* [PATCH net-next 0/2] tcp: make trace of reset logic complete
@ 2024-03-11 2:41 Jason Xing
2024-03-11 2:41 ` [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters Jason Xing
2024-03-11 2:41 ` [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset Jason Xing
0 siblings, 2 replies; 8+ messages in thread
From: Jason Xing @ 2024-03-11 2:41 UTC (permalink / raw
To: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem
Cc: netdev, linux-trace-kernel, kerneljasonxing, Jason Xing
From: Jason Xing <kernelxing@tencent.com>
Before this, we miss some cases where the TCP layer could send rst but
we cannot trace it. So I decided to complete it :)
Jason Xing (2):
trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters
trace: tcp: fully support trace_tcp_send_reset
include/trace/events/tcp.h | 60 ++++++++++++++++++++++++++++++--------
net/ipv4/tcp_ipv4.c | 4 +--
net/ipv6/tcp_ipv6.c | 3 +-
3 files changed, 52 insertions(+), 15 deletions(-)
--
2.37.3
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters
2024-03-11 2:41 [PATCH net-next 0/2] tcp: make trace of reset logic complete Jason Xing
@ 2024-03-11 2:41 ` Jason Xing
2024-03-11 3:23 ` Ratheesh Kannoth
2024-03-11 2:41 ` [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset Jason Xing
1 sibling, 1 reply; 8+ messages in thread
From: Jason Xing @ 2024-03-11 2:41 UTC (permalink / raw
To: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem
Cc: netdev, linux-trace-kernel, kerneljasonxing, Jason Xing
From: Jason Xing <kernelxing@tencent.com>
Introducing entry_saddr and entry_daddr parameters in this macro
for later use can help us record the reverse 4-turple by analyzing
the 4-turple of the incoming skb when receiving.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
include/trace/events/tcp.h | 21 +++++++++++----------
1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 699dafd204ea..2495a1d579be 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -302,15 +302,15 @@ TRACE_EVENT(tcp_probe,
__entry->skbaddr, __entry->skaddr)
);
-#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \
+#define TP_STORE_ADDR_PORTS_SKB_V4(skb, entry_saddr, entry_daddr) \
do { \
const struct tcphdr *th = (const struct tcphdr *)skb->data; \
- struct sockaddr_in *v4 = (void *)__entry->saddr; \
+ struct sockaddr_in *v4 = (void *)entry_saddr; \
\
v4->sin_family = AF_INET; \
v4->sin_port = th->source; \
v4->sin_addr.s_addr = ip_hdr(skb)->saddr; \
- v4 = (void *)__entry->daddr; \
+ v4 = (void *)entry_daddr; \
v4->sin_family = AF_INET; \
v4->sin_port = th->dest; \
v4->sin_addr.s_addr = ip_hdr(skb)->daddr; \
@@ -318,29 +318,30 @@ TRACE_EVENT(tcp_probe,
#if IS_ENABLED(CONFIG_IPV6)
-#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \
+#define TP_STORE_ADDR_PORTS_SKB(skb, entry_saddr, entry_daddr) \
do { \
const struct iphdr *iph = ip_hdr(skb); \
\
if (iph->version == 6) { \
const struct tcphdr *th = (const struct tcphdr *)skb->data; \
- struct sockaddr_in6 *v6 = (void *)__entry->saddr; \
+ struct sockaddr_in6 *v6 = (void *)entry_saddr; \
\
v6->sin6_family = AF_INET6; \
v6->sin6_port = th->source; \
v6->sin6_addr = ipv6_hdr(skb)->saddr; \
- v6 = (void *)__entry->daddr; \
+ v6 = (void *)entry_daddr; \
v6->sin6_family = AF_INET6; \
v6->sin6_port = th->dest; \
v6->sin6_addr = ipv6_hdr(skb)->daddr; \
} else \
- TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb); \
+ TP_STORE_ADDR_PORTS_SKB_V4(skb, entry_saddr, \
+ entry_daddr); \
} while (0)
#else
-#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \
- TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)
+#define TP_STORE_ADDR_PORTS_SKB(skb, entry_saddr, entry_daddr) \
+ TP_STORE_ADDR_PORTS_SKB_V4(skb, entry_saddr, entry_daddr)
#endif
@@ -365,7 +366,7 @@ DECLARE_EVENT_CLASS(tcp_event_skb,
memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
- TP_STORE_ADDR_PORTS_SKB(__entry, skb);
+ TP_STORE_ADDR_PORTS_SKB(skb, __entry->saddr, __entry->daddr);
),
TP_printk("skbaddr=%p src=%pISpc dest=%pISpc",
--
2.37.3
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset
2024-03-11 2:41 [PATCH net-next 0/2] tcp: make trace of reset logic complete Jason Xing
2024-03-11 2:41 ` [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters Jason Xing
@ 2024-03-11 2:41 ` Jason Xing
2024-03-11 3:27 ` Ratheesh Kannoth
1 sibling, 1 reply; 8+ messages in thread
From: Jason Xing @ 2024-03-11 2:41 UTC (permalink / raw
To: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem
Cc: netdev, linux-trace-kernel, kerneljasonxing, Jason Xing
From: Jason Xing <kernelxing@tencent.com>
Prior to this patch, what we can see by enabling trace_tcp_send is
only happening under two circumstances:
1) active rst mode
2) non-active rst mode and based on the full socket
That means the inconsistency occurs if we use tcpdump and trace
simultaneously to see how rst happens.
