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>

3 files changed, 33 insertions, 2 deletions

diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 9055cb380ee2..db0f4fcfdaf4 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -79,8 +79,9 @@ extern int				icmpv6_init(void);
 extern int				icmpv6_err_convert(u8 type, u8 code,
 							   int *err);
 extern void				icmpv6_cleanup(void);
-extern void				icmpv6_param_prob(struct sk_buff *skb,
-							  u8 code, int pos);
+extern void				icmpv6_param_prob_reason(struct sk_buff *skb,
+								 u8 code, int pos,
+								 enum skb_drop_reason reason);
 
 struct flowi6;
 struct in6_addr;
@@ -91,6 +92,12 @@ extern void				icmpv6_flow_init(struct sock *sk,
 							 const struct in6_addr *daddr,
 							 int oif);
 
+static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
+{
+	icmpv6_param_prob_reason(skb, code, pos,
+				 SKB_DROP_REASON_NOT_SPECIFIED);
+}
+
 static inline bool icmpv6_is_err(int type)
 {
 	switch (type) {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9b81ba497665..0ef11df1bc67 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -447,9 +447,30 @@ enum skb_drop_reason {
 					 * 2211, such as a broadcasts
 					 * ICMP_TIMESTAMP
 					 */
+	SKB_DROP_REASON_IP_INADDRERRORS,	/* host unreachable, corresponding
+						 * to IPSTATS_MIB_INADDRERRORS
+						 */
+	SKB_DROP_REASON_IP_INNOROUTES,	/* network unreachable, corresponding
+					 * to IPSTATS_MIB_INADDRERRORS
+					 */
+	SKB_DROP_REASON_PKT_TOO_BIG,	/* packet size is too big (maybe exceed
+					 * the MTU)
+					 */
 	SKB_DROP_REASON_MAX,
 };
 
+#define SKB_DR_INIT(name, reason)				\
+	enum skb_drop_reason name = SKB_DROP_REASON_##reason
+#define SKB_DR(name)						\
+	SKB_DR_INIT(name, NOT_SPECIFIED)
+#define SKB_DR_SET(name, reason)				\
+	(name = SKB_DROP_REASON_##reason)
+#define SKB_DR_OR(name, reason)					\
+	do {							\
+		if (name == SKB_DROP_REASON_NOT_SPECIFIED)	\
+			SKB_DR_SET(name, reason);		\
+	} while (0)
+
 /* To allow 64K frame to be packed as single skb without frag_list we
  * require 64K/PAGE_SIZE pages plus 1 additional page to allow for
  * buffers which do not start on a page boundary.
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 42647114fffe..2da72a9a5764 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -63,6 +63,9 @@
 	EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER)		\
 	EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM)		\
 	EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO)	\
+	EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS)	\
+	EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES)	\
+	EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG)		\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM