Merge branch 'ipv6-kfree_skb_reason'

Menglong Dong says:

====================
net: use kfree_skb_reason() for ip/udp packet receive

In this series patches, kfree_skb() is replaced with kfree_skb_reason()
during ipv4 and udp4 packet receiving path, and following drop reasons
are introduced:

SKB_DROP_REASON_SOCKET_FILTER
SKB_DROP_REASON_NETFILTER_DROP
SKB_DROP_REASON_OTHERHOST
SKB_DROP_REASON_IP_CSUM
SKB_DROP_REASON_IP_INHDR
SKB_DROP_REASON_IP_RPFILTER
SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST
SKB_DROP_REASON_XFRM_POLICY
SKB_DROP_REASON_IP_NOPROTO
SKB_DROP_REASON_SOCKET_RCVBUFF
SKB_DROP_REASON_PROTO_MEM

TCP is more complex, so I left it in the next series.

I just figure out how __print_symbolic() works. It doesn't base on the
array index, but searching for symbols by loop. So I'm a little afraid
it's performance.

Changes since v3:
- fix some small problems in the third patch (net: ipv4: use
  kfree_skb_reason() in ip_rcv_core()), as David Ahern said

Changes since v2:
- use SKB_DROP_REASON_PKT_TOO_SMALL for a path in ip_rcv_core()

Changes since v1:
- add document for all drop reasons, as David advised
- remove unreleated cleanup
- remove EARLY_DEMUX and IP_ROUTE_INPUT drop reason
- replace {UDP, TCP}_FILTER with SOCKET_FILTER
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/skbuff.h

@@ -314,12 +314,38 @@ struct sk_buff;
  * used to translate the reason to string.
  */
 enum skb_drop_reason {
-	SKB_DROP_REASON_NOT_SPECIFIED,
-	SKB_DROP_REASON_NO_SOCKET,
-	SKB_DROP_REASON_PKT_TOO_SMALL,
-	SKB_DROP_REASON_TCP_CSUM,
-	SKB_DROP_REASON_SOCKET_FILTER,
-	SKB_DROP_REASON_UDP_CSUM,
+	SKB_DROP_REASON_NOT_SPECIFIED,	/* drop reason is not specified */
+	SKB_DROP_REASON_NO_SOCKET,	/* socket not found */
+	SKB_DROP_REASON_PKT_TOO_SMALL,	/* packet size is too small */
+	SKB_DROP_REASON_TCP_CSUM,	/* TCP checksum error */
+	SKB_DROP_REASON_SOCKET_FILTER,	/* dropped by socket filter */
+	SKB_DROP_REASON_UDP_CSUM,	/* UDP checksum error */
+	SKB_DROP_REASON_NETFILTER_DROP,	/* dropped by netfilter */
+	SKB_DROP_REASON_OTHERHOST,	/* packet don't belong to current
+					 * host (interface is in promisc
+					 * mode)
+					 */
+	SKB_DROP_REASON_IP_CSUM,	/* IP checksum error */
+	SKB_DROP_REASON_IP_INHDR,	/* there is something wrong with
+					 * IP header (see
+					 * IPSTATS_MIB_INHDRERRORS)
+					 */
+	SKB_DROP_REASON_IP_RPFILTER,	/* IP rpfilter validate failed.
+					 * see the document for rp_filter
+					 * in ip-sysctl.rst for more
+					 * information
+					 */
+	SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2
+						  * is multicast, but L3 is
+						  * unicast.
+						  */
+	SKB_DROP_REASON_XFRM_POLICY,	/* xfrm policy check failed */
+	SKB_DROP_REASON_IP_NOPROTO,	/* no support for IP protocol */
+	SKB_DROP_REASON_SOCKET_RCVBUFF,	/* socket receive buff is full */
+	SKB_DROP_REASON_PROTO_MEM,	/* proto memory limition, such as
+					 * udp packet drop out of
+					 * udp_memory_allocated.
+					 */
 	SKB_DROP_REASON_MAX,
 };
 

include/trace/events/skb.h

@@ -16,6 +16,17 @@
 	EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM)			\
 	EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER)	\
 	EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM)			\
+	EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP)	\
+	EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST)		\
+	EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM)			\
+	EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR)			\
+	EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER)		\
+	EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST,		\
+	   UNICAST_IN_L2_MULTICAST)				\
+	EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY)		\
+	EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO)		\
+	EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF)	\
+	EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM)		\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM

