From 16edd9b511a13e7760ed4b92ba4e39bacda5c86f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 22 Mar 2022 11:57:08 -0700 Subject: locking: Add lock contention tracepoints This adds two new lock contention tracepoints like below: * lock:contention_begin * lock:contention_end The lock:contention_begin takes a flags argument to classify locks. I found it useful to identify what kind of locks it's tracing like if it's spinning or sleeping, reader-writer lock, real-time, and per-cpu. Move tracepoint definitions into mutex.c so that we can use them without lockdep. Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Link: https://lkml.kernel.org/r/20220322185709.141236-2-namhyung@kernel.org --- include/trace/events/lock.h | 61 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index d7512129a324..b9b6e3edd518 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -5,11 +5,21 @@ #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LOCK_H -#include +#include #include +/* flags for lock:contention_begin */ +#define LCB_F_SPIN (1U << 0) +#define LCB_F_READ (1U << 1) +#define LCB_F_WRITE (1U << 2) +#define LCB_F_RT (1U << 3) +#define LCB_F_PERCPU (1U << 4) + + #ifdef CONFIG_LOCKDEP +#include + TRACE_EVENT(lock_acquire, TP_PROTO(struct lockdep_map *lock, unsigned int subclass, @@ -78,8 +88,53 @@ DEFINE_EVENT(lock, lock_acquired, TP_ARGS(lock, ip) ); -#endif -#endif +#endif /* CONFIG_LOCK_STAT */ +#endif /* CONFIG_LOCKDEP */ + +TRACE_EVENT(contention_begin, + + TP_PROTO(void *lock, unsigned int flags), + + TP_ARGS(lock, flags), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(unsigned int, flags) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->flags = flags; + ), + + TP_printk("%p (flags=%s)", __entry->lock_addr, + __print_flags(__entry->flags, "|", + { LCB_F_SPIN, "SPIN" }, + { LCB_F_READ, "READ" }, + { LCB_F_WRITE, "WRITE" }, + { LCB_F_RT, "RT" }, + { LCB_F_PERCPU, "PERCPU" } + )) +); + +TRACE_EVENT(contention_end, + + TP_PROTO(void *lock, int ret), + + TP_ARGS(lock, ret), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(int, ret) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->ret = ret; + ), + + TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret) +); #endif /* _TRACE_LOCK_H */ -- cgit v1.2.3 From dc1f7893a70fe403983bd8492f177bf993940e2c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Mar 2022 13:06:54 +0200 Subject: locking/mutex: Make contention tracepoints more consistent wrt adaptive spinning Have the trace_contention_*() tracepoints consistently include adaptive spinning. In order to differentiate between the spinning and non-spinning states add LCB_F_MUTEX and combine with LCB_F_SPIN. The consequence is that a mutex contention can now triggler multiple _begin() tracepoints before triggering an _end(). Additionally, this fixes one path where mutex would trigger _end() without ever seeing a _begin(). Signed-off-by: Peter Zijlstra (Intel) --- include/trace/events/lock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index b9b6e3edd518..9ebd081e057e 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -14,6 +14,7 @@ #define LCB_F_WRITE (1U << 2) #define LCB_F_RT (1U << 3) #define LCB_F_PERCPU (1U << 4) +#define LCB_F_MUTEX (1U << 5) #ifdef CONFIG_LOCKDEP @@ -113,7 +114,8 @@ TRACE_EVENT(contention_begin, { LCB_F_READ, "READ" }, { LCB_F_WRITE, "WRITE" }, { LCB_F_RT, "RT" }, - { LCB_F_PERCPU, "PERCPU" } + { LCB_F_PERCPU, "PERCPU" }, + { LCB_F_MUTEX, "MUTEX" } )) ); -- cgit v1.2.3 From 40570375356c874b1578e05c1dcc3ff7c1322dbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Apr 2022 16:35:38 -0700 Subject: tcp: add accessors to read/set tp->snd_cwnd We had various bugs over the years with code breaking the assumption that tp->snd_cwnd is greater than zero. Lately, syzbot reported the WARN_ON_ONCE(!tp->prior_cwnd) added in commit 8b8a321ff72c ("tcp: fix zero cwnd in tcp_cwnd_reduction") can trigger, and without a repro we would have to spend considerable time finding the bug. Instead of complaining too late, we want to catch where and when tp->snd_cwnd is set to an illegal value. Signed-off-by: Eric Dumazet Suggested-by: Yuchung Cheng Cc: Neal Cardwell Acked-by: Yuchung Cheng Link: https://lore.kernel.org/r/20220405233538.947344-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/trace/events/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 521059d8dc0a..edcd6369de10 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -279,7 +279,7 @@ TRACE_EVENT(tcp_probe, __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; __entry->snd_una = tp->snd_una; - __entry->snd_cwnd = tp->snd_cwnd; + __entry->snd_cwnd = tcp_snd_cwnd(tp); __entry->snd_wnd = tp->snd_wnd; __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); -- cgit v1.2.3 From 15fcdf6ae116d1e8da4ff76c6fd82514f5ea501b Mon Sep 17 00:00:00 2001 From: Ping Gan Date: Wed, 6 Apr 2022 09:09:56 +0800 Subject: tcp: Add tracepoint for tcp_set_ca_state The congestion status of a tcp flow may be updated since there is congestion between tcp sender and receiver. It makes sense to add tracepoint for congestion status set function to summate cc status duration and evaluate the performance of network and congestion algorithm. the backgound of this patch is below. Link: https://github.com/iovisor/bcc/pull/3899 Signed-off-by: Ping Gan Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220406010956.19656-1-jacky_gam_2001@163.com Signed-off-by: Jakub Kicinski --- include/trace/events/tcp.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index edcd6369de10..901b440238d5 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -371,6 +371,51 @@ DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, TP_ARGS(skb) ); +TRACE_EVENT(tcp_cong_state_set, + + TP_PROTO(struct sock *sk, const u8 ca_state), + + TP_ARGS(sk, ca_state), + + 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) + __field(__u8, cong_state) + ), + + TP_fast_assign( + struct inet_sock *inet = inet_sk(sk); + __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; + + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); + + __entry->cong_state = ca_state; + ), + + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + __entry->sport, __entry->dport, + __entry->saddr, __entry->daddr, + __entry->saddr_v6, __entry->daddr_v6, + __entry->cong_state) +); + #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 9f8ed577c28813410614b418bad42285840c1a00 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:50 +0800 Subject: net: skb: rename SKB_DROP_REASON_PTYPE_ABSENT As David Ahern suggested, the reasons for skb drops should be more general and not be code based. Therefore, rename SKB_DROP_REASON_PTYPE_ABSENT to SKB_DROP_REASON_UNHANDLED_PROTO, which is used for the cases of no L3 protocol handler, no L4 protocol handler, version extensions, etc. From previous discussion, now we have the aim to make these reasons more abstract and users based, avoiding code based. Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/trace/events/skb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index e1670e1e4934..85abd7cbd221 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -50,7 +50,7 @@ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EM(SKB_DROP_REASON_XDP, XDP) \ EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \ + EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ -- cgit v1.2.3 From b384c95a861eebf47e88695cf6a29f34e0b10b0f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:52 +0800 Subject: net: icmp: add skb drop reasons to icmp protocol Replace kfree_skb() used in icmp_rcv() and icmpv6_rcv() with kfree_skb_reason(). In order to get the reasons of the skb drops after icmp message handle, we change the return type of 'handler()' in 'struct icmp_control' from 'bool' to 'enum skb_drop_reason'. This may change its original intention, as 'false' means failure, but 'SKB_NOT_DROPPED_YET' means success now. Therefore, all 'handler' and the call of them need to be handled. Following 'handler' functions are involved: icmp_unreach() icmp_redirect() icmp_echo() icmp_timestamp() icmp_discard() And following new drop reasons are added: SKB_DROP_REASON_ICMP_CSUM SKB_DROP_REASON_INVALID_PROTO The reason 'INVALID_PROTO' is introduced for the case that the packet doesn't follow rfc 1122 and is dropped. This is not a common case, and I believe we can locate the problem from the data in the packet. For now, this 'INVALID_PROTO' is used for the icmp broadcasts with wrong types. Maybe there should be a document file for these reasons. For example, list all the case that causes the 'UNHANDLED_PROTO' and 'INVALID_PROTO' drop reason. Therefore, users can locate their problems according to the document. Reviewed-by: Hao Peng Reviewed-by: Jiang Biao Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/trace/events/skb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 85abd7cbd221..42647114fffe 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -61,6 +61,8 @@ EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ + EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ + EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From c4eb664191b4a5ff6856478f903924176697719e Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:53 +0800 Subject: net: ipv4: add skb drop reasons to ip_error() Eventually, I find out the handler function for inputting route lookup fail: ip_error(). The drop reasons we used in ip_error() are almost corresponding to IPSTATS_MIB_*, and following new reasons are introduced: SKB_DROP_REASON_IP_INADDRERRORS SKB_DROP_REASON_IP_INNOROUTES Isn't the name SKB_DROP_REASON_IP_HOSTUNREACH and SKB_DROP_REASON_IP_NETUNREACH more accurate? To make them corresponding to IPSTATS_MIB_*, we keep their name still. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/trace/events/skb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 42647114fffe..0acac7e5a019 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -63,6 +63,8 @@ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ + EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ + EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 2edc1a383fda8d2f580216292dfd9daeae691e47 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:55 +0800 Subject: net: ip: add skb drop reasons to ip forwarding Replace kfree_skb() which is used in ip6_forward() and ip_forward() with kfree_skb_reason(). The new drop reason 'SKB_DROP_REASON_PKT_TOO_BIG' is introduced for the case that the length of the packet exceeds MTU and can't fragment. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/trace/events/skb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 0acac7e5a019..2da72a9a5764 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -65,6 +65,7 @@ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ + EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From fde33ca4cb2bae6472714123b451475fdfd9995c Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 11 Apr 2022 16:01:15 +0200 Subject: tracing/timer: Add missing argument documentation of trace points Documentation of trace points timer_start, timer_expire_entry and hrtimer_start lack always the last argument. Add it to keep implementation and documentation in sync. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220411140115.24185-1-anna-maria@linutronix.de --- include/trace/events/timer.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 6ad031c71be7..2e713a7d9aa3 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -48,6 +48,7 @@ DEFINE_EVENT(timer_class, timer_init, * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time + * @flags: the timers flags */ TRACE_EVENT(timer_start, @@ -84,6 +85,7 @@ TRACE_EVENT(timer_start, /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list + * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ @@ -190,7 +192,8 @@ TRACE_EVENT(hrtimer_init, /** * hrtimer_start - called when the hrtimer is started - * @hrtimer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer + * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, -- cgit v1.2.3 From da40b613f89c43c58986e6f30560ad6573a4d569 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:41 -0700 Subject: tcp: add drop reason support to tcp_validate_incoming() Creates four new drop reasons for the following cases: 1) packet being rejected by RFC 7323 PAWS check 2) packet being rejected by SEQUENCE check 3) Invalid RST packet 4) Invalid SYN packet Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/trace/events/skb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 2da72a9a5764..820dacd14bad 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,11 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ + EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ + TCP_INVALID_SEQUENCE) \ + EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ + EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 669da7a71890b2b2a31a7e9571c0fdf1123e26ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:43 -0700 Subject: tcp: add drop reasons to tcp_rcv_state_process() Add basic support for drop reasons in tcp_rcv_state_process() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/trace/events/skb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 820dacd14bad..fbe21ad038bc 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,6 +42,9 @@ TCP_INVALID_SEQUENCE) \ EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ + EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ + EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ + EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 4b506af9c5b8de0da34097d50d9448dfb33d70c3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:44 -0700 Subject: tcp: add two drop reasons for tcp_ack() Add TCP_TOO_OLD_ACK and TCP_ACK_UNSENT_DATA drop reasons so that tcp_rcv_established() can report them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/trace/events/skb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index fbe21ad038bc..eab0b09223f3 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -45,6 +45,9 @@ EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ + TCP_ACK_UNSENT_DATA) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From e7c89ae4078eab24af71ba26b91642e819a4bd7f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:45 -0700 Subject: tcp: add drop reason support to tcp_prune_ofo_queue() Add one reason for packets dropped from OFO queue because of memory pressure. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/trace/events/skb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index eab0b09223f3..73d7a6e594cb 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -48,6 +48,8 @@ EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ TCP_ACK_UNSENT_DATA) \ + EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ + TCP_OFO_QUEUE_PRUNE) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 8fbf195798b56e1e87f62d01be636a6425c304c2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:48 -0700 Subject: tcp: add drop reason support to tcp_ofo_queue() packets in OFO queue might be redundant, and dropped. tcp_drop() is no longer needed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/trace/events/skb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 73d7a6e594cb..a477bf907498 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,7 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ TCP_INVALID_SEQUENCE) \ -- cgit v1.2.3 From c6af2aa9ffc9763826607bc2664ef3ea4475ed18 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Mar 2022 17:27:33 +0200 Subject: swiotlb: make the swiotlb_init interface more useful Pass a boolean flag to indicate if swiotlb needs to be enabled based on the addressing needs, and replace the verbose argument with a set of flags, including one to force enable bounce buffering. Note that this patch removes the possibility to force xen-swiotlb use with the swiotlb=force parameter on the command line on x86 (arm and arm64 never supported that), but this interface will be restored shortly. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/trace/events/swiotlb.h | 29 ++++++++++------------------- 1 file changed, 10 insertions(+), 19 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h index 705be43b71ab..da05c9ebd224 100644 --- a/include/trace/events/swiotlb.h +++ b/include/trace/events/swiotlb.h @@ -8,20 +8,15 @@ #include TRACE_EVENT(swiotlb_bounced, - - TP_PROTO(struct device *dev, - dma_addr_t dev_addr, - size_t size, - enum swiotlb_force swiotlb_force), - - TP_ARGS(dev, dev_addr, size, swiotlb_force), + TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size), + TP_ARGS(dev, dev_addr, size), TP_STRUCT__entry( - __string( dev_name, dev_name(dev) ) - __field( u64, dma_mask ) - __field( dma_addr_t, dev_addr ) - __field( size_t, size ) - __field( enum swiotlb_force, swiotlb_force ) + __string(dev_name, dev_name(dev)) + __field(u64, dma_mask) + __field(dma_addr_t, dev_addr) + __field(size_t, size) + __field(bool, force) ), TP_fast_assign( @@ -29,19 +24,15 @@ TRACE_EVENT(swiotlb_bounced, __entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0); __entry->dev_addr = dev_addr; __entry->size = size; - __entry->swiotlb_force = swiotlb_force; + __entry->force = is_swiotlb_force_bounce(dev); ), - TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx " - "size=%zu %s", + TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx size=%zu %s", __get_str(dev_name), __entry->dma_mask, (unsigned long long)__entry->dev_addr, __entry->size, - __print_symbolic(__entry->swiotlb_force, - { SWIOTLB_NORMAL, "NORMAL" }, - { SWIOTLB_FORCE, "FORCE" }, - { SWIOTLB_NO_FORCE, "NO_FORCE" })) + __entry->force ? "FORCE" : "NORMAL") ); #endif /* _TRACE_SWIOTLB_H */ -- cgit v1.2.3 From d9fdd02d4265c4c4fd5264b32b46034239192b7e Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 22 Apr 2022 14:55:42 -0700 Subject: mptcp: dump infinite_map field in mptcp_dump_mpext In trace event class mptcp_dump_mpext, dump the newly added infinite_map field of struct mptcp_dump_mpext too. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/trace/events/mptcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index f8e28e686c65..563e48617374 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -84,6 +84,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __field(u8, reset_transient) __field(u8, reset_reason) __field(u8, csum_reqd) + __field(u8, infinite_map) ), TP_fast_assign( @@ -102,9 +103,10 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->reset_transient = mpext->reset_transient; __entry->reset_reason = mpext->reset_reason; __entry->csum_reqd = mpext->csum_reqd; + __entry->infinite_map = mpext->infinite_map; ), - TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u", + TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u infinite_map=%u", __entry->data_ack, __entry->data_seq, __entry->subflow_seq, __entry->data_len, __entry->csum, __entry->use_map, @@ -112,7 +114,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->use_ack, __entry->ack64, __entry->mpc_map, __entry->frozen, __entry->reset_transient, __entry->reset_reason, - __entry->csum_reqd) + __entry->csum_reqd, __entry->infinite_map) ); DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag, -- cgit v1.2.3 From 47894438e916ca3fe44db33c2d4a1670fd296d6f Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 21 Apr 2022 02:13:40 -0700 Subject: io_uring: add trace support for CQE overflow Add trace function for overflowing CQ ring. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220421091345.2115755-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 42 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..42534ec2ab9d 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -530,7 +530,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", __entry->ctx, __entry->req, __entry->user_data, @@ -543,6 +543,46 @@ TRACE_EVENT(io_uring_req_failed, (unsigned long long) __entry->pad2, __entry->error) ); + +/* + * io_uring_cqe_overflow - a CQE overflowed + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: CQE result + * @cflags: CQE flags + * @ocqe: pointer to the overflow cqe (if available) + * + */ +TRACE_EVENT(io_uring_cqe_overflow, + + TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags, + void *ocqe), + + TP_ARGS(ctx, user_data, res, cflags, ocqe), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned long long, user_data ) + __field( s32, res ) + __field( u32, cflags ) + __field( void *, ocqe ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + __entry->cflags = cflags; + __entry->ocqe = ocqe; + ), + + TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + "overflow_cqe %p", + __entry->ctx, __entry->user_data, __entry->res, + __entry->cflags, __entry->ocqe) +); + #endif /* _TRACE_IO_URING_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 0200ce6a57c5de802f4e438485c14cc9d63d5f4b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 24 Apr 2022 18:16:57 -0600 Subject: io_uring: fix trace for reduced sqe padding __pad2 is only 1 u64 now, the other one is addr3. Adjust the trace so that it matches up. Fixes: a56834e0fafe ("io_uring: add fgetxattr and getxattr support") Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42534ec2ab9d..05b786f8b0bf 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -506,7 +506,7 @@ TRACE_EVENT(io_uring_req_failed, __field( u16, personality ) __field( u32, file_index ) __field( u64, pad1 ) - __field( u64, pad2 ) + __field( u64, addr3 ) __field( int, error ) ), @@ -525,14 +525,15 @@ TRACE_EVENT(io_uring_req_failed, __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; __entry->pad1 = sqe->__pad2[0]; - __entry->pad2 = sqe->__pad2[1]; + __entry->addr3 = sqe->addr3; __entry->error = error; ), TP_printk("ring %p, req %p, user_data 0x%llx, " "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " - "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " + "error=%d", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, @@ -540,7 +541,7 @@ TRACE_EVENT(io_uring_req_failed, __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, - (unsigned long long) __entry->pad2, __entry->error) + (unsigned long long) __entry->addr3, __entry->error) ); -- cgit v1.2.3 From c277f1411d7bc2831d48bde5c18d3b7f87c61646 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 21 Mar 2022 15:13:06 -0700 Subject: f2fs: introduce data read/write showing path info This was used in Android for a long time. Let's upstream it. