Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 4c4fde21 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp-tracepoints' 



Song Liu says:

====================
net: add a set of tracepoints to tcp stack

Changes from v1:

Fix build error (with ipv6 as ko) by adding EXPORT_TRACEPOINT_SYMBOL_GPL
for trace_tcp_send_reset.

These patches add the following tracepoints to tcp stack.

tcp_send_reset
tcp_receive_reset
tcp_destroy_sock
tcp_set_state

These tracepoints can be used to track TCP state changes. Such state
changes include but are not limited to: connection establish,
connection termination, tx and rx of RST, various retransmits.

Currently, we use the following kprobes to trace these events:

int kprobe__tcp_validate_incoming
int kprobe__tcp_send_active_reset
int kprobe__tcp_v4_send_reset
int kprobe__tcp_v6_send_reset
int kprobe__tcp_v4_destroy_sock
int kprobe__tcp_set_state
int kprobe__tcp_retransmit_skb

These tracepoints will help us simplify this work.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents bded4422 e8fce239

include/trace/events/tcp.h

+177 −4
Original line number Diff line number Diff line
@@ -9,15 +9,37 @@ 
#include <linux/tracepoint.h>

#include <net/ipv6.h>



TRACE_EVENT(tcp_retransmit_skb,

#define tcp_state_name(state)	{ state, #state }

#define show_tcp_state_name(val)			\

	__print_symbolic(val,				\

		tcp_state_name(TCP_ESTABLISHED),	\

		tcp_state_name(TCP_SYN_SENT),		\

		tcp_state_name(TCP_SYN_RECV),		\

		tcp_state_name(TCP_FIN_WAIT1),		\

		tcp_state_name(TCP_FIN_WAIT2),		\

		tcp_state_name(TCP_TIME_WAIT),		\

		tcp_state_name(TCP_CLOSE),		\

		tcp_state_name(TCP_CLOSE_WAIT),		\

		tcp_state_name(TCP_LAST_ACK),		\

		tcp_state_name(TCP_LISTEN),		\

		tcp_state_name(TCP_CLOSING),		\

		tcp_state_name(TCP_NEW_SYN_RECV))



	TP_PROTO(struct sock *sk, struct sk_buff *skb),

/*

 * tcp event with arguments sk and skb

 *

 * Note: this class requires a valid sk pointer; while skb pointer could

 *       be NULL.

 */

DECLARE_EVENT_CLASS(tcp_event_sk_skb,



	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),



	TP_ARGS(sk, skb),



	TP_STRUCT__entry(

		__field(void *, skbaddr)

		__field(void *, skaddr)

		__field(const void *, skbaddr)

		__field(const void *, skaddr)

		__field(__u16, sport)

		__field(__u16, dport)

		__array(__u8, saddr, 4)
@@ -64,6 +86,157 @@ TRACE_EVENT(tcp_retransmit_skb, 
		  __entry->saddr_v6, __entry->daddr_v6)

);



DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb,



	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),



	TP_ARGS(sk, skb)

);



/*

 * skb of trace_tcp_send_reset is the skb that caused RST. In case of

 * active reset, skb should be NULL

 */

DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset,



	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),



	TP_ARGS(sk, skb)

);



/*

 * tcp event with arguments sk

 *

 * Note: this class requires a valid sk pointer.

 */

DECLARE_EVENT_CLASS(tcp_event_sk,



	TP_PROTO(const struct sock *sk),



	TP_ARGS(sk),



	TP_STRUCT__entry(

		__field(const void *, skaddr)

		__field(__u16, sport)

		__field(__u16, dport)

		__array(__u8, saddr, 4)

		__array(__u8, daddr, 4)

		__array(__u8, saddr_v6, 16)

		__array(__u8, daddr_v6, 16)

	),



	TP_fast_assign(

		struct inet_sock *inet = inet_sk(sk);

		struct in6_addr *pin6;

		__be32 *p32;



		__entry->skaddr = sk;



		__entry->sport = ntohs(inet->inet_sport);

		__entry->dport = ntohs(inet->inet_dport);



		p32 = (__be32 *) __entry->saddr;

		*p32 = inet->inet_saddr;



		p32 = (__be32 *) __entry->daddr;

		*p32 =  inet->inet_daddr;



#if IS_ENABLED(CONFIG_IPV6)

		if (sk->sk_family == AF_INET6) {

			pin6 = (struct in6_addr *)__entry->saddr_v6;

			*pin6 = sk->sk_v6_rcv_saddr;

			pin6 = (struct in6_addr *)__entry->daddr_v6;

			*pin6 = sk->sk_v6_daddr;

		} else

#endif

		{

			pin6 = (struct in6_addr *)__entry->saddr_v6;

			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);

			pin6 = (struct in6_addr *)__entry->daddr_v6;

			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);

		}

	),



	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",

		  __entry->sport, __entry->dport,

		  __entry->saddr, __entry->daddr,

		  __entry->saddr_v6, __entry->daddr_v6)

);