It's necessary that we should take into other cases into considerations,
say:
1) time-wait socket
2) no socket
...
By parsing the incoming skb and reversing its 4-turple can
we know the exact 'flow' which might not exist.
Samples after applied this patch:
1. tcp_send_reset: skbaddr=XXX skaddr=XXX src=ip:port dest=ip:port
state=TCP_ESTABLISHED
2. tcp_send_reset: skbaddr=000...000 skaddr=XXX src=ip:port dest=ip:port
state=UNKNOWN
Note:
1) UNKNOWN means we cannot extract the right information from skb.
2) skbaddr/skaddr could be 0
Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
include/trace/events/tcp.h | 39 ++++++++++++++++++++++++++++++++++++--
net/ipv4/tcp_ipv4.c | 4 ++--
net/ipv6/tcp_ipv6.c | 3 ++-
3 files changed, 41 insertions(+), 5 deletions(-)
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 2495a1d579be..6c09d7941583 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -107,11 +107,46 @@ DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_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,
+TRACE_EVENT(tcp_send_reset,
TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
- TP_ARGS(sk, skb)
+ TP_ARGS(sk, skb),
+
+ TP_STRUCT__entry(
+ __field(const void *, skbaddr)
+ __field(const void *, skaddr)
+ __field(int, state)
+ __array(__u8, saddr, sizeof(struct sockaddr_in6))
+ __array(__u8, daddr, sizeof(struct sockaddr_in6))
+ ),
+
+ TP_fast_assign(
+ __entry->skbaddr = skb;
+ __entry->skaddr = sk;
+ /* Zero means unknown state. */
+ __entry->state = sk ? sk->sk_state : 0;
+
+ memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+ memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+ if (sk && sk_fullsock(sk)) {
+ const struct inet_sock *inet = inet_sk(sk);
+
+ TP_STORE_ADDR_PORTS(__entry, inet, sk);
+ } else {
+ /*
+ * We should reverse the 4-turple of skb, so later
+ * it can print the right flow direction of rst.
+ */
+ TP_STORE_ADDR_PORTS_SKB(skb, entry->daddr, entry->saddr);
+ }
+ ),
+
+ TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s",
+ __entry->skbaddr, __entry->skaddr,
+ __entry->saddr, __entry->daddr,
+ __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN")
);
/*
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a22ee5838751..d5c4a969c066 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -868,10 +868,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
*/
if (sk) {
arg.bound_dev_if = sk->sk_bound_dev_if;
- if (sk_fullsock(sk))
- trace_tcp_send_reset(sk, skb);
}
+ 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));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3f4cba49e9ee..8e9c59b6c00c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1113,7 +1113,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
if (sk) {
oif = sk->sk_bound_dev_if;
if (sk_fullsock(sk)) {
- trace_tcp_send_reset(sk, skb);
if (inet6_test_bit(REPFLOW, sk))
label = ip6_flowlabel(ipv6h);
priority = READ_ONCE(sk->sk_priority);
@@ -1129,6 +1128,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
label = ip6_flowlabel(ipv6h);
}
+ trace_tcp_send_reset(sk, skb);
+
tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
ipv6_get_dsfield(ipv6h), label, priority, txhash,
&key);
--
2.37.3
^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters
2024-03-11 2:41 ` [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters Jason Xing
@ 2024-03-11 3:23 ` Ratheesh Kannoth
2024-03-11 3:28 ` Jason Xing
0 siblings, 1 reply; 8+ messages in thread
From: Ratheesh Kannoth @ 2024-03-11 3:23 UTC (permalink / raw
To: Jason Xing
Cc: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem, netdev, linux-trace-kernel, Jason Xing
On 2024-03-11 at 08:11:03, Jason Xing (kerneljasonxing@gmail.com) wrote:
> From: Jason Xing <kernelxing@tencent.com>
>
> Introducing entry_saddr and entry_daddr parameters in this macro
> for later use can help us record the reverse 4-turple by analyzing
Did you mean tuple ? what is turple ?
