[PATCH net-next 01/11] ip_tunnel: add drop reasons to the generic RX path

[Anton Danilov]

ip_tunnel_rcv() collapses four distinct failures into a single plain
kfree_skb(), so a packet dropped there simply vanishes:

 - the tunnel options carried by the packet do not match the tunnel
   configuration (checksum or sequence number),
 - the sequence number is older than the expected one,
 - the inner network header cannot be pulled,
 - the ECN decapsulation check fails (RFC 6040).

Only the device error counters (rx_crc_errors, rx_fifo_errors,
rx_length_errors, rx_frame_errors) hint at the cause, and they are not
reported to drop_monitor or to the skb:kfree_skb tracepoint.

Add two drop reasons for the tunnel specific cases and reuse the
existing ones for the rest:

 - SKB_DROP_REASON_IP_TUNNEL_CFG_OPTS_MISMATCH is used when the packet
   does not carry the checksum or the sequence number option the tunnel
   is configured for.  This is a configuration mismatch between the two
   endpoints rather than a corrupted checksum: the checksum itself is
   validated earlier, in gre_parse_header().

 - SKB_DROP_REASON_IP_TUNNEL_OLD_SEQ is used when the sequence number
   is older than the expected one.  Unlike the previous one this is a
   property of the received traffic: a remote endpoint that restarts
   and resets its sequence numbering has all of its packets dropped
   until i_seqno catches up.

 - pskb_inet_may_pull_reason() already computes a drop reason,
   SKB_DROP_REASON_PKT_TOO_SMALL or SKB_DROP_REASON_NOMEM, which was
   discarded so far.

 - SKB_DROP_REASON_IP_TUNNEL_ECN already exists and documents exactly
   this check, but until now it was only used by vxlan.

The sequence number test is split in two so that the two cases can be
told apart.  The error counters are left unchanged.

ip_tunnel_rcv() is the RX path of ip_gre, ipip and sit.  The checksum
and the sequence number options only exist for GRE, so the two new
reasons are reachable through ip_gre alone, while the length and the
ECN ones apply to all three.

Assisted-by: Claude-Code:claude-opus-5
Signed-off-by: Anton Danilov <littlesmilingcloud@xxxxxxxxx>
---
 include/net/dropreason-core.h | 16 ++++++++++++++++
 net/ipv4/ip_tunnel.c          | 19 +++++++++++++++----
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 2f312d1f67d6..40f94ecb912a 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -128,6 +128,8 @@
 	FN(PSP_INPUT)			\
 	FN(PSP_OUTPUT)			\
 	FN(RECURSION_LIMIT)		\
+	FN(IP_TUNNEL_CFG_OPTS_MISMATCH)	\
+	FN(IP_TUNNEL_OLD_SEQ)		\
 	FNe(MAX)
 
 /**
@@ -606,6 +608,20 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_PSP_OUTPUT,
 	/** @SKB_DROP_REASON_RECURSION_LIMIT: Dead loop on virtual device. */
 	SKB_DROP_REASON_RECURSION_LIMIT,
+	/**
+	 * @SKB_DROP_REASON_IP_TUNNEL_CFG_OPTS_MISMATCH: the tunnel options
+	 * carried by the packet do not match the tunnel configuration, e.g.
+	 * a GRE tunnel configured with 'icsum' or 'iseq' received a packet
+	 * with no checksum or no sequence number.
+	 */
+	SKB_DROP_REASON_IP_TUNNEL_CFG_OPTS_MISMATCH,
+	/**
+	 * @SKB_DROP_REASON_IP_TUNNEL_OLD_SEQ: the sequence number carried
+	 * by the packet is older than the one expected by the tunnel, e.g.
+	 * after the remote endpoint restarted and reset its sequence
+	 * numbering.
+	 */
+	SKB_DROP_REASON_IP_TUNNEL_OLD_SEQ,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e6bcf01411d0..ab8bae8ba781 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -379,6 +379,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  bool log_ecn_error)
 {
 	const struct iphdr *iph = ip_hdr(skb);
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	int nh, err;
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
@@ -392,14 +393,22 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 	    test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) {
 		DEV_STATS_INC(tunnel->dev, rx_crc_errors);
 		DEV_STATS_INC(tunnel->dev, rx_errors);
+		reason = SKB_DROP_REASON_IP_TUNNEL_CFG_OPTS_MISMATCH;
 		goto drop;
 	}
 
 	if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) {
-		if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) ||
-		    (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
+		if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags)) {
 			DEV_STATS_INC(tunnel->dev, rx_fifo_errors);
 			DEV_STATS_INC(tunnel->dev, rx_errors);
+			reason = SKB_DROP_REASON_IP_TUNNEL_CFG_OPTS_MISMATCH;
+			goto drop;
+		}
+		if (tunnel->i_seqno &&
+		    (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0) {
+			DEV_STATS_INC(tunnel->dev, rx_fifo_errors);
+			DEV_STATS_INC(tunnel->dev, rx_errors);
+			reason = SKB_DROP_REASON_IP_TUNNEL_OLD_SEQ;
 			goto drop;
 		}
 		tunnel->i_seqno = ntohl(tpi->seq) + 1;
@@ -413,7 +422,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 
 	skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0);
 
-	if (!pskb_inet_may_pull(skb)) {
+	reason = pskb_inet_may_pull_reason(skb);
+	if (reason) {
 		DEV_STATS_INC(tunnel->dev, rx_length_errors);
 		DEV_STATS_INC(tunnel->dev, rx_errors);
 		goto drop;
@@ -428,6 +438,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		if (err > 1) {
 			DEV_STATS_INC(tunnel->dev, rx_frame_errors);
 			DEV_STATS_INC(tunnel->dev, rx_errors);
+			reason = SKB_DROP_REASON_IP_TUNNEL_ECN;
 			goto drop;
 		}
 	}
@@ -451,7 +462,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 drop:
 	if (tun_dst)
 		dst_release((struct dst_entry *)tun_dst);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
-- 
2.47.3