From 3ca55ca225d7627e76fcfe2894740c4f615ff2e0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 2 Apr 2025 11:09:25 -0700 Subject: [PATCH] exit: move and extend sched_process_exit() tracepoint It is useful to be able to access current->mm at task exit to, say, record a bunch of VMA information right before the task exits (e.g., for stack symbolization reasons when dealing with short-lived processes that exit in the middle of profiling session). Currently, trace_sched_process_exit() is triggered after exit_mm() which resets current->mm to NULL making this tracepoint unsuitable for inspecting and recording task's mm_struct-related data when tracing process lifetimes. There is a particularly suitable place, though, right after taskstats_exit() is called, but before we do exit_mm() and other exit_*() resource teardowns. taskstats performs a similar kind of accounting that some applications do with BPF, and so co-locating them seems like a good fit. So that's where trace_sched_process_exit() is moved with this patch. Also, existing trace_sched_process_exit() tracepoint is notoriously missing `group_dead` flag that is certainly useful in practice and some of our production applications have to work around this. So plumb `group_dead` through while at it, to have a richer and more complete tracepoint. Note that we can't use sched_process_template anymore, and so we use TRACE_EVENT()-based tracepoint definition. But all the field names and order, as well as assign and output logic remain intact. We just add one extra field at the end in backwards-compatible way. [andrii@kernel.org: document sched_process_exit and sched_process_template relation] Link: https://lkml.kernel.org/r/20250403174120.4087794-1-andrii@kernel.org Link: https://lkml.kernel.org/r/20250402180925.90914-1-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Steven Rostedt (Google) Acked-by: Oleg Nesterov Suggested-by: Ingo Molnar Cc: Alexander Potapenko Cc: Christian Brauner Cc: "Masami Hiramatsu (Google)" Cc: Mathieu Desnoyers Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/trace/events/sched.h | 34 ++++++++++++++++++++++++++++++---- kernel/exit.c | 2 +- 2 files changed, 31 insertions(+), 5 deletions(-) diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 8994e97d86c13..3bec9fb73a363 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -326,11 +326,37 @@ DEFINE_EVENT(sched_process_template, sched_process_free, TP_ARGS(p)); /* - * Tracepoint for a task exiting: + * Tracepoint for a task exiting. + * Note, it's a superset of sched_process_template and should be kept + * compatible as much as possible. sched_process_exits has an extra + * `group_dead` argument, so sched_process_template can't be used, + * unfortunately, just like sched_migrate_task above. */ -DEFINE_EVENT(sched_process_template, sched_process_exit, - TP_PROTO(struct task_struct *p), - TP_ARGS(p)); +TRACE_EVENT(sched_process_exit, + + TP_PROTO(struct task_struct *p, bool group_dead), + + TP_ARGS(p, group_dead), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( bool, group_dead ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ + __entry->group_dead = group_dead; + ), + + TP_printk("comm=%s pid=%d prio=%d group_dead=%s", + __entry->comm, __entry->pid, __entry->prio, + __entry->group_dead ? "true" : "false" + ) +); /* * Tracepoint for waiting on task to unschedule: diff --git a/kernel/exit.c b/kernel/exit.c index 1b51dc099f1e0..f1db86dcbeb10 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -936,12 +936,12 @@ void __noreturn do_exit(long code) tsk->exit_code = code; taskstats_exit(tsk, group_dead); + trace_sched_process_exit(tsk, group_dead); exit_mm(); if (group_dead) acct_process(); - trace_sched_process_exit(tsk); exit_sem(tsk); exit_shm(tsk); -- 2.47.2