[IPV4] ROUTE: ip_rt_dump() is unecessary slow

I noticed "ip route list cache x.y.z.t" can be *very* slow.

While strace-ing -T it I also noticed that first part of route cache
is fetched quite fast :

recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202
GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3772 <0.000047>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\234\0\0\0\30\0\2\0\254i\
202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3736 <0.000042>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\204\0\0\0\30\0\2\0\254i\
202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3740 <0.000055>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\234\0\0\0\30\0\2\0\254i\
202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3712 <0.000043>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\204\0\0\0\30\0\2\0\254i\
202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3732 <0.000053>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202
GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3708 <0.000052>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202
GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3680 <0.000041>

while the part at the end of the table is more expensive:

recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\204\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3656 <0.003857>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\204\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3772 <0.003891>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3712 <0.003765>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3700 <0.003879>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3676 <0.003797>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"p\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\2\0\2\0"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3724 <0.003856>
recvmsg(3, {msg_name(12)={sa_family=AF_NETLINK, pid=0, groups=00000000}, msg_iov(1)=[{"\234\0\0\0\30\0\2\0\254i\202GXm\0\0\2  \0\376\0\0\1\0\2"..., 16384}], msg_controllen=0, msg_flags=0}, 0) = 3736 <0.003848>

The following patch corrects this performance/latency problem,
removing quadratic behavior.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/route.c

@@ -2626,11 +2626,10 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 	int idx, s_idx;
 
 	s_h = cb->args[0];
+	if (s_h < 0)
+		s_h = 0;
 	s_idx = idx = cb->args[1];
-	for (h = 0; h <= rt_hash_mask; h++) {
-		if (h < s_h) continue;
-		if (h > s_h)
-			s_idx = 0;
+	for (h = s_h; h <= rt_hash_mask; h++) {
 		rcu_read_lock_bh();
 		for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
 		     rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
@@ -2647,6 +2646,7 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 			dst_release(xchg(&skb->dst, NULL));
 		}
 		rcu_read_unlock_bh();
+		s_idx = 0;
 	}
 
 done: