From 00cf3d672a9dd409418647e9f98784c339c3ff63 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 17 Jan 2023 10:21:28 -0500 Subject: tracing: Allow synthetic events to pass around stacktraces Allow a stacktrace from one event to be displayed by the end event of a synthetic event. This is very useful when looking for the longest latency of a sleep or something blocked on I/O. # cd /sys/kernel/tracing/ # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' > events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger The above creates a "block_lat" synthetic event that take the stacktrace of when a task schedules out in either the interruptible or uninterruptible states, and on a new per process max $delta (the time it was scheduled out), will print the process id and the stacktrace. # echo 1 > events/synthetic/block_lat/enable # cat trace # TASK-PID CPU# ||||| TIMESTAMP FUNCTION # | | | ||||| | | kworker/u16:0-767 [006] d..4. 560.645045: block_lat: pid=767 delta=66 stack=STACK: => __schedule => schedule => pipe_read => vfs_read => ksys_read => do_syscall_64 => 0x966000aa -0 [003] d..4. 561.132117: block_lat: pid=0 delta=413787 stack=STACK: => __schedule => schedule => schedule_hrtimeout_range_clock => do_sys_poll => __x64_sys_poll => do_syscall_64 => 0x966000aa <...>-153 [006] d..4. 562.068407: block_lat: pid=153 delta=54 stack=STACK: => __schedule => schedule => io_schedule => rq_qos_wait => wbt_wait => __rq_qos_throttle => blk_mq_submit_bio => submit_bio_noacct_nocheck => ext4_bio_write_page => mpage_submit_page => mpage_process_page_bufs => mpage_prepare_extent_to_map => ext4_do_writepages => ext4_writepages => do_writepages => __writeback_single_inode Link: https://lkml.kernel.org/r/20230117152236.010941267@goodmis.org Cc: Masami Hiramatsu Cc: Andrew Morton Cc: Tom Zanussi Cc: Ross Zwisler Cc: Ching-lin Yu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4eb6d6b97a9f..d16929dd0f08 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -113,6 +113,10 @@ enum trace_type { #define MEM_FAIL(condition, fmt, ...) \ DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__) +#define HIST_STACKTRACE_DEPTH 16 +#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long)) +#define HIST_STACKTRACE_SKIP 5 + /* * syscalls are special, and need special handling, this is why * they are not included in trace_entries.h -- cgit v1.2.3 From c4846480831ea526bcab0ca0bf6364bfa6ed4227 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 7 Feb 2023 12:28:51 -0500 Subject: tracing: Add enabling of events to boot instances Add the format of: trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall That will create the "foo" instance and enable the sched_switch event (here were the "sched" system is explicitly specified), the irq_handler_entry event, and all events under the system initcall. Link: https://lkml.kernel.org/r/20230207173026.386114535@goodmis.org Cc: Masami Hiramatsu Cc: Andrew Morton Reviewed-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) --- Documentation/admin-guide/kernel-parameters.txt | 14 ++++++++++++++ kernel/trace/trace.c | 4 ++++ kernel/trace/trace.h | 2 ++ kernel/trace/trace_events.c | 9 ++++----- 4 files changed, 24 insertions(+), 5 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9545da5ed849..40304dc3d319 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6278,6 +6278,20 @@ /sys/kernel/tracing/instances + Events can be enabled at the time the instance is created + via: + + trace_instance=,:,: + + Note, the ":" portion is optional if the event is + unique. + + trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall + + will enable the "sched_switch" event (note, the "sched:" is optional, and + the same thing would happen if it was left off). The irq_handler_entry + event, and all events under the "initcall" system. + trace_options=[option-list] [FTRACE] Enable or disable tracer options at boot. The option-list is a comma delimited list of options diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 863716fcca49..5b16af9e7d30 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10188,6 +10188,10 @@ __init static void enable_instances(void) } /* Allow user space to delete it */ trace_array_put(tr); + + while ((tok = strsep(&curr_str, ","))) { + early_enable_events(tr, tok, true); + } } } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d16929dd0f08..f10bf804dd2b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1334,6 +1334,8 @@ DECLARE_PER_CPU(int, trace_buffered_event_cnt); void trace_buffered_event_disable(void); void trace_buffered_event_enable(void); +void early_enable_events(struct trace_array *tr, char *buf, bool disable_first); + static inline void __trace_event_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b07931ad97de..cf3fd74fa675 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3750,10 +3750,9 @@ static __init int event_trace_memsetup(void) return 0; } -static __init void -early_enable_events(struct trace_array *tr, bool disable_first) +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) { - char *buf = bootup_event_buf; char *token; int ret; @@ -3806,7 +3805,7 @@ static __init int event_trace_enable(void) */ __trace_early_add_events(tr); - early_enable_events(tr, false); + early_enable_events(tr, bootup_event_buf, false); trace_printk_start_comm(); @@ -3834,7 +3833,7 @@ static __init int event_trace_enable_again(void) if (!tr) return -ENODEV; - early_enable_events(tr, true); + early_enable_events(tr, bootup_event_buf, true); return 0; } -- cgit v1.2.3