* [MPTCP][PATCH v2 mptcp-next 0/5] add tracepoints @ 2021-03-24 8:51 Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Geliang Tang 0 siblings, 1 reply; 10+ messages in thread From: Geliang Tang @ 2021-03-24 8:51 UTC (permalink / raw) To: mptcp, mptcp; +Cc: Geliang Tang v2: - add two new patches. - update the patch set as Paolo suggested. This patchset addressed issues 131, replace some/most pr_debug with trace events. As Paolo suggested, we should add the tracepoints at "the packet scheduler and the mapping status" first. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/131 Geliang Tang (5): mptcp: export mptcp_subflow_active mptcp: add tracepoint in mptcp_subflow_get_send mptcp: add tracepoint in get_mapping_status mptcp: add tracepoint in ack_update_msk mptcp: add tracepoint in subflow_check_data_avail include/trace/events/mptcp.h | 151 +++++++++++++++++++++++++++++++++++ net/mptcp/options.c | 3 + net/mptcp/protocol.c | 6 +- net/mptcp/protocol.h | 1 + net/mptcp/subflow.c | 10 +-- 5 files changed, 164 insertions(+), 7 deletions(-) create mode 100644 include/trace/events/mptcp.h -- 2.30.2 ^ permalink raw reply [flat|nested] 10+ messages in thread
* [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active 2021-03-24 8:51 [MPTCP][PATCH v2 mptcp-next 0/5] add tracepoints Geliang Tang @ 2021-03-24 8:51 ` Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Geliang Tang 2021-03-29 13:52 ` [MPTCP] [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Paolo Abeni 0 siblings, 2 replies; 10+ messages in thread From: Geliang Tang @ 2021-03-24 8:51 UTC (permalink / raw) To: mptcp, mptcp; +Cc: Geliang Tang This patch exported the static function mptcp_subflow_active. Signed-off-by: Geliang Tang <geliangtang@gmail.com> --- net/mptcp/protocol.c | 2 +- net/mptcp/protocol.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9d7e7e13fba8..3ad236689480 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -399,7 +399,7 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; } -static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) +bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 14f0114be17a..20770fe39ea5 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -538,6 +538,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); void mptcp_info2sockaddr(const struct mptcp_addr_info *info, struct sockaddr_storage *addr, unsigned short family); +bool mptcp_subflow_active(struct mptcp_subflow_context *subflow); static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) -- 2.30.2 ^ permalink raw reply related [flat|nested] 10+ messages in thread
* [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Geliang Tang @ 2021-03-24 8:51 ` Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Geliang Tang 2021-03-29 13:52 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Paolo Abeni 2021-03-29 13:52 ` [MPTCP] [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Paolo Abeni 1 sibling, 2 replies; 10+ messages in thread From: Geliang Tang @ 2021-03-24 8:51 UTC (permalink / raw) To: mptcp, mptcp; +Cc: Geliang Tang, Paolo Abeni This patch added a tracepoint in the packet scheduler function mptcp_subflow_get_send(). Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Geliang Tang <geliangtang@gmail.com> --- include/trace/events/mptcp.h | 43 ++++++++++++++++++++++++++++++++++++ net/mptcp/protocol.c | 4 ++++ 2 files changed, 47 insertions(+) create mode 100644 include/trace/events/mptcp.h diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h new file mode 100644 index 000000000000..06908ea6afb4 --- /dev/null +++ b/include/trace/events/mptcp.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mptcp + +#if !defined(_TRACE_MPTCP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MPTCP_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(mptcp_subflow_get_send, + + TP_PROTO(struct mptcp_subflow_context *subflow, struct sock *ssk), + + TP_ARGS(subflow, ssk), + + TP_STRUCT__entry( + __field(bool, active) + __field(bool, free) + __field(u32, snd_wnd) + __field(u32, pace) + __field(u8, backup) + __field(u64, ratio) + ), + + TP_fast_assign( + __entry->active = mptcp_subflow_active(subflow); + __entry->free = sk_stream_memory_free(subflow->tcp_sock); + __entry->snd_wnd = tcp_sk(ssk)->snd_wnd; + __entry->pace = ssk->sk_pacing_rate; + __entry->backup = subflow->backup; + __entry->ratio = div_u64((u64)ssk->sk_wmem_queued << 32, __entry->pace); + ), + + TP_printk("active=%d free=%d snd_wnd=%u pace=%u backup=%u ratio=%llu", + __entry->active, __entry->free, + __entry->snd_wnd, __entry->pace, + __entry->backup, __entry->ratio) +); + +#endif /* _TRACE_MPTCP_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3ad236689480..0265b8be0f84 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -25,6 +25,9 @@ #include "protocol.h" #include "mib.h" +#define CREATE_TRACE_POINTS +#include <trace/events/mptcp.h> + #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; @@ -1394,6 +1397,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); + trace_mptcp_subflow_get_send(subflow, ssk); if (!mptcp_subflow_active(subflow)) continue; -- 2.30.2 ^ permalink raw reply related [flat|nested] 10+ messages in thread
* [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Geliang Tang @ 2021-03-24 8:51 ` Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Geliang Tang 2021-03-29 14:00 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Paolo Abeni 2021-03-29 13:52 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Paolo Abeni 1 sibling, 2 replies; 10+ messages in thread From: Geliang Tang @ 2021-03-24 8:51 UTC (permalink / raw) To: mptcp, mptcp; +Cc: Geliang Tang, Paolo Abeni This patch added a tracepoint in the mapping status function get_mapping_status() to dump every mpext field. Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Geliang Tang <geliangtang@gmail.com> --- include/trace/events/mptcp.h | 54 ++++++++++++++++++++++++++++++++++++ net/mptcp/subflow.c | 6 ++-- 2 files changed, 57 insertions(+), 3 deletions(-) diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 06908ea6afb4..503a6098909d 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -37,6 +37,60 @@ TRACE_EVENT(mptcp_subflow_get_send, __entry->backup, __entry->ratio) ); +DECLARE_EVENT_CLASS(mptcp_dump_mpext, + + TP_PROTO(struct mptcp_ext *mpext), + + TP_ARGS(mpext), + + TP_STRUCT__entry( + __field(u64, data_ack) + __field(u32, data_ack32) + __field(u64, data_seq) + __field(u32, subflow_seq) + __field(u16, data_len) + __field(u8, use_map) + __field(u8, dsn64) + __field(u8, data_fin) + __field(u8, use_ack) + __field(u8, ack64) + __field(u8, mpc_map) + __field(u8, frozen) + __field(u8, reset_transient) + __field(u8, reset_reason) + ), + + TP_fast_assign( + __entry->data_ack = mpext->data_ack; + __entry->data_ack32 = mpext->data_ack32; + __entry->data_seq = mpext->data_seq; + __entry->subflow_seq = mpext->subflow_seq; + __entry->data_len = mpext->data_len; + __entry->use_map = mpext->use_map; + __entry->dsn64 = mpext->dsn64; + __entry->data_fin = mpext->data_fin; + __entry->use_ack = mpext->use_ack; + __entry->ack64 = mpext->ack64; + __entry->mpc_map = mpext->mpc_map; + __entry->frozen = mpext->frozen; + __entry->reset_transient = mpext->reset_transient; + __entry->reset_reason = mpext->reset_reason; + ), + + TP_printk("data_ack=%llu data_ack32=%u data_seq=%llu subflow_seq=%u data_len=%u