Merge branch 'ip-ingress-skb-reason'

Menglong Dong says:

====================
net: ip: add skb drop reasons to ip ingress

In the series "net: use kfree_skb_reason() for ip/udp packet receive",
skb drop reasons are added to the basic ingress path of IPv4. And in
the series "net: use kfree_skb_reason() for ip/neighbour", the egress
paths of IPv4 and IPv6 are handled. Related links:

https://lore.kernel.org/netdev/20220205074739.543606-1-imagedong@tencent.com/
https://lore.kernel.org/netdev/20220226041831.2058437-1-imagedong@tencent.com/

Seems we still have a lot work to do with IP layer, including IPv6 basic
ingress path, IPv4/IPv6 forwarding, IPv6 exthdrs, fragment and defrag,
etc.

In this series, skb drop reasons are added to the basic ingress path of
IPv6 protocol and IPv4/IPv6 packet forwarding. Following functions, which
are used for IPv6 packet receiving are handled:

  ip6_pkt_drop()
  ip6_rcv_core()
  ip6_protocol_deliver_rcu()

And following functions that used for IPv6 TLV parse are handled:

  ip6_parse_tlv()
  ipv6_hop_ra()
  ipv6_hop_ioam()
  ipv6_hop_jumbo()
  ipv6_hop_calipso()
  ipv6_dest_hao()

Besides, ip_forward() and ip6_forward(), which are used for IPv4/IPv6
forwarding, are also handled. And following new drop reasons are added:

  /* host unreachable, corresponding to IPSTATS_MIB_INADDRERRORS */
  SKB_DROP_REASON_IP_INADDRERRORS
  /* network unreachable, corresponding to IPSTATS_MIB_INADDRERRORS */
  SKB_DROP_REASON_IP_INNOROUTES
  /* packet size is too big, corresponding to
   * IPSTATS_MIB_INTOOBIGERRORS
   */
  SKB_DROP_REASON_PKT_TOO_BIG

In order to simply the definition and assignment for
'enum skb_drop_reason', some helper functions are introduced in the 1th
patch. I'm not such if this is necessary, but it makes the code simpler.
For example, we can replace the code:

  if (reason == SKB_DROP_REASON_NOT_SPECIFIED)
          reason = SKB_DROP_REASON_IP_INHDR;

with:

  SKB_DR_OR(reason, IP_INHDR);

In the 6th patch, the statistics for skb in ipv6_hop_jum() is removed,
as I think it is redundant. There are two call chains for
ipv6_hop_jumbo(). The first one is:

  ipv6_destopt_rcv() -> ip6_parse_tlv() -> ipv6_hop_jumbo()

On this call chain, the drop statistics will be done in
ipv6_destopt_rcv() with 'IPSTATS_MIB_INHDRERRORS' if ipv6_hop_jumbo()
returns false.

The second call chain is:

  ip6_rcv_core() -> ipv6_parse_hopopts() -> ip6_parse_tlv()

And the drop statistics will also be done in ip6_rcv_core() with
'IPSTATS_MIB_INHDRERRORS' if ipv6_hop_jumbo() returns false.

Therefore, the statistics in ipv6_hop_jumbo() is redundant, which
means the drop is counted twice. The statistics in ipv6_hop_jumbo()
is almost the same as the outside, except the
'IPSTATS_MIB_INTRUNCATEDPKTS', which seems that we have to ignore it.

======================================================================

Here is a basic test for IPv6 forwarding packet drop that monitored by
'dropwatch' tool:

  drop at: ip6_forward+0x81a/0xb70 (0xffffffff86c73f8a)
  origin: software
  input port ifindex: 7
  timestamp: Wed Apr 13 11:51:06 2022 130010176 nsec
  protocol: 0x86dd
  length: 94
  original length: 94
  drop reason: IP_INADDRERRORS

The origin cause of this case is that IPv6 doesn't allow to forward the
packet with LOCAL-LINK saddr, and results the 'IP_INADDRERRORS' drop
reason.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 12 deletions

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index b4880c7c84eb..126ae3aa67e1 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -145,13 +145,14 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
 static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 				    struct net *net)
 {
+	enum skb_drop_reason reason;
 	const struct ipv6hdr *hdr;
 	u32 pkt_len;
 	struct inet6_dev *idev;
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
 		return NULL;
 	}
 
@@ -161,9 +162,12 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 
 	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
 
+	SKB_DR_SET(reason, NOT_SPECIFIED);
 	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
 	    !idev || unlikely(idev->cnf.disable_ipv6)) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+		if (unlikely(idev->cnf.disable_ipv6))
+			SKB_DR_SET(reason, IPV6DISABLED);
 		goto drop;
 	}
 
@@ -187,8 +191,10 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 
 	hdr = ipv6_hdr(skb);
 
-	if (hdr->version != 6)
+	if (hdr->version != 6) {
+		SKB_DR_SET(reason, UNHANDLED_PROTO);
 		goto err;
+	}
 
 	__IP6_ADD_STATS(net, idev,
 			IPSTATS_MIB_NOECTPKTS +
@@ -226,8 +232,10 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
 	    (skb->pkt_type == PACKET_BROADCAST ||
 	     skb->pkt_type == PACKET_MULTICAST) &&
-	    idev->cnf.drop_unicast_in_l2_multicast)
+	    idev->cnf.drop_unicast_in_l2_multicast) {
+		SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST);
 		goto err;
+	}
 
 	/* RFC4291 2.7
 	 * Nodes must not originate a packet to a multicast address whose scope
@@ -256,12 +264,11 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 		if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
 			__IP6_INC_STATS(net,
 					idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+			SKB_DR_SET(reason, PKT_TOO_SMALL);
 			goto drop;
 		}
-		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
-			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
-			goto drop;
-		}
+		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
+			goto err;
 		hdr = ipv6_hdr(skb);
 	}
 
@@ -282,9 +289,10 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 err:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+	SKB_DR_OR(reason, IP_INHDR);
 drop:
 	rcu_read_unlock();
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return NULL;
 }
 
@@ -354,6 +362,7 @@ void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
 	const struct inet6_protocol *ipprot;
 	struct inet6_dev *idev;
 	unsigned int nhoff;
+	SKB_DR(reason);
 	bool raw;
 
 	/*
@@ -413,12 +422,16 @@ resubmit_final:
 			if (ipv6_addr_is_multicast(&hdr->daddr) &&
 			    !ipv6_chk_mcast_addr(dev, &hdr->daddr,
 						 &hdr->saddr) &&
-			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
+			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) {
+				SKB_DR_SET(reason, IP_INADDRERRORS);
 				goto discard;
+			}
 		}
 		if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
-		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
+		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+			SKB_DR_SET(reason, XFRM_POLICY);
 			goto discard;
+		}
 
 		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
 				      skb);
@@ -444,8 +457,11 @@ resubmit_final:
 						IPSTATS_MIB_INUNKNOWNPROTOS);
 				icmpv6_send(skb, ICMPV6_PARAMPROB,
 					    ICMPV6_UNK_NEXTHDR, nhoff);
+				SKB_DR_SET(reason, IP_NOPROTO);
+			} else {
+				SKB_DR_SET(reason, XFRM_POLICY);
 			}
-			kfree_skb(skb);
+			kfree_skb_reason(skb, reason);
 		} else {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
 			consume_skb(skb);
@@ -455,7 +471,7 @@ resubmit_final:
 
 discard:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 }
 
 static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)