tcp: add u32 counter in tcp_sock and an SNMP counter for PLB

A u32 counter is added to tcp_sock for counting the number of PLB
triggered rehashes for a TCP connection. An SNMP counter is also
added to count overall PLB triggered rehash events for a host. These
counters are hooked up to PLB implementation for DCTCP.

TCP_NLA_REHASH is added to SCM_TIMESTAMPING_OPT_STATS that reports
the rehash attempts triggered due to PLB or timeouts. This gives
a historical view of sustained congestion or timeouts experienced
by the TCP connection.

Signed-off-by: Mubashir Adnan Qureshi <mubashirq@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -423,6 +423,7 @@ struct tcp_sock {
 		u32		  probe_seq_start;
 		u32		  probe_seq_end;
 	} mtu_probe;
+	u32     plb_rehash;     /* PLB-triggered rehash attempts */
 	u32	mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
 			   * while socket was owned by user.
 			   */

include/uapi/linux/snmp.h

@@ -292,6 +292,7 @@ enum
 	LINUX_MIB_TCPDSACKIGNOREDDUBIOUS,	/* TCPDSACKIgnoredDubious */
 	LINUX_MIB_TCPMIGRATEREQSUCCESS,		/* TCPMigrateReqSuccess */
 	LINUX_MIB_TCPMIGRATEREQFAILURE,		/* TCPMigrateReqFailure */
+	LINUX_MIB_TCPPLBREHASH,			/* TCPPLBRehash */
 	__LINUX_MIB_MAX
 };
 

include/uapi/linux/tcp.h

@@ -315,6 +315,7 @@ enum {
 	TCP_NLA_BYTES_NOTSENT,	/* Bytes in write queue not yet sent */
 	TCP_NLA_EDT,		/* Earliest departure time (CLOCK_MONOTONIC) */
 	TCP_NLA_TTL,		/* TTL or hop limit of a packet received */
+	TCP_NLA_REHASH,         /* PLB and timeout triggered rehash attempts */
 };
 
 /* for TCP_MD5SIG socket option */

net/ipv4/proc.c

@@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS),
 	SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS),
 	SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE),
+	SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH),
 	SNMP_MIB_SENTINEL
 };
 

net/ipv4/tcp.c

@@ -3176,6 +3176,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->sacked_out = 0;
 	tp->tlp_high_seq = 0;
 	tp->last_oow_ack_time = 0;
+	tp->plb_rehash = 0;
 	/* There's a bubble in the pipe until at least the first ACK. */
 	tp->app_limited = ~0U;
 	tp->rack.mstamp = 0;
@@ -3973,6 +3974,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */
 		nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */
 		0;
 }
 
@@ -4049,6 +4051,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 		nla_put_u8(stats, TCP_NLA_TTL,
 			   tcp_skb_ttl_or_hop_limit(ack_skb));
 
+	nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash);
 	return stats;
 }
 

net/ipv4/tcp_plb.c

@@ -79,6 +79,8 @@ void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb)
 
 	sk_rethink_txhash(sk);
 	plb->consec_cong_rounds = 0;
+	tcp_sk(sk)->plb_rehash++;
+	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH);
 }
 EXPORT_SYMBOL_GPL(tcp_plb_check_rehash);