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 94 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..4d1ad64d4cab 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -2067,6 +2067,100 @@ TRACE_EVENT(f2fs_fiemap, __entry->ret) ); +DECLARE_EVENT_CLASS(f2fs__rw_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command), + + TP_STRUCT__entry( + __string(pathbuf, pathname) + __field(loff_t, offset) + __field(int, bytes) + __field(loff_t, i_size) + __string(cmdline, command) + __field(pid_t, pid) + __field(ino_t, ino) + ), + + TP_fast_assign( + /* + * Replace the spaces in filenames and cmdlines + * because this screws up the tooling that parses + * the traces. + */ + __assign_str(pathbuf, pathname); + (void)strreplace(__get_str(pathbuf), ' ', '_'); + __entry->offset = offset; + __entry->bytes = bytes; + __entry->i_size = i_size_read(inode); + __assign_str(cmdline, command); + (void)strreplace(__get_str(cmdline), ' ', '_'); + __entry->pid = pid; + __entry->ino = inode->i_ino; + ), + + TP_printk("entry_name %s, offset %llu, bytes %d, cmdline %s," + " pid %d, i_size %llu, ino %lu", + __get_str(pathbuf), __entry->offset, __entry->bytes, + __get_str(cmdline), __entry->pid, __entry->i_size, + (unsigned long) __entry->ino) +); + +DECLARE_EVENT_CLASS(f2fs__rw_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes), + + TP_STRUCT__entry( + __field(ino_t, ino) + __field(loff_t, offset) + __field(int, bytes) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->offset = offset; + __entry->bytes = bytes; + ), + + TP_printk("ino %lu, offset %llu, bytes %d", + (unsigned long) __entry->ino, + __entry->offset, __entry->bytes) +); + +DEFINE_EVENT(f2fs__rw_start, f2fs_dataread_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command) +); + +DEFINE_EVENT(f2fs__rw_end, f2fs_dataread_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes) +); + +DEFINE_EVENT(f2fs__rw_start, f2fs_datawrite_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command) +); + +DEFINE_EVENT(f2fs__rw_end, f2fs_datawrite_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 1460af7de6ab33da82b8a1f03ce0f8e831a9e29e Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:06 -0700 Subject: io_uring: rename op -> opcode do this for consistency with the other trace messages Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-4-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 05b786f8b0bf..42c7e1a3c6ae 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -530,7 +530,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", -- cgit v1.2.3 From 033b87d24f7257c45506bd043ad85ed24a9925e2 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:07 -0700 Subject: io_uring: use the text representation of ops in trace It is annoying to translate opcodes to textwhen tracing io_uring. Use the io_uring_get_opcode function instead to use the text representation. A downside here might have been that if the opcode is invalid it will not be obvious, however the opcode is already overridden in these cases to 0 (NOP) in io_init_req(). Therefore this is a non issue. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-5-dylany@fb.com [axboe: don't include register, those are not req opcodes] Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42c7e1a3c6ae..3f2961baebcc 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include #include +#include struct io_wq_work; @@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", - __entry->ctx, __entry->req, __entry->data, __entry->opcode) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", + __entry->ctx, __entry->req, __entry->data, + io_uring_get_opcode(__entry->opcode)) ); /** @@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, - __entry->link) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->link) ); /** @@ -389,9 +392,9 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, __entry->opcode, + __entry->user_data, io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -433,8 +436,9 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask, __entry->events) ); @@ -470,8 +474,9 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask) ); @@ -530,12 +535,13 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "opcode %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", __entry->ctx, __entry->req, __entry->user_data, - __entry->opcode, __entry->flags, __entry->ioprio, + io_uring_get_opcode(__entry->opcode), + __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, __entry->op_flags, -- cgit v1.2.3 From c3d438eeb5413111889edef10cb5fcc2c0fb8bc9 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 Apr 2022 09:08:06 +0100 Subject: arch_topology: Trace the update thermal pressure Add trace event to capture the moment of the call for updating the thermal pressure value. It's helpful to investigate how often those events occur in a system dealing with throttling. This trace event is needed since the old 'cdev_update' might not be used by some drivers. The old 'cdev_update' trace event only provides a cooling state value: [0, n]. That state value then needs additional tools to translate it: state -> freq -> capacity -> thermal pressure. This new trace event just stores proper thermal pressure value in the trace buffer, no need for additional logic. This is helpful for cooperation when someone can simply sends to the list the trace buffer output from the platform (no need from additional information from other subsystems). There are also platforms which due to some design reasons don't use cooling devices and thus don't trigger old 'cdev_update' trace event. They are also important and measuring latency for the thermal signal raising/decaying characteristics is in scope. This new trace event would cover them as well. We already have a trace point 'pelt_thermal_tp' which after a change to trace event can be paired with this new 'thermal_pressure_update' and derive more insight what is going on in the system under thermal pressure (and why). Signed-off-by: Lukasz Luba Acked-by: Sudeep Holla Link: https://lore.kernel.org/r/20220427080806.1906-1-lukasz.luba@arm.com Signed-off-by: Greg Kroah-Hartman --- include/trace/events/thermal_pressure.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/trace/events/thermal_pressure.h (limited to 'include/trace') diff --git a/include/trace/events/thermal_pressure.h b/include/trace/events/thermal_pressure.h new file mode 100644 index 000000000000..b68680201360 --- /dev/null +++ b/include/trace/events/thermal_pressure.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thermal_pressure + +#if !defined(_TRACE_THERMAL_PRESSURE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THERMAL_PRESSURE_H + +#include + +TRACE_EVENT(thermal_pressure_update, + TP_PROTO(int cpu, unsigned long thermal_pressure), + TP_ARGS(cpu, thermal_pressure), + + TP_STRUCT__entry( + __field(unsigned long, thermal_pressure) + __field(int, cpu) + ), + + TP_fast_assign( + __entry->thermal_pressure = thermal_pressure; + __entry->cpu = cpu; + ), + + TP_printk("cpu=%d thermal_pressure=%lu", __entry->cpu, __entry->thermal_pressure) +); +#endif /* _TRACE_THERMAL_PRESSURE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 9d6b0cd7579844761ed68926eb3073bab1dca87b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 14:31:43 -0500 Subject: fs: Remove flags parameter from aops->write_begin There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/trace/events/ext4.h | 21 ++++++++------------- include/trace/events/f2fs.h | 12 ++++-------- 2 files changed, 12 insertions(+), 21 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d06ffffad434..229e8fae66a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -335,17 +335,15 @@ TRACE_EVENT(ext4_begin_ordered_truncate, DECLARE_EVENT_CLASS(ext4__write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) - __field( unsigned int, flags ) ), TP_fast_assign( @@ -353,29 +351,26 @@ DECLARE_EVENT_CLASS(ext4__write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->flags) + __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..bea654a85e6b 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1159,17 +1159,15 @@ DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio, TRACE_EVENT(f2fs_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, pos) __field(unsigned int, len) - __field(unsigned int, flags) ), TP_fast_assign( @@ -1177,14 +1175,12 @@ TRACE_EVENT(f2fs_write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u", + TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u", show_dev_ino(__entry), (unsigned long long)__entry->pos, - __entry->len, - __entry->flags) + __entry->len) ); TRACE_EVENT(f2fs_write_end, -- cgit v1.2.3 From c4bb964fa092fb68645a852365dfe9855fef178a Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Tue, 26 Apr 2022 11:21:31 -0700 Subject: io_uring: add tracing for additional CQE32 fields This adds tracing for the extra1 and extra2 fields. Co-developed-by: Jens Axboe Signed-off-by: Stefan Roesch Reviewed-by: Kanchan Joshi Link: https://lore.kernel.org/r/20220426182134.136504-10-shr@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 3f2961baebcc..630982b3c34c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -321,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link, * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags + * @extra1: extra 64-bit data for CQE32 + * @extra2: extra 64-bit data for CQE32 * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, + u64 extra1, u64 extra2), - TP_ARGS(ctx, req, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), TP_STRUCT__entry ( __field( void *, ctx ) @@ -335,6 +338,8 @@ TRACE_EVENT(io_uring_complete, __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) + __field( u64, extra1 ) + __field( u64, extra2 ) ), TP_fast_assign( @@ -343,12 +348,17 @@ TRACE_EVENT(io_uring_complete, __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; + __entry->extra1 = extra1; + __entry->extra2 = extra2; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " + "extra1 %llu extra2 %llu ", __entry->ctx, __entry->req, __entry->user_data, - __entry->res, __entry->cflags) + __entry->res, __entry->cflags, + (unsigned long long) __entry->extra1, + (unsigned long long) __entry->extra2) ); /** -- cgit v1.2.3 From 9c2136be0878c88c53dea26943ce40bb03ad8d8d Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Wed, 11 May 2022 18:28:36 +0000 Subject: sched/tracing: Append prev_state to tp args instead Commit fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20) added a new prev_state argument to the sched_switch tracepoint, before the prev task_struct pointer. This reordering of arguments broke BPF programs that use the raw tracepoint (e.g. tp_btf programs). The type of the second argument has changed and existing programs that assume a task_struct* argument (e.g. for bpf_task_storage access) will now fail to verify. If we instead append the new argument to the end, all existing programs would continue to work and can conditionally extract the prev_state argument on supported kernel versions. Fixes: fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20) Signed-off-by: Delyan Kratunov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt (Google) Link: https://lkml.kernel.org/r/c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com --- include/trace/events/sched.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 65e786756321..fbb99a61f714 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) -- cgit v1.2.3 From 2d2d5cb6ca8424fa849ebb4edb8e8022c13860c7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 12 May 2022 02:18:33 -0700 Subject: io_uring: fix ordering of args in io_uring_queue_async_work Fix arg ordering in TP_ARGS macro, which fixes the output. Fixes: 502c87d65564c ("io-uring: Make tracepoints consistent.") Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220512091834.728610-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..80d2588a090c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -147,7 +147,7 @@ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), + TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), TP_STRUCT__entry ( __field( void *, ctx ) -- cgit v1.2.3 From 51af802fc05152e84727a4293ccaa7e7e1b64d7e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 6 May 2022 15:54:08 -0700 Subject: trace: platform/x86/intel/ifs: Add trace point to track Intel IFS operations Add tracing support which may be useful for debugging systems that fail to complete In Field Scan tests. Acked-by: Steven Rostedt (Google) Reviewed-by: Dan Williams Signed-off-by: Tony Luck Acked-by: Hans de Goede Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220506225410.1652287-11-tony.luck@intel.com Signed-off-by: Hans de Goede --- include/trace/events/intel_ifs.h | 41 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/trace/events/intel_ifs.h (limited to 'include/trace') diff --git a/include/trace/events/intel_ifs.h b/include/trace/events/intel_ifs.h new file mode 100644 index 000000000000..d7353024016c --- /dev/null +++ b/include/trace/events/intel_ifs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM intel_ifs + +#if !defined(_TRACE_IFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IFS_H + +#include +#include + +TRACE_EVENT(ifs_status, + + TP_PROTO(int cpu, union ifs_scan activate, union ifs_status status), + + TP_ARGS(cpu, activate, status), + + TP_STRUCT__entry( + __field( u64, status ) + __field( int, cpu ) + __field( u8, start ) + __field( u8, stop ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->start = activate.start; + __entry->stop = activate.stop; + __entry->status = status.data; + ), + + TP_printk("cpu: %d, start: %.2x, stop: %.2x, status: %llx", + __entry->cpu, + __entry->start, + __entry->stop, + __entry->status) +); + +#endif /* _TRACE_IFS_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 3db1de0e582c358dd013f3703cd55b5fe4076436 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Thu, 28 Apr 2022 11:18:09 -0700 Subject: f2fs: change the current atomic write way Current atomic write has three major issues like below. - keeps the updates in non-reclaimable memory space and they are even hard to be migrated, which is not good for contiguous memory allocation. - disk spaces used for atomic files cannot be garbage collected, so this makes it difficult for the filesystem to be defragmented. - If atomic write operations hit the threshold of either memory usage or garbage collection failure count, All the atomic write operations will fail immediately. To resolve the issues, I will keep a COW inode internally for all the updates to be flushed from memory, when we need to flush them out in a situation like high memory pressure. These COW inodes will be tagged as orphan inodes to be reclaimed in case of sudden power-cut or system failure during atomic writes. Signed-off-by: Daeho Jeong Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4d1ad64d4cab..7e915dbf3674 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -15,10 +15,6 @@ TRACE_DEFINE_ENUM(NODE); TRACE_DEFINE_ENUM(DATA); TRACE_DEFINE_ENUM(META); TRACE_DEFINE_ENUM(META_FLUSH); -TRACE_DEFINE_ENUM(INMEM); -TRACE_DEFINE_ENUM(INMEM_DROP); -TRACE_DEFINE_ENUM(INMEM_INVALIDATE); -TRACE_DEFINE_ENUM(INMEM_REVOKE); TRACE_DEFINE_ENUM(IPU); TRACE_DEFINE_ENUM(OPU); TRACE_DEFINE_ENUM(HOT); @@ -59,10 +55,6 @@ TRACE_DEFINE_ENUM(CP_RESIZE); { DATA, "DATA" }, \ { META, "META" }, \ { META_FLUSH, "META_FLUSH" }, \ - { INMEM, "INMEM" }, \ - { INMEM_DROP, "INMEM_DROP" }, \ - { INMEM_INVALIDATE, "INMEM_INVALIDATE" }, \ - { INMEM_REVOKE, "INMEM_REVOKE" }, \ { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) @@ -1289,20 +1281,6 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite, TP_ARGS(page, type) ); -DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page, - - TP_PROTO(struct page *page, int type), - - TP_ARGS(page, type) -); - -DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page, - - TP_PROTO(struct page *page, int type), - - TP_ARGS(page, type) -); - TRACE_EVENT(f2fs_filemap_fault, TP_PROTO(struct inode *inode, pgoff_t index, unsigned long ret), -- cgit v1.2.3 From d147ea4adb969b03f7f1c7613cc6f44b70760eb3 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 6 May 2022 11:40:33 -0700 Subject: f2fs: introduce f2fs_gc_control to consolidate f2fs_gc parameters No functional change. - remove checkpoint=disable check for f2fs_write_checkpoint - get sec_freed all the time Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 7e915dbf3674..54ec9e543f09 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -644,19 +644,19 @@ TRACE_EVENT(f2fs_background_gc, TRACE_EVENT(f2fs_gc_begin, - TP_PROTO(struct super_block *sb, bool sync, bool background, + TP_PROTO(struct super_block *sb, int gc_type, bool no_bg_gc, long long dirty_nodes, long long dirty_dents, long long dirty_imeta, unsigned int free_sec, unsigned int free_seg, int reserved_seg, unsigned int prefree_seg), - TP_ARGS(sb, sync, background, dirty_nodes, dirty_dents, dirty_imeta, + TP_ARGS(sb, gc_type, no_bg_gc, dirty_nodes, dirty_dents, dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg), TP_STRUCT__entry( __field(dev_t, dev) - __field(bool, sync) - __field(bool, background) + __field(int, gc_type) + __field(bool, no_bg_gc) __field(long long, dirty_nodes) __field(long long, dirty_dents) __field(long long, dirty_imeta) @@ -668,8 +668,8 @@ TRACE_EVENT(f2fs_gc_begin, TP_fast_assign( __entry->dev = sb->s_dev; - __entry->sync = sync; - __entry->background = background; + __entry->gc_type = gc_type; + __entry->no_bg_gc = no_bg_gc; __entry->dirty_nodes = dirty_nodes; __entry->dirty_dents = dirty_dents; __entry->dirty_imeta = dirty_imeta; @@ -679,12 +679,12 @@ TRACE_EVENT(f2fs_gc_begin, __entry->prefree_seg = prefree_seg; ), - TP_printk("dev = (%d,%d), sync = %d, background = %d, nodes = %lld, " + TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nodes = %lld, " "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " "rsv_seg:%d, prefree_seg:%u", show_dev(__entry->dev), - __entry->sync, - __entry->background, + show_gc_type(__entry->gc_type), + (__entry->gc_type == BG_GC) ? __entry->no_bg_gc : -1, __entry->dirty_nodes, __entry->dirty_dents, __entry->dirty_imeta, -- cgit v1.2.3 From f67bed134a053663852a1a3ab1b3223bfc2104a2 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 12 May 2022 20:23:07 -0700 Subject: percpu: improve percpu_alloc_percpu event trace Add call_site, bytes_alloc and gfp_flags fields to the output of the percpu_alloc_percpu ftrace event: mkdir-4393 [001] 169.334788: percpu_alloc_percpu: call_site=mem_cgroup_css_alloc+0xa6 reserved=0 is_atomic=0 size=2408 align=8 base_addr=0xffffc7117fc00000 off=402176 ptr=0x3dc867a62300 bytes_alloc=14448 gfp_flags=GFP_KERNEL_ACCOUNT This is required to track memcg-accounted percpu allocations. Link: https://lkml.kernel.org/r/a07be858-c8a3-7851-9086-e3262cbcf707@openvz.org Signed-off-by: Vasily Averin Acked-by: Roman Gushchin Cc: Shakeel Butt Cc: Steven Rostedt Cc: Ingo Molnar Cc: Vlastimil Babka Cc: Michal Hocko Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Signed-off-by: Andrew Morton --- include/trace/events/percpu.h | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index df112a64f6c9..e989cefc0def 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -6,15 +6,20 @@ #define _TRACE_PERCPU_H #include +#include TRACE_EVENT(percpu_alloc_percpu, - TP_PROTO(bool reserved, bool is_atomic, size_t size, - size_t align, void *base_addr, int off, void __percpu *ptr), + TP_PROTO(unsigned long call_site, + bool reserved, bool is_atomic, size_t size, + size_t align, void *base_addr, int off, + void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), - TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr), + TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, + ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( + __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) @@ -22,9 +27,11 @@ TRACE_EVENT(percpu_alloc_percpu, __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) ), - TP_fast_assign( + __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; @@ -32,12 +39,16 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; ), - TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p", + TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", + (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, - __entry->base_addr, __entry->off, __entry->ptr) + __entry->base_addr, __entry->off, __entry->ptr, + __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, -- cgit