tipc: add trace_events for tipc socket

The commit adds the new trace_events for TIPC socket object:

trace_tipc_sk_create()
trace_tipc_sk_poll()
trace_tipc_sk_sendmsg()
trace_tipc_sk_sendmcast()
trace_tipc_sk_sendstream()
trace_tipc_sk_filter_rcv()
trace_tipc_sk_advance_rx()
trace_tipc_sk_rej_msg()
trace_tipc_sk_drop_msg()
trace_tipc_sk_release()
trace_tipc_sk_shutdown()
trace_tipc_sk_overlimit1()
trace_tipc_sk_overlimit2()

Also, enables the traces for the following cases:
- When user creates a TIPC socket;
- When user calls poll() on TIPC socket;
- When user sends a dgram/mcast/stream message.
- When a message is put into the socket 'sk_receive_queue';
- When a message is released from the socket 'sk_receive_queue';
- When a message is rejected (e.g. due to no port, invalid, etc.);
- When a message is dropped (e.g. due to wrong message type);
- When socket is released;
- When socket is shutdown;
- When socket rcvq's allocation is overlimit (> 90%);
- When socket rcvq + bklq's allocation is overlimit (> 90%);
- When the 'TIPC_ERR_OVERLOAD/2' issue happens;

Note:
a) All the socket traces are designed to be able to trace on a specific
socket by either using the 'event filtering' feature on a known socket
'portid' value or the sysctl file:

/proc/sys/net/tipc/sk_filter

The file determines a 'tuple' for what socket should be traced:

(portid, sock type, name type, name lower, name upper)

where:
+ 'portid' is the socket portid generated at socket creating, can be
found in the trace outputs or the 'tipc socket list' command printouts;
+ 'sock type' is the socket type (1 = SOCK_TREAM, ...);
+ 'name type', 'name lower' and 'name upper' are the service name being
connected to or published by the socket.

Value '0' means 'ANY', the default tuple value is (0, 0, 0, 0, 0) i.e.
the traces happen for every sockets with no filter.

b) The 'tipc_sk_overlimit1/2' event is also a conditional trace_event
which happens when the socket receive queue (and backlog queue) is
about to be overloaded, when the queue allocation is > 90%. Then, when
the trace is enabled, the last skbs leading to the TIPC_ERR_OVERLOAD/2
issue can be traced.

The trace event is designed as an 'upper watermark' notification that
the other traces (e.g. 'tipc_sk_advance_rx' vs 'tipc_sk_filter_rcv') or
actions can be triggerred in the meanwhile to see what is going on with
the socket queue.

In addition, the 'trace_tipc_sk_dump()' is also placed at the
'TIPC_ERR_OVERLOAD/2' case, so the socket and last skb can be dumped
for post-analysis.

Acked-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 4 deletions

diff --git a/net/tipc/trace.h b/net/tipc/trace.h
index 535c8958651f..ebbfcd14627e 100644
--- a/net/tipc/trace.h
+++ b/net/tipc/trace.h
@@ -113,11 +113,14 @@ enum {
 			{(0xcbe),	"SYNCH_BEGIN_EVT"		},\
 			{(0xcee),	"SYNCH_END_EVT"			})
 
+extern unsigned long sysctl_tipc_sk_filter[5] __read_mostly;
+
 int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
 int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf);
 int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf);
 int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf);
 int tipc_node_dump(struct tipc_node *n, bool more, char *buf);
+bool tipc_sk_filtering(struct sock *sk);
 
 DECLARE_EVENT_CLASS(tipc_skb_class,
 
@@ -199,12 +202,33 @@ DECLARE_EVENT_CLASS(tipc_sk_class,
 		  __get_str(skb_buf), __get_str(buf))
 );
 
-#define DEFINE_SK_EVENT(name) \
-DEFINE_EVENT(tipc_sk_class, name, \
+#define DEFINE_SK_EVENT_FILTER(name) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+		 const char *header), \
+	TP_ARGS(sk, skb, dqueues, header), \
+	TP_CONDITION(tipc_sk_filtering(sk)))
+DEFINE_SK_EVENT_FILTER(tipc_sk_dump);
+DEFINE_SK_EVENT_FILTER(tipc_sk_create);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmcast);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmsg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendstream);
+DEFINE_SK_EVENT_FILTER(tipc_sk_poll);
+DEFINE_SK_EVENT_FILTER(tipc_sk_filter_rcv);
+DEFINE_SK_EVENT_FILTER(tipc_sk_advance_rx);
+DEFINE_SK_EVENT_FILTER(tipc_sk_rej_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_drop_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_release);
+DEFINE_SK_EVENT_FILTER(tipc_sk_shutdown);
+
+#define DEFINE_SK_EVENT_FILTER_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
 	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
 		 const char *header), \
-	TP_ARGS(sk, skb, dqueues, header))
-DEFINE_SK_EVENT(tipc_sk_dump);
+	TP_ARGS(sk, skb, dqueues, header), \
+	TP_CONDITION(tipc_sk_filtering(sk) && (cond)))
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit1, tipc_sk_overlimit1(sk, skb));
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit2, tipc_sk_overlimit2(sk, skb));
 
 DECLARE_EVENT_CLASS(tipc_link_class,