> the 4-turple of the incoming skb when receiving.
>
> Signed-off-by: Jason Xing <kernelxing@tencent.com>
> ---
> include/trace/events/tcp.h | 21 +++++++++++----------
> 1 file changed, 11 insertions(+), 10 deletions(-)
>
> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
> index 699dafd204ea..2495a1d579be 100644
> --- a/include/trace/events/tcp.h
> +++ b/include/trace/events/tcp.h
> @@ -302,15 +302,15 @@ TRACE_EVENT(tcp_probe,
> __entry->skbaddr, __entry->skaddr)
> );
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset
2024-03-11 2:41 ` [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset Jason Xing
@ 2024-03-11 3:27 ` Ratheesh Kannoth
2024-03-11 5:00 ` Jason Xing
0 siblings, 1 reply; 8+ messages in thread
From: Ratheesh Kannoth @ 2024-03-11 3:27 UTC (permalink / raw
To: Jason Xing
Cc: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem, netdev, linux-trace-kernel, Jason Xing
On 2024-03-11 at 08:11:04, Jason Xing (kerneljasonxing@gmail.com) wrote:
> From: Jason Xing <kernelxing@tencent.com>
>
> Prior to this patch, what we can see by enabling trace_tcp_send is
> only happening under two circumstances:
> 1) active rst mode
> 2) non-active rst mode and based on the full socket
>
> That means the inconsistency occurs if we use tcpdump and trace
> simultaneously to see how rst happens.
>
> It's necessary that we should take into other cases into considerations,
> say:
> 1) time-wait socket
> 2) no socket
> ...
>
> By parsing the incoming skb and reversing its 4-turple can
> we know the exact 'flow' which might not exist.
>
> Samples after applied this patch:
> 1. tcp_send_reset: skbaddr=XXX skaddr=XXX src=ip:port dest=ip:port
> state=TCP_ESTABLISHED
> 2. tcp_send_reset: skbaddr=000...000 skaddr=XXX src=ip:port dest=ip:port
> state=UNKNOWN
> Note:
> 1) UNKNOWN means we cannot extract the right information from skb.
> 2) skbaddr/skaddr could be 0
>
> Signed-off-by: Jason Xing <kernelxing@tencent.com>
> ---
> include/trace/events/tcp.h | 39 ++++++++++++++++++++++++++++++++++++--
> net/ipv4/tcp_ipv4.c | 4 ++--
> net/ipv6/tcp_ipv6.c | 3 ++-
> 3 files changed, 41 insertions(+), 5 deletions(-)
>
> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
> index 2495a1d579be..6c09d7941583 100644
> --- a/include/trace/events/tcp.h
> +++ b/include/trace/events/tcp.h
> @@ -107,11 +107,46 @@ DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_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,
> +TRACE_EVENT(tcp_send_reset,
>
> TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
>
> - TP_ARGS(sk, skb)
> + TP_ARGS(sk, skb),
> +
> + TP_STRUCT__entry(
> + __field(const void *, skbaddr)
> + __field(const void *, skaddr)
> + __field(int, state)
> + __array(__u8, saddr, sizeof(struct sockaddr_in6))
> + __array(__u8, daddr, sizeof(struct sockaddr_in6))
> + ),
> +
> + TP_fast_assign(
> + __entry->skbaddr = skb;
> + __entry->skaddr = sk;
> + /* Zero means unknown state. */
> + __entry->state = sk ? sk->sk_state : 0;
> +
> + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
> + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
> +
> + if (sk && sk_fullsock(sk)) {
> + const struct inet_sock *inet = inet_sk(sk);
> +
> + TP_STORE_ADDR_PORTS(__entry, inet, sk);
> + } else {
> + /*
> + * We should reverse the 4-turple of skb, so later
> + * it can print the right flow direction of rst.
> + */
> + TP_STORE_ADDR_PORTS_SKB(skb, entry->daddr, entry->saddr);
> + }
> + ),
> +
> + TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s",
Could you consider using %px ? is it permitted ? it will be easy to track skb.
