Merge: net: visibility improvements for 10.1

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/902

JIRA: https://issues.redhat.com/browse/RHEL-88891

A few patches added to ease backporting visibility patches, none should
introduce a change in behavior.

Signed-off-by: Antoine Tenart <[email protected]>

Approved-by: Guillaume Nault <[email protected]>

Merged-by: Julio Faracco <[email protected]>

Author: jcfaracco

Documentation/networking/net_cachelines/snmp.rst

@@ -35,6 +35,8 @@ unsigned_long  LINUX_MIB_TIMEWAITRECYCLED
 unsigned_long  LINUX_MIB_TIMEWAITKILLED                                                      
 unsigned_long  LINUX_MIB_PAWSACTIVEREJECTED                                                  
 unsigned_long  LINUX_MIB_PAWSESTABREJECTED                                                   
+unsigned_long  LINUX_MIB_PAWS_OLD_ACK
+unsigned_long  LINUX_MIB_PAWS_TW_REJECTED
 unsigned_long  LINUX_MIB_DELAYEDACKLOST                                                      
 unsigned_long  LINUX_MIB_LISTENOVERFLOWS                                                     
 unsigned_long  LINUX_MIB_LISTENDROPS                                                         

drivers/net/vxlan/vxlan_core.c

@@ -2808,7 +2808,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			dev_core_stats_tx_dropped_inc(dev);
 			vxlan_vnifilter_count(vxlan, vni, NULL,
 					      VXLAN_VNI_STATS_TX_DROPS, 0);
-			kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE);
+			kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET);
 			return NETDEV_TX_OK;
 		}
 	}
@@ -2831,7 +2831,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (fdst)
 			vxlan_xmit_one(skb, dev, vni, fdst, did_rsc);
 		else
-			kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE);
+			kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET);
 	}
 
 	return NETDEV_TX_OK;

drivers/net/vxlan/vxlan_mdb.c

@@ -1712,7 +1712,7 @@ netdev_tx_t vxlan_mdb_xmit(struct vxlan_dev *vxlan,
 		vxlan_xmit_one(skb, vxlan->dev, src_vni,
 			       rcu_dereference(fremote->rd), false);
 	else
-		kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE);
+		kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET);
 
 	return NETDEV_TX_OK;
 }

include/net/dropreason-core.h

@@ -6,9 +6,13 @@
 #define DEFINE_DROP_REASON(FN, FNe)	\
 	FN(NOT_SPECIFIED)		\
 	FN(NO_SOCKET)			\
+	FN(SOCKET_CLOSE)		\
+	FN(SOCKET_FILTER)		\
+	FN(SOCKET_RCVBUFF)		\
+	FN(UNIX_DISCONNECT)		\
+	FN(UNIX_SKIP_OOB)		\
 	FN(PKT_TOO_SMALL)		\
 	FN(TCP_CSUM)			\
-	FN(SOCKET_FILTER)		\
 	FN(UDP_CSUM)			\
 	FN(NETFILTER_DROP)		\
 	FN(OTHERHOST)			\
@@ -18,7 +22,6 @@
 	FN(UNICAST_IN_L2_MULTICAST)	\
 	FN(XFRM_POLICY)			\
 	FN(IP_NOPROTO)			\
-	FN(SOCKET_RCVBUFF)		\
 	FN(PROTO_MEM)			\
 	FN(TCP_AUTH_HDR)		\
 	FN(TCP_MD5NOTFOUND)		\
@@ -36,6 +39,10 @@
 	FN(TCP_OVERWINDOW)		\
 	FN(TCP_OFOMERGE)		\
 	FN(TCP_RFC7323_PAWS)		\
+	FN(TCP_RFC7323_PAWS_ACK)	\
+	FN(TCP_RFC7323_TW_PAWS)		\
+	FN(TCP_RFC7323_TSECR)		\
+	FN(TCP_LISTEN_OVERFLOW)		\
 	FN(TCP_OLD_SEQUENCE)		\
 	FN(TCP_INVALID_SEQUENCE)	\
 	FN(TCP_INVALID_ACK_SEQUENCE)	\
@@ -58,6 +65,12 @@
 	FN(TC_EGRESS)			\
 	FN(SECURITY_HOOK)		\
 	FN(QDISC_DROP)			\
+	FN(QDISC_OVERLIMIT)		\
+	FN(QDISC_CONGESTED)		\
+	FN(CAKE_FLOOD)			\
+	FN(FQ_BAND_LIMIT)		\
+	FN(FQ_HORIZON_LIMIT)		\
+	FN(FQ_FLOW_LIMIT)		\
 	FN(CPU_BACKLOG)			\
 	FN(XDP)				\
 	FN(TC_INGRESS)			\
@@ -76,6 +89,10 @@
 	FN(INVALID_PROTO)		\
 	FN(IP_INADDRERRORS)		\
 	FN(IP_INNOROUTES)		\
+	FN(IP_LOCAL_SOURCE)		\
+	FN(IP_INVALID_SOURCE)		\
+	FN(IP_LOCALNET)			\
+	FN(IP_INVALID_DEST)		\
 	FN(PKT_TOO_BIG)			\
 	FN(DUP_FRAG)			\
 	FN(FRAG_REASM_TIMEOUT)		\
@@ -96,10 +113,13 @@
 	FN(VXLAN_VNI_NOT_FOUND)		\
 	FN(MAC_INVALID_SOURCE)		\
 	FN(VXLAN_ENTRY_EXISTS)		\
-	FN(VXLAN_NO_REMOTE)		\
+	FN(NO_TX_TARGET)		\
 	FN(IP_TUNNEL_ECN)		\
 	FN(TUNNEL_TXINFO)		\
 	FN(LOCAL_MAC)			\
+	FN(ARP_PVLAN_DISABLE)		\
+	FN(MAC_IEEE_MAC_CONTROL)	\
+	FN(BRIDGE_INGRESS_STP_STATE)	\
 	FNe(MAX)
 
