inetpeer: get rid of ip_id_count

[ Upstream commit 73f156a6e8c1074ac6327e0abd1169e95eb66463 ]

Ideally, we would need to generate IP ID using a per destination IP
generator.

linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.

1) each inet_peer struct consumes 192 bytes

2) inetpeer cache uses a binary tree of inet_peer structs,
   with a nominal size of ~66000 elements under load.

3) lookups in this tree are hitting a lot of cache lines, as tree depth
   is about 20.

4) If server deals with many tcp flows, we have a high probability of
   not finding the inet_peer, allocating a fresh one, inserting it in
   the tree with same initial ip_id_count, (cf secure_ip_id())

5) We garbage collect inet_peer aggressively.

IP ID generation do not have to be 'perfect'

Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.

We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.

ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)

secure_ip_id() and secure_ipv6_id() no longer are needed.

Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 16 insertions, 24 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ffa8d295c56c..a425052ac274 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -540,6 +540,21 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	static bool hashrnd_initialized = false;
+	u32 hash, id;
+
+	if (unlikely(!hashrnd_initialized)) {
+		hashrnd_initialized = true;
+		get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+	}
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
+}
+
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 3d2c81a66d6a..a5d465105b69 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -6,29 +6,6 @@
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static atomic_t ipv6_fragmentation_id;
-	int ident;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		struct inet_peer *peer;
-		struct net *net;
-
-		net = dev_net(rt->dst.dev);
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		if (peer) {
-			fhdr->identification = htonl(inet_getid(peer, 0));
-			inet_putpeer(peer);
-			return;
-		}
-	}
-#endif
-	ident = atomic_inc_return(&ipv6_fragmentation_id);
-	fhdr->identification = htonl(ident);
-}
-EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 540d58921007..8d22460a811b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -919,7 +919,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		iph->ttl	=	iph6->hop_limit;
 
 	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(skb, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	iptunnel_xmit(skb, dev);
 	return NETDEV_TX_OK;