> + __entry->skbaddr, __entry->skaddr,
> + __entry->saddr, __entry->daddr,
> + __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN")
> );
>
> /*
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index a22ee5838751..d5c4a969c066 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -868,10 +868,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
> */
> if (sk) {
> arg.bound_dev_if = sk->sk_bound_dev_if;
> - if (sk_fullsock(sk))
> - trace_tcp_send_reset(sk, skb);
> }
>
> + 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));
>
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index 3f4cba49e9ee..8e9c59b6c00c 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1113,7 +1113,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
> if (sk) {
> oif = sk->sk_bound_dev_if;
> if (sk_fullsock(sk)) {
> - trace_tcp_send_reset(sk, skb);
> if (inet6_test_bit(REPFLOW, sk))
> label = ip6_flowlabel(ipv6h);
> priority = READ_ONCE(sk->sk_priority);
> @@ -1129,6 +1128,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
> label = ip6_flowlabel(ipv6h);
> }
>
> + trace_tcp_send_reset(sk, skb);
> +
> tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
> ipv6_get_dsfield(ipv6h), label, priority, txhash,
> &key);
> --
> 2.37.3
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters
2024-03-11 3:23 ` Ratheesh Kannoth
@ 2024-03-11 3:28 ` Jason Xing
0 siblings, 0 replies; 8+ messages in thread
From: Jason Xing @ 2024-03-11 3:28 UTC (permalink / raw
To: Ratheesh Kannoth
Cc: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem, netdev, linux-trace-kernel, Jason Xing
On Mon, Mar 11, 2024 at 11:23 AM Ratheesh Kannoth <rkannoth@marvell.com> wrote:
>
> On 2024-03-11 at 08:11:03, Jason Xing (kerneljasonxing@gmail.com) wrote:
> > From: Jason Xing <kernelxing@tencent.com>
> >
> > Introducing entry_saddr and entry_daddr parameters in this macro
> > for later use can help us record the reverse 4-turple by analyzing
> Did you mean tuple ? what is turple ?
>
> > the 4-turple of the incoming skb when receiving.
Oh, thanks for reminding me. I always remember the wrong word... Yes,
it is tuple.
Thanks,
Jason
> >
> > Signed-off-by: Jason Xing <kernelxing@tencent.com>
> > ---
> > include/trace/events/tcp.h | 21 +++++++++++----------
> > 1 file changed, 11 insertions(+), 10 deletions(-)
> >
> > diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
> > index 699dafd204ea..2495a1d579be 100644
> > --- a/include/trace/events/tcp.h
> > +++ b/include/trace/events/tcp.h
> > @@ -302,15 +302,15 @@ TRACE_EVENT(tcp_probe,
> > __entry->skbaddr, __entry->skaddr)
> > );
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset
2024-03-11 3:27 ` Ratheesh Kannoth
@ 2024-03-11 5:00 ` Jason Xing
2024-03-11 5:09 ` Ratheesh Kannoth
0 siblings, 1 reply; 8+ messages in thread
From: Jason Xing @ 2024-03-11 5:00 UTC (permalink / raw
To: Ratheesh Kannoth
Cc: edumazet, mhiramat, mathieu.desnoyers, rostedt, kuba, pabeni,
davem, netdev, linux-trace-kernel, Jason Xing
On Mon, Mar 11, 2024 at 11:27 AM Ratheesh Kannoth <rkannoth@marvell.com> wrote:
>
> On 2024-03-11 at 08:11:04, Jason Xing (kerneljasonxing@gmail.com) wrote:
> > From: Jason Xing <kernelxing@tencent.com>
> >
> > Prior to this patch, what we can see by enabling trace_tcp_send is
> > only happening under two circumstances:
> > 1) active rst mode
> > 2) non-active rst mode and based on the full socket
> >
> > That means the inconsistency occurs if we use tcpdump and trace
> > simultaneously to see how rst happens.
> >
> > It's necessary that we should take into other cases into considerations,
> > say:
> > 1) time-wait socket
> > 2) no socket
> > ...
> >
> > By parsing the incoming skb and reversing its 4-turple can
> > we know the exact 'flow' which might not exist.
> >
> > Samples after applied this patch:
> > 1. tcp_send_reset: skbaddr=XXX skaddr=XXX src=ip:port dest=ip:port
> > state=TCP_ESTABLISHED
> > 2. tcp_send_reset: skbaddr=000...000 skaddr=XXX src=ip:port dest=ip:port
> > state=UNKNOWN
> > Note:
> > 1) UNKNOWN means we cannot extract the right information from skb.