use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u", + __entry->data_ack, __entry->data_ack32, + __entry->data_seq, __entry->subflow_seq, + __entry->data_len, __entry->use_map, + __entry->dsn64, __entry->data_fin, + __entry->use_ack, __entry->ack64, + __entry->mpc_map, __entry->frozen, + __entry->reset_transient, __entry->reset_reason) +); + +DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, + TP_PROTO(struct mptcp_ext *mpext), + TP_ARGS(mpext)); + #endif /* _TRACE_MPTCP_H */ /* This part must be outside protection */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 5fc3cada11dd..dc08e5de807e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -25,6 +25,8 @@ #include "protocol.h" #include "mib.h" +#include <trace/events/mptcp.h> + static void mptcp_subflow_ops_undo_override(struct sock *ssk); static void SUBFLOW_REQ_INC_STATS(struct request_sock *req, @@ -853,9 +855,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, goto validate_seq; } - pr_debug("seq=%llu is64=%d ssn=%u data_len=%u data_fin=%d", - mpext->data_seq, mpext->dsn64, mpext->subflow_seq, - mpext->data_len, mpext->data_fin); + trace_get_mapping_status(mpext); data_len = mpext->data_len; if (data_len == 0) { -- 2.30.2 ^ permalink raw reply related [flat|nested] 10+ messages in thread
* [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Geliang Tang @ 2021-03-24 8:51 ` Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 5/5] mptcp: add tracepoint in subflow_check_data_avail Geliang Tang 2021-03-29 14:03 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Paolo Abeni 2021-03-29 14:00 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Paolo Abeni 1 sibling, 2 replies; 10+ messages in thread From: Geliang Tang @ 2021-03-24 8:51 UTC (permalink / raw) To: mptcp, mptcp; +Cc: Geliang Tang, Paolo Abeni This patch added a tracepoint in ack_update_msk() to track the incoming data_ack and window/snd_una updates. Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Geliang Tang <geliangtang@gmail.com> --- include/trace/events/mptcp.h | 25 +++++++++++++++++++++++++ net/mptcp/options.c | 3 +++ 2 files changed, 28 insertions(+) diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 503a6098909d..2b8ae5e81cd1 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -91,6 +91,31 @@ DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext)); +TRACE_EVENT(ack_update_msk, + + TP_PROTO(u64 data_ack, u64 old_snd_una, u64 new_snd_una, u64 new_wnd_end), + + TP_ARGS(data_ack, old_snd_una, new_snd_una, new_wnd_end), + + TP_STRUCT__entry( + __field(u64, data_ack) + __field(u64, old_snd_una) + __field(u64, new_snd_una) + __field(u64, new_wnd_end) + ), + + TP_fast_assign( + __entry->data_ack = data_ack; + __entry->old_snd_una = old_snd_una; + __entry->new_snd_una = new_snd_una; + __entry->new_wnd_end = new_wnd_end; + ), + + TP_printk("data_ack=%llu old_snd_una=%llu new_snd_una=%llu new_wnd_end=%llu", + __entry->data_ack, __entry->old_snd_una, + __entry->new_snd_una, __entry->new_wnd_end) +); + #endif /* _TRACE_MPTCP_H */ /* This part must be outside protection */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c7eb61d0564c..87bd1bfde964 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -13,6 +13,8 @@ #include "protocol.h" #include "mib.h" +#include <trace/events/mptcp.h> + static bool mptcp_cap_flag_sha256(u8 flags) { return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; @@ -942,6 +944,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_data_acked(sk); } mptcp_data_unlock(sk); + trace_ack_update_msk(mp_opt->data_ack, old_snd_una, new_snd_una, new_wnd_end); } bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit) -- 2.30.2 ^ permalink raw reply related [flat|nested] 10+ messages in thread