net/ipv4/ip_input.c

@@ -196,7 +196,8 @@ void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
 	if (ipprot) {
 		if (!ipprot->no_policy) {
 			if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-				kfree_skb(skb);
+				kfree_skb_reason(skb,
+						 SKB_DROP_REASON_XFRM_POLICY);
 				return;
 			}
 			nf_reset_ct(skb);
@@ -215,7 +216,7 @@ void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
 				icmp_send(skb, ICMP_DEST_UNREACH,
 					  ICMP_PROT_UNREACH, 0);
 			}
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_IP_NOPROTO);
 		} else {
 			__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
 			consume_skb(skb);
@@ -318,8 +319,10 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int (*edemux)(struct sk_buff *skb);
+	int err, drop_reason;
 	struct rtable *rt;
-	int err;
+
+	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 
 	if (ip_can_use_hint(skb, iph, hint)) {
 		err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
@@ -396,19 +399,23 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 		 * so-called "hole-196" attack) so do it for both.
 		 */
 		if (in_dev &&
-		    IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
+		    IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) {
+			drop_reason = SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST;
 			goto drop;
 		}
+	}
 
 	return NET_RX_SUCCESS;
 
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return NET_RX_DROP;
 
 drop_error:
-	if (err == -EXDEV)
+	if (err == -EXDEV) {
+		drop_reason = SKB_DROP_REASON_IP_RPFILTER;
 		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
+	}
 	goto drop;
 }
 
@@ -436,13 +443,16 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 {
 	const struct iphdr *iph;
+	int drop_reason;
 	u32 len;
 
 	/* When the interface is in promisc. mode, drop all the crap
 	 * that it receives, do not try to analyse it.
 	 */
-	if (skb->pkt_type == PACKET_OTHERHOST)
+	if (skb->pkt_type == PACKET_OTHERHOST) {
+		drop_reason = SKB_DROP_REASON_OTHERHOST;
 		goto drop;
+	}
 
 	__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
 
@@ -452,6 +462,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 		goto out;
 	}
 
+	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto inhdr_error;
 
@@ -488,6 +499,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 
 	len = ntohs(iph->tot_len);
 	if (skb->len < len) {
+		drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
 		goto drop;
 	} else if (len < (iph->ihl*4))
@@ -516,11 +528,14 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 	return skb;
 
 csum_error:
+	drop_reason = SKB_DROP_REASON_IP_CSUM;
 	__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
 inhdr_error:
+	if (drop_reason == SKB_DROP_REASON_NOT_SPECIFIED)
+		drop_reason = SKB_DROP_REASON_IP_INHDR;
 	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 out:
 	return NULL;
 }

net/ipv4/udp.c

@@ -2093,16 +2093,20 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	rc = __udp_enqueue_schedule_skb(sk, skb);
 	if (rc < 0) {
 		int is_udplite = IS_UDPLITE(sk);
+		int drop_reason;
 
 		/* Note that an ENOMEM error is charged twice */
-		if (rc == -ENOMEM)
+		if (rc == -ENOMEM) {
 			UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
 					is_udplite);
-		else
+			drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
+		} else {
 			UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS,
 				      is_udplite);
+			drop_reason = SKB_DROP_REASON_PROTO_MEM;
+		}
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, drop_reason);
 		trace_udp_fail_queue_rcv_skb(rc, sk);
 		return -1;
 	}
@@ -2120,14 +2124,17 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
  */
 static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
+	int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
 
 	/*
 	 *	Charge it to the socket, dropping if the queue is full.
 	 */
-	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
+		drop_reason = SKB_DROP_REASON_XFRM_POLICY;
 		goto drop;
+	}
 	nf_reset_ct(skb);
 
 	if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
@@ -2204,8 +2211,10 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 			goto csum_error;
 
-	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr)))
+	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
+		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		goto drop;
+	}
 
 	udp_csum_pull_header(skb);
 
@@ -2213,11 +2222,12 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	return __udp_queue_rcv_skb(sk, skb);
 
 csum_error:
+	drop_reason = SKB_DROP_REASON_UDP_CSUM;
 	__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 drop:
 	__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	atomic_inc(&sk->sk_drops);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return -1;
 }
 

net/netfilter/core.c

@@ -621,7 +621,8 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
 		case NF_ACCEPT:
 			break;
 		case NF_DROP:
-			kfree_skb(skb);
+			kfree_skb_reason(skb,
+					 SKB_DROP_REASON_NETFILTER_DROP);
 			ret = NF_DROP_GETERR(verdict);
 			if (ret == 0)
 				ret = -EPERM;