind_bucket_cachep =
                 kmem_cache_create("tcp_bind_bucket",
                                   sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cab2458f86fd..26b9030747cc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1797,7 +1797,7 @@ static int tcp_v4_init_sock(struct sock *sk)
         sk->sk_sndbuf = sysctl_tcp_wmem[1];
         sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
-        atomic_inc(&tcp_sockets_allocated);
+        percpu_counter_inc(&tcp_sockets_allocated);
 
         return 0;
 }
@@ -1845,7 +1845,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
                 sk->sk_sndmsg_page = NULL;
         }
 
-        atomic_dec(&tcp_sockets_allocated);
+        percpu_counter_dec(&tcp_sockets_allocated);
 }
 
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f259c9671f3e..8702b06cb60a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1830,7 +1830,7 @@ static int tcp_v6_init_sock(struct sock *sk)
         sk->sk_sndbuf = sysctl_tcp_wmem[1];
         sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
-        atomic_inc(&tcp_sockets_allocated);
+        percpu_counter_inc(&tcp_sockets_allocated);
 
         return 0;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index a8ca743241ee..d5ea232c9126 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -102,6 +102,8 @@ struct sock *sctp_get_ctl_sock(void)
 /* Set up the proc fs entry for the SCTP protocol. */
 static __init int sctp_proc_init(void)
 {
+        if (percpu_counter_init(&sctp_sockets_allocated, 0))
+                goto out_nomem;
 #ifdef CONFIG_PROC_FS
         if (!proc_net_sctp) {
                 struct proc_dir_entry *ent;
@@ -110,7 +112,7 @@ static __init int sctp_proc_init(void)
                         ent->owner = THIS_MODULE;
                         proc_net_sctp = ent;
                 } else
-                        goto out_nomem;
+                        goto out_free_percpu;
         }
 
         if (sctp_snmp_proc_init())
@@ -135,6 +137,8 @@ out_snmp_proc_init:
                 proc_net_sctp = NULL;
                 remove_proc_entry("sctp", init_net.proc_net);
         }
+out_free_percpu:
+        percpu_counter_destroy(&sctp_sockets_allocated);
 out_nomem:
         return -ENOMEM;
 #else
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ba81fe3ccab8..a2de585888d0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -114,7 +114,7 @@ extern int sysctl_sctp_wmem[3];
 
 static int sctp_memory_pressure;
 static atomic_t sctp_memory_allocated;
-static atomic_t sctp_sockets_allocated;
+struct percpu_counter sctp_sockets_allocated;
 
 static void sctp_enter_memory_pressure(struct sock *sk)
 {
@@ -3613,7 +3613,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
         sp->hmac = NULL;
 
         SCTP_DBG_OBJCNT_INC(sock);
-        atomic_inc(&sctp_sockets_allocated);
+        percpu_counter_inc(&sctp_sockets_allocated);
 
         local_bh_disable();
         sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -3632,7 +3632,7 @@ SCTP_STATIC void sctp_destroy_sock(struct sock *sk)
         /* Release our hold on the endpoint. */
         ep = sctp_sk(sk)->ep;
         sctp_endpoint_free(ep);
-        atomic_dec(&sctp_sockets_allocated);
+        percpu_counter_dec(&sctp_sockets_allocated);
         local_bh_disable();
         sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
         local_bh_enable();
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3a35a6e8bf91..5aaf23e43f1d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -571,7 +571,6 @@ static const struct proto_ops unix_seqpacket_ops = {
 static struct proto unix_proto = {
         .name                   = "UNIX",
         .owner                  = THIS_MODULE,
-        .sockets_allocated      = &unix_nr_socks,
         .obj_size               = sizeof(struct unix_sock),
 };