* [MPTCP][PATCH v2 mptcp-next 5/5] mptcp: add tracepoint in subflow_check_data_avail 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Geliang Tang @ 2021-03-24 8:51 ` Geliang Tang 2021-03-29 14:03 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Paolo Abeni 1 sibling, 0 replies; 10+ messages in thread From: Geliang Tang @ 2021-03-24 8:51 UTC (permalink / raw) To: mptcp, mptcp; +Cc: Geliang Tang, Paolo Abeni This patch added a tracepoint in subflow_check_data_avail() to show the mapping status. Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Geliang Tang <geliangtang@gmail.com> --- include/trace/events/mptcp.h | 29 +++++++++++++++++++++++++++++ net/mptcp/subflow.c | 4 +--- 2 files changed, 30 insertions(+), 3 deletions(-) diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 2b8ae5e81cd1..5571c45c61f2 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -7,6 +7,14 @@ #include <linux/tracepoint.h> +#define show_mapping_status(status) \ + __print_symbolic(status, \ + { 0, "MAPPING_OK" }, \ + { 1, "MAPPING_INVALID" }, \ + { 2, "MAPPING_EMPTY" }, \ + { 3, "MAPPING_DATA_FIN" }, \ + { 4, "MAPPING_DUMMY" }) + TRACE_EVENT(mptcp_subflow_get_send, TP_PROTO(struct mptcp_subflow_context *subflow, struct sock *ssk), @@ -116,6 +124,27 @@ TRACE_EVENT(ack_update_msk, __entry->new_snd_una, __entry->new_wnd_end) ); +TRACE_EVENT(subflow_check_data_avail, + + TP_PROTO(__u8 status, struct sk_buff *skb), + + TP_ARGS(status, skb), + + TP_STRUCT__entry( + __field(u8, status) + __field(const void *, skb) + ), + + TP_fast_assign( + __entry->status = status; + __entry->skb = skb; + ), + + TP_printk("mapping_status=%s, skb=%p", + show_mapping_status(__entry->status), + __entry->skb) +); + #endif /* _TRACE_MPTCP_H */ /* This part must be outside protection */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index dc08e5de807e..de8f16006fce 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -993,8 +993,6 @@ static bool subflow_check_data_avail(struct sock *ssk) struct mptcp_sock *msk; struct sk_buff *skb; - pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk, - subflow->data_avail, skb_peek(&ssk->sk_receive_queue)); if (!skb_peek(&ssk->sk_receive_queue)) subflow->data_avail = 0; if (subflow->data_avail) @@ -1006,7 +1004,7 @@ static bool subflow_check_data_avail(struct sock *ssk) u64 old_ack; status = get_mapping_status(ssk, msk); - pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status); + trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue)); if (status == MAPPING_INVALID) { ssk->sk_err = EBADMSG; goto fatal; -- 2.30.2 ^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 5/5] mptcp: add tracepoint in subflow_check_data_avail Geliang Tang @ 2021-03-29 14:03 ` Paolo Abeni 1 sibling, 0 replies; 10+ messages in thread From: Paolo Abeni @ 2021-03-29 14:03 UTC (permalink / raw) To: Geliang Tang, mptcp, mptcp On Wed, 2021-03-24 at 16:51 +0800, Geliang Tang wrote: > This patch added a tracepoint in ack_update_msk() to track the > incoming data_ack and window/snd_una updates. > > Suggested-by: Paolo Abeni <pabeni@redhat.com> > Signed-off-by: Geliang Tang <geliangtang@gmail.com> > --- > include/trace/events/mptcp.h | 25 +++++++++++++++++++++++++ > net/mptcp/options.c | 3 +++ > 2 files changed, 28 insertions(+) > > diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h > index 503a6098909d..2b8ae5e81cd1 100644 > --- a/include/trace/events/mptcp.h > +++ b/include/trace/events/mptcp.h > @@ -91,6 +91,31 @@ DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, > TP_PROTO(struct mptcp_ext *mpext), > TP_ARGS(mpext)); > > +TRACE_EVENT(ack_update_msk, > + > + TP_PROTO(u64 data_ack, u64 old_snd_una, u64 new_snd_una, u64 