tcp: add TCPMemoryPressuresChrono counter

DRAM supply shortage and poor memory pressure tracking in TCP
stack makes any change in SO_SNDBUF/SO_RCVBUF (or equivalent autotuning
limits) and tcp_mem[] quite hazardous.

TCPMemoryPressures SNMP counter is an indication of tcp_mem sysctl
limits being hit, but only tracking number of transitions.

If TCP stack behavior under stress was perfect :
1) It would maintain memory usage close to the limit.
2) Memory pressure state would be entered for short times.

We certainly prefer 100 events lasting 10ms compared to one event
lasting 200 seconds.

This patch adds a new SNMP counter tracking cumulative duration of
memory pressure events, given in ms units.

$ cat /proc/sys/net/ipv4/tcp_mem
3088    4117    6176
$ grep TCP /proc/net/sockstat
TCP: inuse 180 orphan 0 tw 2 alloc 234 mem 4140
$ nstat -n ; sleep 10 ; nstat |grep Pressure
TcpExtTCPMemoryPressures        1700
TcpExtTCPMemoryPressuresChrono  5209

v2: Used EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() as David
instructed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 5 insertions, 21 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 3467d9e89e7d..858891c36f94 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1080,6 +1080,7 @@ struct proto {
 	bool			(*stream_memory_free)(const struct sock *sk);
 	/* Memory pressure */
 	void			(*enter_memory_pressure)(struct sock *sk);
+	void			(*leave_memory_pressure)(struct sock *sk);
 	atomic_long_t		*memory_allocated;	/* Current allocated memory. */
 	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
 	/*
@@ -1088,7 +1089,7 @@ struct proto {
 	 * All the __sk_mem_schedule() is of this nature: accounting
 	 * is strict, actions are advisory and have some latency.
 	 */
-	int			*memory_pressure;
+	unsigned long		*memory_pressure;
 	long			*sysctl_mem;
 	int			*sysctl_wmem;
 	int			*sysctl_rmem;
@@ -1193,25 +1194,6 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
 	return !!*sk->sk_prot->memory_pressure;
 }
 
-static inline void sk_leave_memory_pressure(struct sock *sk)
-{
-	int *memory_pressure = sk->sk_prot->memory_pressure;
-
-	if (!memory_pressure)
-		return;
-
-	if (*memory_pressure)
-		*memory_pressure = 0;
-}
-
-static inline void sk_enter_memory_pressure(struct sock *sk)
-{
-	if (!sk->sk_prot->enter_memory_pressure)
-		return;
-
-	sk->sk_prot->enter_memory_pressure(sk);
-}
-
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
diff --git a/include/net/tcp.h b/include/net/tcp.h
index aec092560d9b..3ab677d11d02 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -276,7 +276,7 @@ extern int sysctl_tcp_pacing_ca_ratio;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
-extern int tcp_memory_pressure;
+extern unsigned long tcp_memory_pressure;
 
 /* optimized version of sk_under_memory_pressure() for TCP sockets */
 static inline bool tcp_under_memory_pressure(const struct sock *sk)
@@ -1320,6 +1320,7 @@ extern void tcp_openreq_init_rwin(struct request_sock *req,
 				  const struct dst_entry *dst);
 
 void tcp_enter_memory_pressure(struct sock *sk);
+void tcp_leave_memory_pressure(struct sock *sk);
 
 static inline int keepalive_intvl_when(const struct tcp_sock *tp)
 {
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 95cffcb21dfd..d85693295798 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -228,6 +228,7 @@ enum
 	LINUX_MIB_TCPABORTONLINGER,		/* TCPAbortOnLinger */
 	LINUX_MIB_TCPABORTFAILED,		/* TCPAbortFailed */
 	LINUX_MIB_TCPMEMORYPRESSURES,		/* TCPMemoryPressures */
+	LINUX_MIB_TCPMEMORYPRESSURESCHRONO,	/* TCPMemoryPressuresChrono */
 	LINUX_MIB_TCPSACKDISCARD,		/* TCPSACKDiscard */
 	LINUX_MIB_TCPDSACKIGNOREDOLD,		/* TCPSACKIgnoredOld */
 	LINUX_MIB_TCPDSACKIGNOREDNOUNDO,	/* TCPSACKIgnoredNoUndo */