 /**
@@ -124,12 +144,27 @@ enum skb_drop_reason {
 	 * 3) no valid child socket during 3WHS process
 	 */
 	SKB_DROP_REASON_NO_SOCKET,
+	/** @SKB_DROP_REASON_SOCKET_CLOSE: socket is close()d */
+	SKB_DROP_REASON_SOCKET_CLOSE,
+	/** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */
+	SKB_DROP_REASON_SOCKET_FILTER,
+	/** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
+	SKB_DROP_REASON_SOCKET_RCVBUFF,
+	/**
+	 * @SKB_DROP_REASON_UNIX_DISCONNECT: recv queue is purged when SOCK_DGRAM
+	 * or SOCK_SEQPACKET socket re-connect()s to another socket or notices
+	 * during send() that the peer has been close()d.
+	 */
+	SKB_DROP_REASON_UNIX_DISCONNECT,
+	/**
+	 * @SKB_DROP_REASON_UNIX_SKIP_OOB: Out-Of-Band data is skipped by
+	 * recv() without MSG_OOB so dropped.
+	 */
+	SKB_DROP_REASON_UNIX_SKIP_OOB,
 	/** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */
 	SKB_DROP_REASON_PKT_TOO_SMALL,
 	/** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */
 	SKB_DROP_REASON_TCP_CSUM,
-	/** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */
-	SKB_DROP_REASON_SOCKET_FILTER,
 	/** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */
 	SKB_DROP_REASON_UDP_CSUM,
 	/** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */
@@ -160,8 +195,6 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_XFRM_POLICY,
 	/** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */
 	SKB_DROP_REASON_IP_NOPROTO,
-	/** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
-	SKB_DROP_REASON_SOCKET_RCVBUFF,
 	/**
 	 * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as
 	 * udp packet drop out of udp_memory_allocated.
@@ -246,6 +279,24 @@ enum skb_drop_reason {
 	 * LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED
 	 */
 	SKB_DROP_REASON_TCP_RFC7323_PAWS,
+	/**
+	 * @SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK: PAWS check, old ACK packet.
+	 * Corresponds to LINUX_MIB_PAWS_OLD_ACK.
+	 */
+	SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK,
+	/**
+	 * @SKB_DROP_REASON_TCP_RFC7323_TW_PAWS: PAWS check, socket is in
+	 * TIME_WAIT state.
+	 * Corresponds to LINUX_MIB_PAWS_TW_REJECTED.
+	 */
+	SKB_DROP_REASON_TCP_RFC7323_TW_PAWS,
+	/**
+	 * @SKB_DROP_REASON_TCP_RFC7323_TSECR: PAWS check, invalid TSEcr.
+	 * Corresponds to LINUX_MIB_TSECRREJECTED.
+	 */
+	SKB_DROP_REASON_TCP_RFC7323_TSECR,
+	/** @SKB_DROP_REASON_TCP_LISTEN_OVERFLOW: listener queue full. */
+	SKB_DROP_REASON_TCP_LISTEN_OVERFLOW,
 	/** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */
 	SKB_DROP_REASON_TCP_OLD_SEQUENCE,
 	/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */
@@ -306,6 +357,36 @@ enum skb_drop_reason {
 	 * failed to enqueue to current qdisc)
 	 */
 	SKB_DROP_REASON_QDISC_DROP,
+	/**
+	 * @SKB_DROP_REASON_QDISC_OVERLIMIT: dropped by qdisc when a qdisc
+	 * instance exceeds its total buffer size limit.