new_wnd_end), > + > + TP_ARGS(data_ack, old_snd_una, new_snd_una, new_wnd_end), > + > + TP_STRUCT__entry( > + __field(u64, data_ack) > + __field(u64, old_snd_una) > + __field(u64, new_snd_una) > + __field(u64, new_wnd_end) > + ), > + > + TP_fast_assign( > + __entry->data_ack = data_ack; > + __entry->old_snd_una = old_snd_una; > + __entry->new_snd_una = new_snd_una; > + __entry->new_wnd_end = new_wnd_end; > + ), > + > + TP_printk("data_ack=%llu old_snd_una=%llu new_snd_una=%llu new_wnd_end=%llu", > + __entry->data_ack, __entry->old_snd_una, > + __entry->new_snd_una, __entry->new_wnd_end) > +); > + > #endif /* _TRACE_MPTCP_H */ > > /* This part must be outside protection */ > diff --git a/net/mptcp/options.c b/net/mptcp/options.c > index c7eb61d0564c..87bd1bfde964 100644 > --- a/net/mptcp/options.c > +++ b/net/mptcp/options.c > @@ -13,6 +13,8 @@ > #include "protocol.h" > #include "mib.h" > > +#include <trace/events/mptcp.h> > + > static bool mptcp_cap_flag_sha256(u8 flags) > { > return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; > @@ -942,6 +944,7 @@ static void ack_update_msk(struct mptcp_sock *msk, > __mptcp_data_acked(sk); > } > mptcp_data_unlock(sk); > + trace_ack_update_msk(mp_opt->data_ack, old_snd_una, new_snd_una, new_wnd_end); Here it would be nice add also 'msk->wnd_end' as an argument and dump it in the trace event, so that trace point could tell us always the new windows end value. Thanks! Paolo ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Geliang Tang @ 2021-03-29 14:00 ` Paolo Abeni 1 sibling, 0 replies; 10+ messages in thread From: Paolo Abeni @ 2021-03-29 14:00 UTC (permalink / raw) To: Geliang Tang, mptcp, mptcp On Wed, 2021-03-24 at 16:51 +0800, Geliang Tang wrote: > This patch added a tracepoint in the mapping status function > get_mapping_status() to dump every mpext field. > > Suggested-by: Paolo Abeni <pabeni@redhat.com> > Signed-off-by: Geliang Tang <geliangtang@gmail.com> > --- > include/trace/events/mptcp.h | 54 ++++++++++++++++++++++++++++++++++++ > net/mptcp/subflow.c | 6 ++-- > 2 files changed, 57 insertions(+), 3 deletions(-) > > diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h > index 06908ea6afb4..503a6098909d 100644 > --- a/include/trace/events/mptcp.h > +++ b/include/trace/events/mptcp.h > @@ -37,6 +37,60 @@ TRACE_EVENT(mptcp_subflow_get_send, > __entry->backup, __entry->ratio) > ); > > +DECLARE_EVENT_CLASS(mptcp_dump_mpext, > + > + TP_PROTO(struct mptcp_ext *mpext), > + > + TP_ARGS(mpext), > + > + TP_STRUCT__entry( > + __field(u64, data_ack) > + __field(u32, data_ack32) > + __field(u64, data_seq) > + __field(u32, subflow_seq) > + __field(u16, data_len) > + __field(u8, use_map) > + __field(u8, dsn64) > + __field(u8, data_fin) > + __field(u8, use_ack) > + __field(u8, ack64) > + __field(u8, mpc_map) > + __field(u8, frozen) > + __field(u8, reset_transient) > + __field(u8, reset_reason) > + ), > + > + TP_fast_assign( > + __entry->data_ack = mpext->data_ack; > + __entry->data_ack32 = mpext->data_ack32; Here it's probaly better dump only one of __entry->data_ack and and mpext->data_ack32: __entry->data_ack = mpext->ack64 ? mpext->data_ack : mpext->data_ack32; Thanks! Paolo ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Geliang Tang @ 2021-03-29 13:52 ` Paolo Abeni 1 sibling, 0 replies; 10+ messages in thread From: Paolo Abeni @ 2021-03-29 13:52 UTC (permalink / raw) To: Geliang Tang, mptcp, mptcp On Wed, 2021-03-24 at 16:51 +0800, Geliang Tang wrote: > This patch added a tracepoint in the packet scheduler function > mptcp_subflow_get_send(). > > Suggested-by: Paolo Abeni <pabeni@redhat.com> > Signed-off-by: Geliang Tang <geliangtang@gmail.com> > --- > include/trace/events/mptcp.h | 43 ++++++++++++++++++++++++++++++++++++ > net/mptcp/protocol.c | 4 ++++ > 2 files