v1.2.3 From fe573327ffb1deba802c91dd1d4ff41dafa97a0e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 12 May 2022 20:23:08 -0700 Subject: tracing: incorrect gfp_t conversion Fixes the following sparse warnings: include/trace/events/*: sparse: cast to restricted gfp_t include/trace/events/*: sparse: restricted gfp_t degrades to integer gfp_t type is bitwise and requires __force attributes for any casts. Link: https://lkml.kernel.org/r/331d88fe-f4f7-657c-02a2-d977f15fbff6@openvz.org Signed-off-by: Vasily Averin Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/trace/events/btrfs.h | 4 +- include/trace/events/compaction.h | 4 +- include/trace/events/kmem.h | 12 +++--- include/trace/events/mmflags.h | 78 +++++++++++++++++++-------------------- include/trace/events/vmscan.h | 16 ++++---- 5 files changed, 57 insertions(+), 57 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..ed92c80331ea 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1344,13 +1344,13 @@ TRACE_EVENT(alloc_extent_state, TP_STRUCT__entry( __field(const struct extent_state *, state) - __field(gfp_t, mask) + __field(unsigned long, mask) __field(const void*, ip) ), TP_fast_assign( __entry->state = state, - __entry->mask = mask, + __entry->mask = (__force unsigned long)mask, __entry->ip = (const void *)IP ), diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c6d5d70dc7a5..3313eb83c117 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -162,13 +162,13 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages, TP_STRUCT__entry( __field(int, order) - __field(gfp_t, gfp_mask) + __field(unsigned long, gfp_mask) __field(int, prio) ), TP_fast_assign( __entry->order = order; - __entry->gfp_mask = gfp_mask; + __entry->gfp_mask = (__force unsigned long)gfp_mask; __entry->prio = prio; ), diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index ddc8c944f417..71c141804222 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -24,7 +24,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( @@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", @@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, node ) ), @@ -84,7 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), @@ -208,14 +208,14 @@ TRACE_EVENT(mm_page_alloc, TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 6532119a6bf1..fcb1ffb2cc8d 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -14,48 +14,48 @@ */ #define __def_gfpflag_names \ - {(unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(unsigned long)GFP_USER, "GFP_USER"}, \ - {(unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ + {(__force unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ + {(__force unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ + {(__force unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ + {(__force unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ + {(__force unsigned long)GFP_USER, "GFP_USER"}, \ + {(__force unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ + {(__force unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ + {(__force unsigned long)GFP_NOFS, "GFP_NOFS"}, \ + {(__force unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ + {(__force unsigned long)GFP_NOIO, "GFP_NOIO"}, \ + {(__force unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ + {(__force unsigned long)GFP_DMA, "GFP_DMA"}, \ + {(__force unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ + {(__force unsigned long)GFP_DMA32, "GFP_DMA32"}, \ + {(__force unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ + {(__force unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ + {(__force unsigned long)__GFP_IO, "__GFP_IO"}, \ + {(__force unsigned long)__GFP_FS, "__GFP_FS"}, \ + {(__force unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ + {(__force unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ + {(__force unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ + {(__force unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ + {(__force unsigned long)__GFP_COMP, "__GFP_COMP"}, \ + {(__force unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ + {(__force unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ + {(__force unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ + {(__force unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ + {(__force unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ + {(__force unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ + {(__force unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ + {(__force unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ + {(__force unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ + {(__force unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ + {(__force unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ + {(__force unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ + {(__force unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ #ifdef CONFIG_KASAN_HW_TAGS #define __def_gfpflag_names_kasan , \ - {(unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} + {(__force unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ + {(__force unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ + {(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} #else #define __def_gfpflag_names_kasan #endif diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index de136dbd623a..408c86244d64 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -96,14 +96,14 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, __field( int, nid ) __field( int, zid ) __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", @@ -120,12 +120,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_STRUCT__entry( __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("order=%d gfp_flags=%s", @@ -210,7 +210,7 @@ TRACE_EVENT(mm_shrink_slab_start, __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) @@ -222,7 +222,7 @@ TRACE_EVENT(mm_shrink_slab_start, __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; - __entry->gfp_flags = sc->gfp_mask; + __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; @@ -446,13 +446,13 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_STRUCT__entry( __field(int, nid) __field(int, order) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", -- cgit v1.2.3 From a31b4a4368d28c5e780f0906588fbd1dcfe4ad54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Apr 2022 06:43:09 +0200 Subject: btrfs: simplify WQ_HIGHPRI handling in struct btrfs_workqueue Just let the one caller that wants optional WQ_HIGHPRI handling allocate a separate btrfs_workqueue for that. This allows to rename struct __btrfs_workqueue to btrfs_workqueue, remove a pointer indirection and separate allocation for all btrfs_workqueue users and generally simplify the code. Reviewed-by: Qu Wenruo Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..290f07eb050a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -24,7 +24,7 @@ struct btrfs_free_cluster; struct map_lookup; struct extent_buffer; struct btrfs_work; -struct __btrfs_workqueue; +struct btrfs_workqueue; struct btrfs_qgroup_extent_record; struct btrfs_qgroup; struct extent_io_tree; @@ -1457,42 +1457,36 @@ DEFINE_EVENT(btrfs__work, btrfs_ordered_sched, TP_ARGS(work) ); -DECLARE_EVENT_CLASS(btrfs__workqueue, +DECLARE_EVENT_CLASS(btrfs_workqueue, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high), + TP_ARGS(wq, name), TP_STRUCT__entry_btrfs( __field( const void *, wq ) __string( name, name ) - __field( int , high ) ), TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); - __entry->high = high; ), - TP_printk_btrfs("name=%s%s wq=%p", __get_str(name), - __print_flags(__entry->high, "", - {(WQ_HIGHPRI), "-high"}), + TP_printk_btrfs("name=%s wq=%p", __get_str(name), __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue, btrfs_workqueue_alloc, +DEFINE_EVENT(btrfs_workqueue, btrfs_workqueue_alloc, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high) + TP_ARGS(wq, name) ); -DECLARE_EVENT_CLASS(btrfs__workqueue_done, +DECLARE_EVENT_CLASS(btrfs_workqueue_done, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq), @@ -1507,9 +1501,9 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done, TP_printk_btrfs("wq=%p", __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, +DEFINE_EVENT(btrfs_workqueue_done, btrfs_workqueue_destroy, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq) ); -- cgit v1.2.3 From c8383054506c77b814489c09877b5db83fd4abf2 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:24 +0800 Subject: cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells Signed-off-by: Gao Xiang --- include/trace/events/cachefiles.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 311c14a20e70..93df9391bd7f 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -31,6 +31,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_lookup_failed, cachefiles_obj_see_withdraw_cookie, cachefiles_obj_see_withdrawal, + cachefiles_obj_get_ondemand_fd, + cachefiles_obj_put_ondemand_fd, }; enum fscache_why_object_killed { -- cgit v1.2.3 From 1519670e4fecc6063fa2f0c10f0666d3331f219b Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:29 +0800 Subject: cachefiles: add tracepoints for on-demand read mode Add tracepoints for on-demand read mode. Currently following tracepoints are added: OPEN request / COPEN reply CLOSE request READ request / CREAD reply write through anonymous fd release of anonymous fd Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-8-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/trace/events/cachefiles.h | 174 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 174 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 93df9391bd7f..d8d4d73fe7b6 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -673,6 +673,180 @@ TRACE_EVENT(cachefiles_io_error, __entry->error) ); +TRACE_EVENT(cachefiles_ondemand_open, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_open *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(unsigned int, fd ) + __field(unsigned int, flags ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->fd = load->fd; + __entry->flags = load->flags; + ), + + TP_printk("o=%08x mid=%x oid=%x fd=%d f=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->fd, + __entry->flags) + ); + +TRACE_EVENT(cachefiles_ondemand_copen, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id, + long len), + + TP_ARGS(obj, msg_id, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(long, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + __entry->len = len; + ), + + TP_printk("o=%08x