af_unix: speedup /proc/net/unix

/proc/net/unix has quadratic behavior, and can hold unix_table_lock for
a while if high number of unix sockets are alive. (90 ms for 200k
sockets...)

We already have a hash table, so its quite easy to use it.

Problem is unbound sockets are still hashed in a single hash slot
(unix_socket_table[UNIX_HASH_TABLE])

This patch also spreads unbound sockets to 256 hash slots, to speedup
both /proc/net/unix and unix_diag.

Time to read /proc/net/unix with 200k unix sockets :
(time dd if=/proc/net/unix of=/dev/null bs=4k)

before : 520 secs
after : 2 secs

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 2ee33da..b5f8988 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -14,10 +14,11 @@
 extern struct sock *unix_peer_get(struct sock *);
 
 #define UNIX_HASH_SIZE	256
+#define UNIX_HASH_BITS	8
 
 extern unsigned int unix_tot_inflight;
 extern spinlock_t unix_table_lock;
-extern struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
+extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
 
 struct unix_address {
 	atomic_t	refcnt;