+	 */
+	SKB_DROP_REASON_QDISC_OVERLIMIT,
+	/**
+	 * @SKB_DROP_REASON_QDISC_CONGESTED: dropped by a qdisc AQM algorithm
+	 * due to congestion.
+	 */
+	SKB_DROP_REASON_QDISC_CONGESTED,
+	/**
+	 * @SKB_DROP_REASON_CAKE_FLOOD: dropped by the flood protection part of
+	 * CAKE qdisc AQM algorithm (BLUE).
+	 */
+	SKB_DROP_REASON_CAKE_FLOOD,
+	/**
+	 * @SKB_DROP_REASON_FQ_BAND_LIMIT: dropped by fq qdisc when per band
+	 * limit is reached.
+	 */
+	SKB_DROP_REASON_FQ_BAND_LIMIT,
+	/**
+	 * @SKB_DROP_REASON_FQ_HORIZON_LIMIT: dropped by fq qdisc when packet
+	 * timestamp is too far in the future.
+	 */
+	SKB_DROP_REASON_FQ_HORIZON_LIMIT,
+	/**
+	 * @SKB_DROP_REASON_FQ_FLOW_LIMIT: dropped by fq qdisc when a flow
+	 * exceeds its limits.
+	 */
+	SKB_DROP_REASON_FQ_FLOW_LIMIT,
 	/**
 	 * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU
 	 * backlog queue. This can be caused by backlog queue full (see
@@ -373,6 +454,21 @@ enum skb_drop_reason {
 	 * IPSTATS_MIB_INADDRERRORS
 	 */
 	SKB_DROP_REASON_IP_INNOROUTES,
+	/** @SKB_DROP_REASON_IP_LOCAL_SOURCE: the source ip is local */
+	SKB_DROP_REASON_IP_LOCAL_SOURCE,
+	/**
+	 * @SKB_DROP_REASON_IP_INVALID_SOURCE: the source ip is invalid:
+	 * 1) source ip is multicast or limited broadcast
+	 * 2) source ip is zero and not IGMP
+	 */
+	SKB_DROP_REASON_IP_INVALID_SOURCE,
+	/** @SKB_DROP_REASON_IP_LOCALNET: source or dest ip is local net */
+	SKB_DROP_REASON_IP_LOCALNET,
+	/**
+	 * @SKB_DROP_REASON_IP_INVALID_DEST: the dest ip is invalid:
+	 * 1) dest ip is 0
+	 */
+	SKB_DROP_REASON_IP_INVALID_DEST,
 	/**
 	 * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the
 	 * MTU)
@@ -441,8 +537,8 @@ enum skb_drop_reason {
 	 * entry or an entry pointing to a nexthop.
 	 */
 	SKB_DROP_REASON_VXLAN_ENTRY_EXISTS,
-	/** @SKB_DROP_REASON_VXLAN_NO_REMOTE: no remote found for xmit */
-	SKB_DROP_REASON_VXLAN_NO_REMOTE,
+	/** @SKB_DROP_REASON_NO_TX_TARGET: no target found for xmit */
+	SKB_DROP_REASON_NO_TX_TARGET,
 	/**
 	 * @SKB_DROP_REASON_IP_TUNNEL_ECN: skb is dropped according to
 	 * RFC 6040 4.2, see __INET_ECN_decapsulate() for detail.
@@ -458,6 +554,22 @@ enum skb_drop_reason {
 	 * the MAC address of the local netdev.
 	 */
 	SKB_DROP_REASON_LOCAL_MAC,
+	/**
+	 * @SKB_DROP_REASON_ARP_PVLAN_DISABLE: packet which is not IP is
+	 * forwarded to the in_dev, and the proxy_arp_pvlan is not
+	 * enabled.
+	 */
+	SKB_DROP_REASON_ARP_PVLAN_DISABLE,
+	/**
+	 * @SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL: the destination MAC address
+	 * is an IEEE MAC Control address.
+	 */
+	SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL,
+	/**
+	 * @SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE: the STP state of the
+	 * ingress bridge port does not allow frames to be forwarded.
+	 */
+	SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen

include/net/ip_fib.h

@@ -451,6 +451,19 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev);
 int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			u8 tos, int oif, struct net_device *dev,
 			struct in_device *idev, u32 *itag);
+
+static inline enum skb_drop_reason
+fib_validate_source_reason(struct sk_buff *skb, __be32 src, __be32 dst,
+			   dscp_t dscp, int oif, struct net_device *dev,
+			   struct in_device *idev, u32 *itag)
+{
+	int err = fib_validate_source(skb, src, dst, dscp, oif, dev, idev,
+				      itag);
+	if (err < 0)
+		return -err;
+	return SKB_NOT_DROPPED_YET;
+}
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {

include/net/route.h

@@ -198,30 +198,35 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 	fl4->fl4_gre_key = gre_key;
 	return ip_route_output_key(net, fl4);
 }
-int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-			  u8 tos, struct net_device *dev,
-			  struct in_device *in_dev, u32 *itag);
-int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
-			 u8 tos, struct net_device *devin);
-int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
-		      u8 tos, struct net_device *devin,
-		      const struct sk_buff *hint);
-
-static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
-				 u8 tos, struct net_device *devin)
+
+enum skb_drop_reason
+ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+		      u8 tos, struct net_device *dev,
+		      struct in_device *in_dev, u32 *itag);
+enum skb_drop_reason
+ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+		     u8 tos, struct net_device *dev);
+enum skb_drop_reason
+ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+		  u8 tos, struct net_device *dev,
+		  const struct sk_buff *hint);
+
+static inline enum skb_drop_reason
+ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos,
+	       struct net_device *devin)
 {
-	int err;
+	enum skb_drop_reason reason;
 
 	rcu_read_lock();
-	err = ip_route_input_noref(skb, dst, src, tos, devin);
-	if (!err) {
+	reason = ip_route_input_noref(skb, dst, src, tos, devin);
+	if (!reason) {
 		skb_dst_force(skb);
 		if (!skb_dst(skb))
-			err = -EINVAL;
+			reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	}
 	rcu_read_unlock();
 
-	return err;
+	return reason;
 }
 
 void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,

include/net/sch_generic.h

@@ -1244,6 +1244,14 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_DROP;
 }
 
+static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch,
+				    struct sk_buff **to_free,
+				    enum skb_drop_reason reason)
+{
+	tcf_set_drop_reason(skb, reason);
+	return qdisc_drop(skb, sch, to_free);
+}
+
 static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
 				 struct sk_buff **to_free)
 {

include/net/tcp.h

@@ -388,10 +388,11 @@ enum tcp_tw_status {
 enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
 					      struct sk_buff *skb,
 					      const struct tcphdr *th,
-					      u32 *tw_isn);
+					      u32 *tw_isn,
+					      enum skb_drop_reason *drop_reason);
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req, bool fastopen,
-			   bool *lost_race);
+			   bool *lost_race, enum skb_drop_reason *drop_reason);
 enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 				       struct sk_buff *skb);
 void tcp_enter_loss(struct sock *sk);

include/uapi/linux/snmp.h

@@ -186,6 +186,8 @@ enum
 	LINUX_MIB_TIMEWAITKILLED,		/* TimeWaitKilled */
 	LINUX_MIB_PAWSACTIVEREJECTED,		/* PAWSActiveRejected */
 	LINUX_MIB_PAWSESTABREJECTED,		/* PAWSEstabRejected */
+	LINUX_MIB_PAWS_OLD_ACK,			/* PAWSOldAck */
+	LINUX_MIB_PAWS_TW_REJECTED,		/* PAWSTimewait */
 	LINUX_MIB_DELAYEDACKS,			/* DelayedACKs */
 	LINUX_MIB_DELAYEDACKLOCKED,		/* DelayedACKLocked */
 	LINUX_MIB_DELAYEDACKLOST,		/* DelayedACKLost */