linux-kernel - Re: [RFC PATCH v4 5/7] sched, tracing: add to report task state in symbolic chars

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230802110701.5227346d@gandalf.local.home>
Date:   Wed, 2 Aug 2023 11:07:01 -0400
From:   Steven Rostedt <rostedt@...dmis.org>
To:     Ze Gao <zegao2021@...il.com>
Cc:     Adrian Hunter <adrian.hunter@...el.com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Ian Rogers <irogers@...gle.com>,
        Ingo Molnar <mingo@...hat.com>, Jiri Olsa <jolsa@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
        linux-trace-kernel@...r.kernel.org,
        linux-trace-devel@...r.kernel.org, Ze Gao <zegao@...cent.com>
Subject: Re: [RFC PATCH v4 5/7] sched, tracing: add to report task state in
 symbolic chars

On Wed,  2 Aug 2023 08:10:00 -0400
Ze Gao <zegao2021@...il.com> wrote:

> From: Ze Gao <zegao2021@...il.com>
> 
> Internal representations of task state are likely to be changed
> or ordered, and reporting them to userspace without exporting
> them as part of API is basically wrong, which can easily break
> a userspace observability tool as kernel evolves. For example,
> perf suffers from this and still reports wrong states as of this
> writing.
> 
> OTOH, some masqueraded states like TASK_REPORT_IDLE and
> TASK_REPORT_MAX are also reported inadvertently, which confuses
> things even more and most userspace tools do not even take them
> into consideration.
> 
> So add a new variable in company with the old raw value to
> report task state in symbolic chars, which are self-explaining
> and no further translation is needed. Of course this does not
> break any userspace tool.
> 
> Note for PREEMPT_ACTIVE, we introduce 'p' to report it and use
> the old conventions for the rest.
> 
> Signed-off-by: Ze Gao <zegao@...cent.com>
> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@...nel.org>
> Acked-by: Ian Rogers <irogers@...gle.com>
> ---
>  include/trace/events/sched.h | 44 ++++++++++++++++++++++--------------
>  1 file changed, 27 insertions(+), 17 deletions(-)
> 
> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
> index 7d34db20b2c6..1c7b94793495 100644
> --- a/include/trace/events/sched.h
> +++ b/include/trace/events/sched.h
> @@ -6,6 +6,7 @@
>  #define _TRACE_SCHED_H
>  
>  #include <linux/kthread.h>
> +#include <linux/sched.h>
>  #include <linux/sched/numa_balancing.h>
>  #include <linux/tracepoint.h>
>  #include <linux/binfmts.h>
> @@ -214,6 +215,27 @@ static inline int __trace_sched_switch_state(bool preempt,
>  
>  	return state ? (1 << (state - 1)) : state;
>  }
> +
> +static inline char __trace_sched_switch_state_char(bool preempt,
> +						   unsigned int prev_state,
> +						   struct task_struct *p)
> +{
> +	long state;
> +
> +#ifdef CONFIG_SCHED_DEBUG
> +	BUG_ON(p != current);

BUG? Why not WARN_ON()?

-- Steve

> +#endif /* CONFIG_SCHED_DEBUG */
> +
> +	/*
> +	 * For PREEMPT_ACTIVE, we introduce 'p' to report it and use the old
> +	 * conventions for the rest.
> +	 */
> +	if (preempt)
> +		return 'p';
> +
> +	state = __task_state_index(prev_state, p->exit_state);
> +	return task_index_to_char(state);
> +}
>  #endif /* CREATE_TRACE_POINTS */
>  
>  /*
> @@ -236,6 +258,7 @@ TRACE_EVENT(sched_switch,
>  		__field(	int,	prev_state			)
>  		__array(	char,	prev_comm,	TASK_COMM_LEN	)
>  		__array(	char,	next_comm,	TASK_COMM_LEN	)
> +		__field(	char,	prev_state_char			)
>  	),
>  
>  	TP_fast_assign(
> @@ -246,26 +269,13 @@ TRACE_EVENT(sched_switch,
>  		__entry->prev_state		= __trace_sched_switch_state(preempt, prev_state, prev);
>  		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
>  		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
> +		__entry->prev_state_char	= __trace_sched_switch_state_char(preempt, prev_state, prev);
>  		/* XXX SCHED_DEADLINE */
>  	),
>  
> -	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
> -		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
> -
> -		(__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
> -		  __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
> -				{ TASK_INTERRUPTIBLE, "S" },
> -				{ TASK_UNINTERRUPTIBLE, "D" },
> -				{ __TASK_STOPPED, "T" },
> -				{ __TASK_TRACED, "t" },
> -				{ EXIT_DEAD, "X" },
> -				{ EXIT_ZOMBIE, "Z" },
> -				{ TASK_PARKED, "P" },
> -				{ TASK_DEAD, "I" }) :
> -		  "R",
> -
> -		__entry->prev_state & TASK_REPORT_MAX ? "+" : "",
> -		__entry->next_comm, __entry->next_pid, __entry->next_prio)
> +	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%c ==> next_comm=%s next_pid=%d next_prio=%d",
> +		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio, __entry->prev_state_char, __entry->next_comm,
> +		__entry->next_pid, __entry->next_prio)
>  );
>  
>  /*