Re: [PATCH v4 05/53] perf machine thread: Remove exited threads by default

[Adrian Hunter]

On 2/11/23 19:56, Ian Rogers wrote:
> struct thread values hold onto references to mmaps, dsos, etc. When a
> thread exits it is necessary to clean all of this memory up by
> removing the thread from the machine's threads. Some tools require
> this doesn't happen, such as auxtrace events, perf report if offcpu
> events exist or if a task list is being generated, so add a
> symbol_conf value to make the behavior optional. When an exited thread
> is left in the machine's threads, mark it as exited.
> 
> This change relates to commit 40826c45eb0b ("perf thread: Remove
> notion of dead threads"). Dead threads were removed as they had a
> reference count of 0 and were difficult to reason about with the
> reference count checker. Here a thread is removed from threads when it
> exits, unless via symbol_conf the exited thread isn't remove and is
> marked as exited. Reference counting behaves as it normally does.
> 
> Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>

For auxtrace:

Reviewed-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>

> ---
>  tools/perf/builtin-report.c   |  7 +++++++
>  tools/perf/util/machine.c     | 10 +++++++---
>  tools/perf/util/session.c     |  5 +++++
>  tools/perf/util/symbol_conf.h |  3 ++-
>  tools/perf/util/thread.h      | 14 ++++++++++++++
>  5 files changed, 35 insertions(+), 4 deletions(-)
> 
> diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
> index 9cb1da2dc0c0..121a2781323c 100644
> --- a/tools/perf/builtin-report.c
> +++ b/tools/perf/builtin-report.c
> @@ -1426,6 +1426,13 @@ int cmd_report(int argc, const char **argv)
>  	if (ret < 0)
>  		goto exit;
>  
> +	/*
> +	 * tasks_mode require access to exited threads to list those that are in
> +	 * the data file. Off-cpu events are synthesized after other events and
> +	 * reference exited threads.
> +	 */
> +	symbol_conf.keep_exited_threads = true;
> +
>  	annotation_options__init(&report.annotation_opts);
>  
>  	ret = perf_config(report__config, &report);
> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> index 90c750150b19..a985d004aa8d 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -2157,9 +2157,13 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
>  	if (dump_trace)
>  		perf_event__fprintf_task(event, stdout);
>  
> -	if (thread != NULL)
> -		thread__put(thread);
> -
> +	if (thread != NULL) {
> +		if (symbol_conf.keep_exited_threads)
> +			thread__set_exited(thread, /*exited=*/true);
> +		else
> +			machine__remove_thread(machine, thread);
> +	}
> +	thread__put(thread);
>  	return 0;
>  }
>  
> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> index 1e9aa8ed15b6..c6afba7ab1a5 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -115,6 +115,11 @@ static int perf_session__open(struct perf_session *session, int repipe_fd)
>  		return -1;
>  	}
>  
> +	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) {
> +		/* Auxiliary events may reference exited threads, hold onto dead ones. */
> +		symbol_conf.keep_exited_threads = true;
> +	}
> +
>  	if (perf_data__is_pipe(data))
>  		return 0;
>  
> diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
> index 2b2fb9e224b0..6040286e07a6 100644
> --- a/tools/perf/util/symbol_conf.h
> +++ b/tools/perf/util/symbol_conf.h
> @@ -43,7 +43,8 @@ struct symbol_conf {
>  			disable_add2line_warn,
>  			buildid_mmap2,
>  			guest_code,
> -			lazy_load_kernel_maps;
> +			lazy_load_kernel_maps,
> +			keep_exited_threads;
>  	const char	*vmlinux_name,
>  			*kallsyms_name,
>  			*source_prefix,
> diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
> index e79225a0ea46..0df775b5c110 100644
> --- a/tools/perf/util/thread.h
> +++ b/tools/perf/util/thread.h
> @@ -36,13 +36,22 @@ struct thread_rb_node {
>  };
>  
>  DECLARE_RC_STRUCT(thread) {
> +	/** @maps: mmaps associated with this thread. */
>  	struct maps		*maps;
>  	pid_t			pid_; /* Not all tools update this */
> +	/** @tid: thread ID number unique to a machine. */
>  	pid_t			tid;
> +	/** @ppid: parent process of the process this thread belongs to. */
>  	pid_t			ppid;
>  	int			cpu;
>  	int			guest_cpu; /* For QEMU thread */
>  	refcount_t		refcnt;
> +	/**
> +	 * @exited: Has the thread had an exit event. Such threads are usually
> +	 * removed from the machine's threads but some events/tools require
> +	 * access to dead threads.
> +	 */
> +	bool			exited;
>  	bool			comm_set;
>  	int			comm_len;
>  	struct list_head	namespaces_list;
> @@ -189,6 +198,11 @@ static inline refcount_t *thread__refcnt(struct thread *thread)
>  	return &RC_CHK_ACCESS(thread)->refcnt;
>  }
>  
> +static inline void thread__set_exited(struct thread *thread, bool exited)
> +{
> +	RC_CHK_ACCESS(thread)->exited = exited;
> +}
> +
>  static inline bool thread__comm_set(const struct thread *thread)
>  {
>  	return RC_CHK_ACCESS(thread)->comm_set;