DEFINE_EVENT(tcp_event_sk, tcp_receive_reset,



	TP_PROTO(const struct sock *sk),



	TP_ARGS(sk)

);



DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock,



	TP_PROTO(const struct sock *sk),



	TP_ARGS(sk)

);



TRACE_EVENT(tcp_set_state,



	TP_PROTO(const struct sock *sk, const int oldstate, const int newstate),



	TP_ARGS(sk, oldstate, newstate),



	TP_STRUCT__entry(

		__field(const void *, skaddr)

		__field(int, oldstate)

		__field(int, newstate)

		__field(__u16, sport)

		__field(__u16, dport)

		__array(__u8, saddr, 4)

		__array(__u8, daddr, 4)

		__array(__u8, saddr_v6, 16)

		__array(__u8, daddr_v6, 16)

	),



	TP_fast_assign(

		struct inet_sock *inet = inet_sk(sk);

		struct in6_addr *pin6;

		__be32 *p32;



		__entry->skaddr = sk;

		__entry->oldstate = oldstate;

		__entry->newstate = newstate;



		__entry->sport = ntohs(inet->inet_sport);

		__entry->dport = ntohs(inet->inet_dport);



		p32 = (__be32 *) __entry->saddr;

		*p32 = inet->inet_saddr;



		p32 = (__be32 *) __entry->daddr;

		*p32 =  inet->inet_daddr;



#if IS_ENABLED(CONFIG_IPV6)

		if (sk->sk_family == AF_INET6) {

			pin6 = (struct in6_addr *)__entry->saddr_v6;

			*pin6 = sk->sk_v6_rcv_saddr;

			pin6 = (struct in6_addr *)__entry->daddr_v6;

			*pin6 = sk->sk_v6_daddr;

		} else

#endif

		{

			pin6 = (struct in6_addr *)__entry->saddr_v6;

			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);

			pin6 = (struct in6_addr *)__entry->daddr_v6;

			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);

		}

	),



	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s",

		  __entry->sport, __entry->dport,

		  __entry->saddr, __entry->daddr,

		  __entry->saddr_v6, __entry->daddr_v6,

		  show_tcp_state_name(__entry->oldstate),

		  show_tcp_state_name(__entry->newstate))

);



#endif /* _TRACE_TCP_H */



/* This part must be outside protection */

net/core/net-traces.c

+2 −0
Original line number Diff line number Diff line
@@ -49,3 +49,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); 
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);



EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);



EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);

net/ipv4/tcp.c

+4 −0
Original line number Diff line number Diff line
@@ -282,6 +282,8 @@ 
#include <asm/ioctls.h>

#include <net/busy_poll.h>



#include <trace/events/tcp.h>



int sysctl_tcp_min_tso_segs __read_mostly = 2;



int sysctl_tcp_autocorking __read_mostly = 1;
@@ -2040,6 +2042,8 @@ void tcp_set_state(struct sock *sk, int state) 
{

	int oldstate = sk->sk_state;



	trace_tcp_set_state(sk, oldstate, state);



	switch (state) {

	case TCP_ESTABLISHED:

		if (oldstate != TCP_ESTABLISHED)

net/ipv4/tcp_input.c

+3 −0
Original line number Diff line number Diff line
@@ -75,6 +75,7 @@ 
#include <linux/ipsec.h>

#include <asm/unaligned.h>

#include <linux/errqueue.h>

#include <trace/events/tcp.h>



int sysctl_tcp_fack __read_mostly;

int sysctl_tcp_max_reordering __read_mostly = 300;
@@ -4010,6 +4011,8 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) 
/* When we get a reset we do this. */

void tcp_reset(struct sock *sk)

{

	trace_tcp_receive_reset(sk);



	/* We want the right error as BSD sees it (and indeed as we do). */

	switch (sk->sk_state) {

	case TCP_SYN_SENT:

net/ipv4/tcp_ipv4.c

+7 −1
Original line number Diff line number Diff line
@@ -85,6 +85,8 @@ 
#include <crypto/hash.h>

#include <linux/scatterlist.h>



#include <trace/events/tcp.h>



#ifdef CONFIG_TCP_MD5SIG

static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,

			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -701,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) 
	 * routing might fail in this case. No choice here, if we choose to force

	 * input interface, we will misroute in case of asymmetric route.

	 */

	if (sk)

	if (sk) {

		arg.bound_dev_if = sk->sk_bound_dev_if;

		trace_tcp_send_reset(sk, skb);

	}



	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=

		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -1865,6 +1869,8 @@ void tcp_v4_destroy_sock(struct sock *sk) 
{

	struct tcp_sock *tp = tcp_sk(sk);



	trace_tcp_destroy_sock(sk);



	tcp_clear_xmit_timers(sk);



	tcp_cleanup_congestion_control(sk);