mid=%x l=%lx", + __entry->obj, + __entry->msg_id, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_close, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg), + + TP_ARGS(obj, msg), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + ), + + TP_printk("o=%08x mid=%x oid=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id) + ); + +TRACE_EVENT(cachefiles_ondemand_read, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_read *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->start = load->off; + __entry->len = load->len; + ), + + TP_printk("o=%08x mid=%x oid=%x s=%llx l=%zx", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_cread, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id), + + TP_ARGS(obj, msg_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + ), + + TP_printk("o=%08x mid=%x", + __entry->obj, + __entry->msg_id) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_write, + TP_PROTO(struct cachefiles_object *obj, struct inode *backer, + loff_t start, size_t len), + + TP_ARGS(obj, backer, start, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, backer ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->backer = backer->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("o=%08x iB=%x s=%llx l=%zx", + __entry->obj, + __entry->backer, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_release, + TP_PROTO(struct cachefiles_object *obj, int object_id), + + TP_ARGS(obj, object_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->object_id = object_id; + ), + + TP_printk("o=%08x oid=%x", + __entry->obj, + __entry->object_id) + ); + #endif /* _TRACE_CACHEFILES_H */ /* This part must be outside protection */ -- cgit v1.2.3 From c81d5bae404abc6b257667e84d39b9b50c7063d4 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 6 May 2022 13:34:41 -0700 Subject: f2fs: do not stop GC when requiring a free section The f2fs_gc uses a bitmap to indicate pinned sections, but when disabling chckpoint, we call f2fs_gc() with NULL_SEGNO which selects the same dirty segment as a victim all the time, resulting in checkpoint=disable failure, for example. Let's pick another one, if we fail to collect it. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 54ec9e543f09..16c67ede85b6 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -645,18 +645,21 @@ TRACE_EVENT(f2fs_background_gc, TRACE_EVENT(f2fs_gc_begin, TP_PROTO(struct super_block *sb, int gc_type, bool no_bg_gc, + unsigned int nr_free_secs, long long dirty_nodes, long long dirty_dents, long long dirty_imeta, unsigned int free_sec, unsigned int free_seg, int reserved_seg, unsigned int prefree_seg), - TP_ARGS(sb, gc_type, no_bg_gc, dirty_nodes, dirty_dents, dirty_imeta, + TP_ARGS(sb, gc_type, no_bg_gc, nr_free_secs, dirty_nodes, + dirty_dents, dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg), TP_STRUCT__entry( __field(dev_t, dev) __field(int, gc_type) __field(bool, no_bg_gc) + __field(unsigned int, nr_free_secs) __field(long long, dirty_nodes) __field(long long, dirty_dents) __field(long long, dirty_imeta) @@ -670,6 +673,7 @@ TRACE_EVENT(f2fs_gc_begin, __entry->dev = sb->s_dev; __entry->gc_type = gc_type; __entry->no_bg_gc = no_bg_gc; + __entry->nr_free_secs = nr_free_secs; __entry->dirty_nodes = dirty_nodes; __entry->dirty_dents = dirty_dents; __entry->dirty_imeta = dirty_imeta; @@ -679,12 +683,13 @@ TRACE_EVENT(f2fs_gc_begin, __entry->prefree_seg = prefree_seg; ), - TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nodes = %lld, " - "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " + TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nr_free_secs = %u, " + "nodes = %lld, dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " "rsv_seg:%d, prefree_seg:%u", show_dev(__entry->dev), show_gc_type(__entry->gc_type), (__entry->gc_type == BG_GC) ? __entry->no_bg_gc : -1, + __entry->nr_free_secs, __entry->dirty_nodes, __entry->dirty_dents, __entry->dirty_imeta, -- cgit v1.2.3 From 45cb7955c180a2a34d291e68938250c4f9bd294f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 14 Apr 2022 15:50:12 -0400 Subject: SUNRPC: Clean up svc_deferred_class trace events Replace the temporary fix from commit 4d5004451ab2 ("SUNRPC: Fix the svc_deferred_event trace class") with the use of __sockaddr and friends, which is the preferred solution (but only available in 5.18 and newer). Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 3995c58a1c51..ee84e9289707 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2015,19 +2015,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __array(__u8, addr, INET6_ADDRSTRLEN + 10) + __sockaddr(addr, dr->addrlen) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - snprintf(__entry->addr, sizeof(__entry->addr) - 1, - "%pISpc", (struct sockaddr *)&dr->addr); + __assign_sockaddr(addr, &dr->addr, dr->addrlen); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, - __entry->xid) + TP_printk("addr=%pISpc dr=%p xid=0x%08x", __get_sockaddr(addr), + __entry->dr, __entry->xid) ); #define DEFINE_SVC_DEFERRED_EVENT(name) \ -- cgit v1.2.3 From 983084b2672c593959e3148d6a17c8b920797dde Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 6 Apr 2022 14:38:59 -0400 Subject: SUNRPC: Remove svc_rqst::rq_xprt_hlen Clean up: This field is now always set to zero. Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ee84e9289707..b61d9c90fa26 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2020,8 +2020,7 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_fast_assign( __entry->dr = dr; - __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + - (dr->xprt_hlen>>2))); + __entry->xid = be32_to_cpu(*(__be32 *)dr->args); __assign_sockaddr(addr, &dr->addr, dr->addrlen); ), -- cgit v1.2.3 From 0e7579ca732a39cc377e17509dda9bfc4f6ba78e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 19 May 2022 17:30:49 +0300 Subject: io_uring: fix incorrect __kernel_rwf_t cast Currently 'make C=1 fs/io_uring.o' generates sparse warning: CHECK fs/io_uring.c fs/io_uring.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, i nclude/trace/events/io_uring.h): ./include/trace/events/io_uring.h:488:1: warning: incorrect type in assignment (different base types) expected unsigned int [usertype] op_flags got restricted __kernel_rwf_t const [usertype] rw_flags This happen on cast of sqe->rw_flags which is defined as __kernel_rwf_t, this type is bitwise and requires __force attribute for any casts. However rw_flags is a member of the union, and its access can be safely replaced by using of its neighbours, so let's use poll32_events to fix the sparse warning. Signed-off-by: Vasily Averin Link: https://lore.kernel.org/r/6f009241-a63f-ae43-a04b-62841aaef293@openvz.org Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42534ec2ab9d..7cfd9c5cff37 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -520,7 +520,7 @@ TRACE_EVENT(io_uring_req_failed, __entry->off = sqe->off; __entry->addr = sqe->addr; __entry->len = sqe->len; - __entry->op_flags = sqe->rw_flags; + __entry->op_flags = sqe->poll32_events; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; -- cgit v1.2.3 From 10e0f7530205799e7e971aba699a7cb3a47456de Mon Sep 17 00:00:00 2001 From: Wonhyuk Yang Date: Thu, 19 May 2022 14:08:54 -0700 Subject: mm/page_alloc: fix tracepoint mm_page_alloc_zone_locked() Currently, trace point mm_page_alloc_zone_locked() doesn't show correct information. First, when alloc_flag has ALLOC_HARDER/ALLOC_CMA, page can be allocated from MIGRATE_HIGHATOMIC/MIGRATE_CMA. Nevertheless, tracepoint use requested migration type not MIGRATE_HIGHATOMIC and MIGRATE_CMA. Second, after commit 44042b4498728 ("mm/page_alloc: allow high-order pages to be stored on the per-cpu lists") percpu-list can store high order pages. But trace point determine whether it is a refiil of percpu-list by comparing requested order and 0. To handle these problems, make mm_page_alloc_zone_locked() only be called by __rmqueue_smallest with correct migration type. With a new argument called percpu_refill, it can show roughly whether it is a refill of percpu-list. Link: https://lkml.kernel.org/r/20220512025307.57924-1-vvghjk1234@gmail.com Signed-off-by: Wonhyuk Yang Acked-by: Mel Gorman Cc: Baik Song An Cc: Hong Yeon Kim Cc: Taeung Song Cc: Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/trace/events/kmem.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 71c141804222..f76668305ac5 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -229,20 +229,23 @@ TRACE_EVENT(mm_page_alloc, DECLARE_EVENT_CLASS(mm_page, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype), + TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) + __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; + __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", @@ -250,14 +253,15 @@ DECLARE_EVENT_CLASS(mm_page, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, - __entry->order == 0) + __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype) + TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, -- cgit v1.2.3 From 2b132903de7124dd9a758be0c27562e91a510848 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 11 May 2022 12:46:53 +0300 Subject: tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate Fixes following sparse warnings: CHECK mm/vmscan.c mm/vmscan.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, include/trace/events/vmscan.h): ./include/trace/events/vmscan.h:281:1: sparse: warning: cast to restricted isolate_mode_t ./include/trace/events/vmscan.h:281:1: sparse: warning: restricted isolate_mode_t degrades to integer Link: https://lkml.kernel.org/r/e85d7ff2-fd10-53f8-c24e-ba0458439c1b@openvz.org Signed-off-by: Vasily Averin Acked-by: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/trace/events/vmscan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 408c86244d64..d2123dd960d5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -297,7 +297,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) - __field(isolate_mode_t, isolate_mode) + __field(unsigned int, isolate_mode) __field(int, lru) ), @@ -308,7 +308,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; - __entry->isolate_mode = isolate_mode; + __entry->isolate_mode = (__force unsigned int)isolate_mode; __entry->lru = lru; ), -- cgit v1.2.3 From a05754295e01f006a651eec759c5dbe682ef6cef Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:22 +0100 Subject: rxrpc: Use refcount_t rather than atomic_t Move to using refcount_t rather than atomic_t for refcounts in rxrpc. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4a3ab0ed6e06..cdb28976641b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -583,7 +583,7 @@ TRACE_EVENT(rxrpc_client, TP_fast_assign( __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = conn ? atomic_read(&conn->usage) : -2; + __entry->usage = conn ? refcount_read(&conn->ref) : -2; __entry->op = op; __entry->cid = conn ? conn->proto.cid : 0; ), -- cgit v1.2.3 From dc9fd093b2ebabc25a5d7d0dd5bdfdd6c878e0bf Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:35 +0100 Subject: rxrpc: Automatically generate trace tag enums Automatically generate trace tag enums from the symbol -> string mapping tables rather than having the enums as well, thereby reducing duplicated data. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 261 +++++++------------------------------------ 1 file changed, 42 insertions(+), 219 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index cdb28976641b..66915b872a44 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -13,215 +13,6 @@ #include #include -/* - * Define enums for tracing information. - * - * These should all be kept sorted, making it easier to match the string - * mapping tables further on. - */ -#ifndef __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY -#define __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY - -enum rxrpc_skb_trace { - rxrpc_skb_cleaned, - rxrpc_skb_freed, - rxrpc_skb_got, - rxrpc_skb_lost, - rxrpc_skb_new, - rxrpc_skb_purged, - rxrpc_skb_received, - rxrpc_skb_rotated, - rxrpc_skb_seen, - rxrpc_skb_unshared, - rxrpc_skb_unshared_nomem, -}; - -enum rxrpc_local_trace { - rxrpc_local_got, - rxrpc_local_new, - rxrpc_local_processing, - rxrpc_local_put, - rxrpc_local_queued, -}; - -enum rxrpc_peer_trace { - rxrpc_peer_got, - rxrpc_peer_new, - rxrpc_peer_processing, - rxrpc_peer_put, -}; - -enum rxrpc_conn_trace { - rxrpc_conn_got, - rxrpc_conn_new_client, - rxrpc_conn_new_service, - rxrpc_conn_put_client, - rxrpc_conn_put_service, - rxrpc_conn_queued, - rxrpc_conn_reap_service, - rxrpc_conn_seen, -}; - -enum rxrpc_client_trace { - rxrpc_client_activate_chans, - rxrpc_client_alloc, - rxrpc_client_chan_activate, - rxrpc_client_chan_disconnect, - rxrpc_client_chan_pass, - rxrpc_client_chan_wait_failed, - rxrpc_client_cleanup, - rxrpc_client_discard, - rxrpc_client_duplicate, - rxrpc_client_exposed, - rxrpc_client_replace, - rxrpc_client_to_active, - rxrpc_client_to_idle, -}; - -enum rxrpc_call_trace { - rxrpc_call_connected, - rxrpc_call_error, - rxrpc_call_got, - rxrpc_call_got_kernel, - rxrpc_call_got_timer, - rxrpc_call_got_userid, - rxrpc_call_new_client, - rxrpc_call_new_service, - rxrpc_call_put, - rxrpc_call_put_kernel, - rxrpc_call_put_noqueue, - rxrpc_call_put_notimer, - rxrpc_call_put_timer, - rxrpc_call_put_userid, - rxrpc_call_queued, - rxrpc_call_queued_ref, - rxrpc_call_release, - rxrpc_call_seen, -}; - -enum rxrpc_transmit_trace { - rxrpc_transmit_await_reply, - rxrpc_transmit_end, - rxrpc_transmit_queue, - rxrpc_transmit_queue_last, - rxrpc_transmit_rotate, - rxrpc_transmit_rotate_last, - rxrpc_transmit_wait, -}; - -enum rxrpc_receive_trace { - rxrpc_receive_end, - rxrpc_receive_front, - rxrpc_receive_incoming, - rxrpc_receive_queue, - rxrpc_receive_queue_last, - rxrpc_receive_rotate, -}; - -enum rxrpc_recvmsg_trace { - rxrpc_recvmsg_cont, - rxrpc_recvmsg_data_return, - rxrpc_recvmsg_dequeue, - rxrpc_recvmsg_enter, - rxrpc_recvmsg_full, - rxrpc_recvmsg_hole, - rxrpc_recvmsg_next, - rxrpc_recvmsg_requeue, - rxrpc_recvmsg_return, - rxrpc_recvmsg_terminal, - rxrpc_recvmsg_to_be_accepted, - rxrpc_recvmsg_wait, -}; - -enum rxrpc_rtt_tx_trace { - rxrpc_rtt_tx_cancel, - rxrpc_rtt_tx_data, - rxrpc_rtt_tx_no_slot, - rxrpc_rtt_tx_ping, -}; - -enum rxrpc_rtt_rx_trace { - rxrpc_rtt_rx_cancel, - rxrpc_rtt_rx_lost, - rxrpc_rtt_rx_obsolete, - rxrpc_rtt_rx_ping_response, - rxrpc_rtt_rx_requested_ack, -}; - -enum rxrpc_timer_trace { - rxrpc_timer_begin, - rxrpc_timer_exp_ack, - rxrpc_timer_exp_hard, - rxrpc_timer_exp_idle, - rxrpc_timer_exp_keepalive, - rxrpc_timer_exp_lost_ack, - rxrpc_timer_exp_normal, - rxrpc_timer_exp_ping, - rxrpc_timer_exp_resend, - rxrpc_timer_expired, - rxrpc_timer_init_for_reply, - rxrpc_timer_init_for_send_reply, - rxrpc_timer_restart, - rxrpc_timer_set_for_ack, - rxrpc_timer_set_for_hard, - rxrpc_timer_set_for_idle, - rxrpc_timer_set_for_keepalive, - rxrpc_timer_set_for_lost_ack, - rxrpc_timer_set_for_normal, - rxrpc_timer_set_for_ping, - rxrpc_timer_set_for_resend, - rxrpc_timer_set_for_send, -}; - -enum rxrpc_propose_ack_trace { - rxrpc_propose_ack_client_tx_end, - rxrpc_propose_ack_input_data, - rxrpc_propose_ack_ping_for_check_life, - rxrpc_propose_ack_ping_for_keepalive, - rxrpc_propose_ack_ping_for_lost_ack, - rxrpc_propose_ack_ping_for_lost_reply, - rxrpc_propose_ack_ping_for_params, - rxrpc_propose_ack_processing_op, - rxrpc_propose_ack_respond_to_ack, - rxrpc_propose_ack_respond_to_ping, - rxrpc_propose_ack_retry_tx, - rxrpc_propose_ack_rotate_rx, - rxrpc_propose_ack_terminal_ack, -}; - -enum rxrpc_propose_ack_outcome { - rxrpc_propose_ack_subsume, - rxrpc_propose_ack_update, - rxrpc_propose_ack_use, -}; - -enum rxrpc_congest_change { - rxrpc_cong_begin_retransmission, - rxrpc_cong_cleared_nacks, - rxrpc_cong_new_low_nack, - rxrpc_cong_no_change, - rxrpc_cong_progress, - rxrpc_cong_retransmit_again, - rxrpc_cong_rtt_window_end, - rxrpc_cong_saw_nack, -}; - -enum rxrpc_tx_point { - rxrpc_tx_point_call_abort, - rxrpc_tx_point_call_ack, - rxrpc_tx_point_call_data_frag, - rxrpc_tx_point_call_data_nofrag, - rxrpc_tx_point_call_final_resend, - rxrpc_tx_point_conn_abort, - rxrpc_tx_point_rxkad_challenge, - rxrpc_tx_point_rxkad_response, - rxrpc_tx_point_reject, - rxrpc_tx_point_version_keepalive, - rxrpc_tx_point_version_reply, -}; - -#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ - /* * Declare tracing information enums and their string mappings for display. */ @@ -451,6 +242,36 @@ enum rxrpc_tx_point { EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") +/* + * Generate enums for tracing information. + */ +#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#undef EM +#undef E_ +#define EM(a, b) a, +#define E_(a, b) a + +enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); +enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); +enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); +enum rxrpc_conn_trace { rxrpc_conn_traces } __mode(byte); +enum rxrpc_local_trace { rxrpc_local_traces } __mode(byte); +enum rxrpc_peer_trace { rxrpc_peer_traces } __mode(byte); +enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte); +enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte); +enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte); +enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); +enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); +enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); +enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); +enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); +enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); +enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); + +#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ + /* * Export enum symbols via userspace. */ @@ -459,21 +280,21 @@ enum rxrpc_tx_point { #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); -rxrpc_skb_traces; -rxrpc_local_traces; -rxrpc_conn_traces; -rxrpc_client_traces; rxrpc_call_traces; -rxrpc_transmit_traces; +rxrpc_client_traces; +rxrpc_congest_changes; +rxrpc_congest_modes; +rxrpc_conn_traces; +rxrpc_local_traces; +rxrpc_propose_ack_outcomes; +rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; -rxrpc_rtt_tx_traces; rxrpc_rtt_rx_traces; +rxrpc_rtt_tx_traces; +rxrpc_skb_traces; rxrpc_timer_traces; -rxrpc_propose_ack_traces; -rxrpc_propose_ack_outcomes; -rxrpc_congest_modes; -rxrpc_congest_changes; +rxrpc_transmit_traces; rxrpc_tx_points; /* @@ -1574,6 +1395,8 @@ TRACE_EVENT(rxrpc_rx_discard_ack, __entry->call_ackr_prev) ); +#undef EM +#undef E_ #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 9a3dedcf18096e8f7f22b8777d78c4acfdea1651 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 09:03:31 +0100 Subject: rxrpc: Fix decision on when to generate an IDLE ACK Fix the decision on when to generate an IDLE ACK by keeping a count of the number of packets we've received, but not yet soft-ACK'd, and the number of packets we've processed, but not yet hard-ACK'd, rather than trying to keep track of which DATA sequence numbers correspond to those points. We then generate an ACK when either counter exceeds 2. The counters are both cleared when we transcribe the information into any sort of ACK packet for transmission. IDLE and DELAY ACKs are skipped if both counters are 0 (ie. no change). Fixes: 805b21b929e2 ("rxrpc: Send an ACK after every few DATA packets we receive") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4a3ab0ed6e06..1c714336b863 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1509,7 +1509,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; __entry->tx_seq = call->tx_hard_ack; - __entry->rx_seq = call->ackr_seen; + __entry->rx_seq = call->rx_hard_ack; ), TP_printk("c=%08x %08x:%08x r=%08x/%08x tx=%08x rx=%08x", -- cgit v1.2.3 From 185194f19134716f32b2ab04ac76cf93ea85706a Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 17 May 2022 09:58:14 +0300 Subject: include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion" Redefines __def_gfpflag_names array according to akpm@, willy@ and Joe Perches recommendations. Link: https://lkml.kernel.org/r/6f811e19-41c6-f3e8-fca6-23a19a62e313@openvz.org Fixes: fe573327ffb1 ("tracing: incorrect gfp_t conversion") Signed-off-by: Vasily Averin Cc: Matthew Wilcox Cc: Joe Perches Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/trace/events/mmflags.h | 84 +++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 41 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index fcb1ffb2cc8d..e87cb2b80ed3 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -13,49 +13,51 @@ * Thus most bits set go first. */ -#define __def_gfpflag_names \ - {(__force unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(__force unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(__force unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(__force unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(__force unsigned long)GFP_USER, "GFP_USER"}, \ - {(__force unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(__force unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(__force unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(__force unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(__force unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(__force unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(__force unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(__force unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(__force unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(__force unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(__force unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(__force unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(__force unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(__force unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(__force unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(__force unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(__force unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(__force unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(__force unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(__force unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(__force unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(__force unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(__force unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(__force unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(__force unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(__force unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(__force unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(__force unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(__force unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(__force unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(__force unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ +#define gfpflag_string(flag) {(__force unsigned long)flag, #flag} + +#define __def_gfpflag_names \ + gfpflag_string(GFP_TRANSHUGE), \ + gfpflag_string(GFP_TRANSHUGE_LIGHT), \ + gfpflag_string(GFP_HIGHUSER_MOVABLE), \ + gfpflag_string(GFP_HIGHUSER), \ + gfpflag_string(GFP_USER), \ + gfpflag_string(GFP_KERNEL_ACCOUNT), \ + gfpflag_string(GFP_KERNEL), \ + gfpflag_string(GFP_NOFS), \ + gfpflag_string(GFP_ATOMIC), \ + gfpflag_string(GFP_NOIO), \ + gfpflag_string(GFP_NOWAIT), \ + gfpflag_string(GFP_DMA), \ + gfpflag_string(__GFP_HIGHMEM), \ + gfpflag_string(GFP_DMA32), \ + gfpflag_string(__GFP_HIGH), \ + gfpflag_string(__GFP_ATOMIC), \ + gfpflag_string(__GFP_IO), \ + gfpflag_string(__GFP_FS), \ + gfpflag_string(__GFP_NOWARN), \ + gfpflag_string(__GFP_RETRY_MAYFAIL), \ + gfpflag_string(__GFP_NOFAIL), \ + gfpflag_string(__GFP_NORETRY), \ + gfpflag_string(__GFP_COMP), \ + gfpflag_string(__GFP_ZERO), \ + gfpflag_string(__GFP_NOMEMALLOC), \ + gfpflag_string(__GFP_MEMALLOC), \ + gfpflag_string(__GFP_HARDWALL), \ + gfpflag_string(__GFP_THISNODE), \ + gfpflag_string(__GFP_RECLAIMABLE), \ + gfpflag_string(__GFP_MOVABLE), \ + gfpflag_string(__GFP_ACCOUNT), \ + gfpflag_string(__GFP_WRITE), \ + gfpflag_string(__GFP_RECLAIM), \ + gfpflag_string(__GFP_DIRECT_RECLAIM), \ + gfpflag_string(__GFP_KSWAPD_RECLAIM), \ + gfpflag_string(__GFP_ZEROTAGS) #ifdef CONFIG_KASAN_HW_TAGS -#define __def_gfpflag_names_kasan , \ - {(__force unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(__force unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} +#define __def_gfpflag_names_kasan , \ + gfpflag_string(__GFP_SKIP_ZERO), \ + gfpflag_string(__GFP_SKIP_KASAN_POISON), \ + gfpflag_string(__GFP_SKIP_KASAN_UNPOISON) #else #define __def_gfpflag_names_kasan #endif -- cgit v1.2.3 From e5c3f619a04d9e191de66d5f8e069367f73a6487 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 17 May 2022 09:55:51 +0300 Subject: include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace" Fix sparse warning about incorrect gfp_t cast. Link: https://lkml.kernel.org/r/001979f3-e978-0998-cbed-61a4a2ac87b8@openvz.org Fixes: f67bed134a05 ("percpu: improve percpu_alloc_percpu event trace") Signed-off-by: Vasily Averin Signed-off-by: Andrew Morton --- include/trace/events/percpu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index e989cefc0def..5b8211ca8950 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -28,7 +28,7 @@ TRACE_EVENT(percpu_alloc_percpu, __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; @@ -40,7 +40,7 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", -- cgit v1.2.3 From 873a400938b31a1e443c4d94b560b78300787540 Mon Sep 17 00:00:00 2001 From: Wonhyuk Yang Date: Wed, 4 May 2022 11:32:03 +0900 Subject: workqueue: Fix type of cpu in trace event The trace event "workqueue_queue_work" use unsigned int type for req_cpu, cpu. This casue confusing cpu number like below log. $ cat /sys/kernel/debug/tracing/trace cat-317 [001] ...: workqueue_queue_work: ... req_cpu=8192 cpu=4294967295 So, change unsigned type to signed type in the trace event. After applying this patch, cpu number will be printed as -1 instead of 4294967295 as folllows. $ cat /sys/kernel/debug/tracing/trace cat-1338 [002] ...: workqueue_queue_work: ... req_cpu=8192 cpu=-1 Cc: Baik Song An Cc: Hong Yeon Kim Cc: Taeung Song Cc: linuxgeek@linuxgeek.io Signed-off-by: Wonhyuk Yang Signed-off-by: Tejun Heo --- include/trace/events/workqueue.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 6154a2e72bce..262d52021c23 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -22,7 +22,7 @@ struct pool_workqueue; */ TRACE_EVENT(workqueue_queue_work, - TP_PROTO(unsigned int req_cpu, struct pool_workqueue *pwq, + TP_PROTO(int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), @@ -31,8 +31,8 @@ TRACE_EVENT(workqueue_queue_work, __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) - __field( unsigned int, req_cpu ) - __field( unsigned int, cpu ) + __field( int, req_cpu ) + __field( int, cpu ) ), TP_fast_assign( @@ -43,7 +43,7 @@ TRACE_EVENT(workqueue_queue_work, __entry->cpu = pwq->pool->cpu; ), - TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u", + TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%d cpu=%d", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); -- cgit v1.2.3 From 540a92bfe6dab7310b9df2e488ba247d784d0163 Mon Sep 17 00:00:00 2001 From: Edward Wu Date: Fri, 17 Jun 2022 11:32:20 +0800 Subject: ata: libata: add qc->flags in ata_qc_complete_template tracepoint Add flags value to check the result of ata completion Fixes: 255c03d15a29 ("libata: Add tracepoints") Cc: stable@vger.kernel.org Signed-off-by: Edward Wu Signed-off-by: Damien Le Moal --- include/trace/events/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/libata.h b/include/trace/events/libata.h index d4e631aa976f..6025dd8ba4aa 100644 --- a/include/trace/events/libata.h +++ b/include/trace/events/libata.h @@ -288,6 +288,7 @@ DECLARE_EVENT_CLASS(ata_qc_complete_template, __entry->hob_feature = qc->result_tf.hob_feature; __entry->nsect = qc->result_tf.nsect; __entry->hob_nsect = qc->result_tf.hob_nsect; + __entry->flags = qc->flags; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s status=%s " \ -- cgit v1.2.3 From e70b64a3f28b9f54602ae3e706b1dc1338de3df7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 23 Jun 2022 01:37:43 -0700 Subject: io_uring: move io_uring_get_opcode out of TP_printk The TP_printk macro's are not supposed to use custom code ([1]) or else tools such as perf cannot use these events. Convert the opcode string representation to use the __string wiring that the event framework provides ([2]). [1]: https://lwn.net/Articles/379903/ [2]: https://lwn.net/Articles/381064/ Fixes: 033b87d24f72 ("io_uring: use the text representation of ops in trace") Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220623083743.2648321-1-dylany@fb.com [axboe: fixup spurious removal of sq_thread assignment] Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 42 ++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 66fcc5a1a5b1..aa2f951b07cd 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -158,6 +158,8 @@ TRACE_EVENT(io_uring_queue_async_work, __field( unsigned int, flags ) __field( struct io_wq_work *, work ) __field( int, rw ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -168,11 +170,13 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->opcode = opcode; __entry->work = work; __entry->rw = rw; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -198,6 +202,8 @@ TRACE_EVENT(io_uring_defer, __field( void *, req ) __field( unsigned long long, data ) __field( u8, opcode ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -205,11 +211,13 @@ TRACE_EVENT(io_uring_defer, __entry->req = req; __entry->data = user_data; __entry->opcode = opcode; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", __entry->ctx, __entry->req, __entry->data, - io_uring_get_opcode(__entry->opcode)) + __get_str(op_str)) ); /** @@ -298,6 +306,8 @@ TRACE_EVENT(io_uring_fail_link, __field( unsigned long long, user_data ) __field( u8, opcode ) __field( void *, link ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -306,11 +316,13 @@ TRACE_EVENT(io_uring_fail_link, __entry->user_data = user_data; __entry->opcode = opcode; __entry->link = link; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), __entry->link) + __get_str(op_str), __entry->link) ); /** @@ -390,6 +402,8 @@ TRACE_EVENT(io_uring_submit_sqe, __field( u32, flags ) __field( bool, force_nonblock ) __field( bool, sq_thread ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -400,11 +414,13 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, io_uring_get_opcode(__entry->opcode), + __entry->user_data, __get_str(op_str), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -435,6 +451,8 @@ TRACE_EVENT(io_uring_poll_arm, __field( u8, opcode ) __field( int, mask ) __field( int, events ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -444,11 +462,13 @@ TRACE_EVENT(io_uring_poll_arm, __entry->opcode = opcode; __entry->mask = mask; __entry->events = events; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->mask, __entry->events) ); @@ -474,6 +494,8 @@ TRACE_EVENT(io_uring_task_add, __field( unsigned long long, user_data ) __field( u8, opcode ) __field( int, mask ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -482,11 +504,13 @@ TRACE_EVENT(io_uring_task_add, __entry->user_data = user_data; __entry->opcode = opcode; __entry->mask = mask; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->mask) ); @@ -523,6 +547,8 @@ TRACE_EVENT(io_uring_req_failed, __field( u64, pad1 ) __field( u64, addr3 ) __field( int, error ) + + __string( op_str, io_uring_get_opcode(sqe->opcode) ) ), TP_fast_assign( @@ -542,6 +568,8 @@ TRACE_EVENT(io_uring_req_failed, __entry->pad1 = sqe->__pad2[0]; __entry->addr3 = sqe->addr3; __entry->error = error; + + __assign_str(op_str, io_uring_get_opcode(sqe->opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, " @@ -550,7 +578,7 @@ TRACE_EVENT(io_uring_req_failed, "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, -- cgit v1.2.3