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>

1 files changed, 7 insertions, 3 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))