changed, 47 insertions(+) > create mode 100644 include/trace/events/mptcp.h > > diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h > new file mode 100644 > index 000000000000..06908ea6afb4 > --- /dev/null > +++ b/include/trace/events/mptcp.h > @@ -0,0 +1,43 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +#undef TRACE_SYSTEM > +#define TRACE_SYSTEM mptcp > + > +#if !defined(_TRACE_MPTCP_H) || defined(TRACE_HEADER_MULTI_READ) > +#define _TRACE_MPTCP_H > + > +#include <linux/tracepoint.h> > + > +TRACE_EVENT(mptcp_subflow_get_send, > + > + TP_PROTO(struct mptcp_subflow_context *subflow, struct sock *ssk), > + > + TP_ARGS(subflow, ssk), > + > + TP_STRUCT__entry( > + __field(bool, active) > + __field(bool, free) > + __field(u32, snd_wnd) > + __field(u32, pace) > + __field(u8, backup) > + __field(u64, ratio) > + ), > + > + TP_fast_assign( > + __entry->active = mptcp_subflow_active(subflow); > + __entry->free = sk_stream_memory_free(subflow->tcp_sock); I'm sorry for not noticing the thing before, but subflow->tcp_sock can be potentially a TIME_WAIT socket. We need to do: sk = sk_fullsock(subflow->tcp_sock); and checking for sk being != NULL before accessing any tcp_sock or sock fields. Note that the caller don't need such thing explicitly, because it accesses such fields only for mptcp_subflow_active() sockets - which are NOT TIME_WAIT ones. > + __entry->snd_wnd = tcp_sk(ssk)->snd_wnd; > + __entry->pace = ssk->sk_pacing_rate; > + __entry->backup = subflow->backup; > + __entry->ratio = div_u64((u64)ssk->sk_wmem_queued << 32, __entry->pace); Here we need to check for !__entry->pace, to avoid possible division by 0. Thanks! Paolo ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [MPTCP] [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Geliang Tang @ 2021-03-29 13:52 ` Paolo Abeni 1 sibling, 0 replies; 10+ messages in thread From: Paolo Abeni @ 2021-03-29 13:52 UTC (permalink / raw) To: Geliang Tang, mptcp, mptcp On Wed, 2021-03-24 at 16:51 +0800, Geliang Tang wrote: > This patch exported the static function mptcp_subflow_active. > > Signed-off-by: Geliang Tang <geliangtang@gmail.com> > --- > net/mptcp/protocol.c | 2 +- > net/mptcp/protocol.h | 1 + > 2 files changed, 2 insertions(+), 1 deletion(-) > > diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c > index 9d7e7e13fba8..3ad236689480 100644 > --- a/net/mptcp/protocol.c > +++ b/net/mptcp/protocol.c > @@ -399,7 +399,7 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) > mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; > } > > -static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) > +bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) > { > struct sock *ssk = mptcp_subflow_tcp_sock(subflow); possibly is better to simply move the function definition to the protocol.h header, as 'static inline' one. Thanks! Paolo ^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2021-03-29 14:03 UTC | newest] Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2021-03-24 8:51 [MPTCP][PATCH v2 mptcp-next 0/5] add tracepoints Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Geliang Tang 2021-03-24 8:51 ` [MPTCP][PATCH v2 mptcp-next 5/5] mptcp: add tracepoint in subflow_check_data_avail Geliang Tang 2021-03-29 14:03 ` [MPTCP][PATCH v2 mptcp-next 4/5] mptcp: add tracepoint in ack_update_msk Paolo Abeni 2021-03-29 14:00 ` [MPTCP][PATCH v2 mptcp-next 3/5] mptcp: add tracepoint in get_mapping_status Paolo Abeni 2021-03-29 13:52 ` [MPTCP][PATCH v2 mptcp-next 2/5] mptcp: add tracepoint in mptcp_subflow_get_send Paolo Abeni 2021-03-29 13:52 ` [MPTCP] [MPTCP][PATCH v2 mptcp-next 1/5] mptcp: export mptcp_subflow_active Paolo Abeni
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.