> > 2) skbaddr/skaddr could be 0
> >
> > Signed-off-by: Jason Xing <kernelxing@tencent.com>
> > ---
> > include/trace/events/tcp.h | 39 ++++++++++++++++++++++++++++++++++++--
> > net/ipv4/tcp_ipv4.c | 4 ++--
> > net/ipv6/tcp_ipv6.c | 3 ++-
> > 3 files changed, 41 insertions(+), 5 deletions(-)
> >
> > diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
> > index 2495a1d579be..6c09d7941583 100644
> > --- a/include/trace/events/tcp.h
> > +++ b/include/trace/events/tcp.h
> > @@ -107,11 +107,46 @@ DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_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,
> > +TRACE_EVENT(tcp_send_reset,
> >
> > TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
> >
> > - TP_ARGS(sk, skb)
> > + TP_ARGS(sk, skb),
> > +
> > + TP_STRUCT__entry(
> > + __field(const void *, skbaddr)
> > + __field(const void *, skaddr)
> > + __field(int, state)
> > + __array(__u8, saddr, sizeof(struct sockaddr_in6))
> > + __array(__u8, daddr, sizeof(struct sockaddr_in6))
> > + ),
> > +
> > + TP_fast_assign(
> > + __entry->skbaddr = skb;
> > + __entry->skaddr = sk;
> > + /* Zero means unknown state. */
> > + __entry->state = sk ? sk->sk_state : 0;
> > +
> > + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
> > + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
> > +
> > + if (sk && sk_fullsock(sk)) {
> > + const struct inet_sock *inet = inet_sk(sk);
> > +
> > + TP_STORE_ADDR_PORTS(__entry, inet, sk);
> > + } else {
> > + /*
> > + * We should reverse the 4-turple of skb, so later
> > + * it can print the right flow direction of rst.
> > + */
> > + TP_STORE_ADDR_PORTS_SKB(skb, entry->daddr, entry->saddr);
> > + }
> > + ),
> > +
> > + TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s",
> Could you consider using %px ? is it permitted ? it will be easy to track skb.
I prefer not to use %px because we cannot make use of the real address
of skb. Besides, using %px would leak kernel addresses.
Here is the Documentation (see Documentation/core-api/printk-formats.rst):
"Pointers printed without a specifier extension (i.e unadorned %p) are
hashed to give a unique identifier without leaking kernel addresses to user
space."
Perhaps, that's the reason why all the tracepoints didn't print in %px format:)
Thanks,
Jason
>
> > + __entry->skbaddr, __entry->skaddr,
> > + __entry->saddr, __entry->daddr,
> > + __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN")
> > );
> >
> > /*
> > diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> > index a22ee5838751..d5c4a969c066 100644
> > --- a/net/ipv4/tcp_ipv4.c
> > +++ b/net/ipv4/tcp_ipv4.c
> > @@ -868,10 +868,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
> > */
> > if (sk) {
> > arg.bound_dev_if = sk->sk_bound_dev_if;
> > - if (sk_fullsock(sk))
> > - trace_tcp_send_reset(sk, skb);
> > }
> >
> > + 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));
> >
> > diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> > index 3f4cba49e9ee..8e9c59b6c00c 100644
> > --- a/net/ipv6/tcp_ipv6.c
> > +++ b/net/ipv6/tcp_ipv6.c
> > @@ -1113,7 +1113,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
> > if (sk) {
> > oif = sk->sk_bound_dev_if;
> > if (sk_fullsock(sk)) {
> > - trace_tcp_send_reset(sk, skb);
> > if (inet6_test_bit(REPFLOW, sk))
> > label = ip6_flowlabel(ipv6h);
> > priority = READ_ONCE(sk->sk_priority);
> > @@ -1129,6 +1128,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
> > label = ip6_flowlabel(ipv6h);
> > }
> >
> > + trace_tcp_send_reset(sk, skb);
> > +
> > tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
> > ipv6_get_dsfield(ipv6h), label, priority, txhash,
> > &key);
> > --
> > 2.37.3
> >
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset
2024-03-11 5:00 ` Jason Xing
@ 2024-03-11 5:09 ` Ratheesh Kannoth
0 siblings, 0 replies; 8+ messages in thread
From: Ratheesh Kannoth @ 2024-03-11 5:09 UTC (permalink / raw
To: Jason Xing
Cc: edumazet@google.com, mhiramat@kernel.org,
mathieu.desnoyers@efficios.com, rostedt@goodmis.org,
kuba@kernel.org, pabeni@redhat.com, davem@davemloft.net,
netdev@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
Jason Xing
> From: Jason Xing <kerneljasonxing@gmail.com>
> Sent: Monday, March 11, 2024 10:30 AM
> To: Ratheesh Kannoth <rkannoth@marvell.com>
> Cc: edumazet@google.com; mhiramat@kernel.org;
> mathieu.desnoyers@efficios.com; rostedt@goodmis.org; kuba@kernel.org;
> pabeni@redhat.com; davem@davemloft.net; netdev@vger.kernel.org; linux-
> trace-kernel@vger.kernel.org; Jason Xing <kernelxing@tencent.com>
> Subject: [EXTERNAL] Re: [PATCH net-next 2/2] trace: tcp: fully support
> trace_tcp_send_reset
>
> > > + ),
> > > +
> > > + TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc
> > > + state=%s",
> > Could you consider using %px ? is it permitted ? it will be easy to track skb.
>
> I prefer not to use %px because we cannot make use of the real address of
> skb. Besides, using %px would leak kernel addresses.
>
> Here is the Documentation (see Documentation/core-api/printk-formats.rst):
> "Pointers printed without a specifier extension (i.e unadorned %p) are
> hashed to give a unique identifier without leaking kernel addresses to user
> space."
>
> Perhaps, that's the reason why all the tracepoints didn't print in %px format:)
>
ACK, I understand that. In offload cases, or in mostly in IOVA space, we often end up changing this locally to %px to debug and track skb.
That is why I asked the question.
> Thanks,
> Jason
>
> >
> > > + __entry->skbaddr, __entry->skaddr,
> > > + __entry->saddr, __entry->daddr,
> > > + __entry->state ? show_tcp_state_name(__entry->state)
> > > + : "UNKNOWN")
> > > );
> > >
> > > /*
> > > diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index
> > > a22ee5838751..d5c4a969c066 100644
> > > --- a/net/ipv4/tcp_ipv4.c
> > > +++ b/net/ipv4/tcp_ipv4.c
> > > @@ -868,10 +868,10 @@ static void tcp_v4_send_reset(const struct sock
> *sk, struct sk_buff *skb)
> > > */
> > > if (sk) {
> > > arg.bound_dev_if = sk->sk_bound_dev_if;
> > > - if (sk_fullsock(sk))
> > > - trace_tcp_send_reset(sk, skb);
> > > }
> > >
> > > + 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));
> > >
> > > diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index
> > > 3f4cba49e9ee..8e9c59b6c00c 100644
> > > --- a/net/ipv6/tcp_ipv6.c
> > > +++ b/net/ipv6/tcp_ipv6.c
> > > @@ -1113,7 +1113,6 @@ static void tcp_v6_send_reset(const struct sock
> *sk, struct sk_buff *skb)
> > > if (sk) {
> > > oif = sk->sk_bound_dev_if;
> > > if (sk_fullsock(sk)) {
> > > - trace_tcp_send_reset(sk, skb);
> > > if (inet6_test_bit(REPFLOW, sk))
> > > label = ip6_flowlabel(ipv6h);
> > > priority = READ_ONCE(sk->sk_priority); @@
> > > -1129,6 +1128,8 @@ static void tcp_v6_send_reset(const struct sock *sk,
> struct sk_buff *skb)
> > > label = ip6_flowlabel(ipv6h);
> > > }
> > >
> > > + trace_tcp_send_reset(sk, skb);
> > > +
> > > tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
> > > ipv6_get_dsfield(ipv6h), label, priority, txhash,
> > > &key);
> > > --
> > > 2.37.3
> > >
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2024-03-11 5:09 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-03-11 2:41 [PATCH net-next 0/2] tcp: make trace of reset logic complete Jason Xing
2024-03-11 2:41 ` [PATCH net-next 1/2] trace: adjust TP_STORE_ADDR_PORTS_SKB() parameters Jason Xing
2024-03-11 3:23 ` Ratheesh Kannoth
2024-03-11 3:28 ` Jason Xing
2024-03-11 2:41 ` [PATCH net-next 2/2] trace: tcp: fully support trace_tcp_send_reset Jason Xing
2024-03-11 3:27 ` Ratheesh Kannoth
2024-03-11 5:00 ` Jason Xing
2024-03-11 5:09 ` Ratheesh Kannoth
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).