linux-kernel - Re: [PATCH/RFC v9 2/2] Use trace events to report stalls

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: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date:	Fri, 19 Aug 2011 15:05:42 -0400
From:	Jason Baron <jbaron@...hat.com>
To:	Alex Neronskiy <zakmagnus@...omium.org>
Cc:	linux-kernel@...r.kernel.org, peterz@...radead.org,
	Ingo Molnar <mingo@...e.hu>, Don Zickus <dzickus@...hat.com>,
	Mandeep Singh Baines <msb@...omium.org>, rostedt@...dmis.org
Subject: Re: [PATCH/RFC v9 2/2] Use trace events to report stalls

On Wed, Aug 17, 2011 at 01:36:09PM -0700, Alex Neronskiy wrote:
> Signed-off-by: Alex Neronskiy <zakmagnus@...omium.org>
> ---
> This outputs both the numerical representation of the stall as well
> as a stack trace. The trace, unlike the number, is always output,
> regardless of what debug/tracing/events/watchdog/enable says. I
> don't know how to hook into that.
> 

(adding Steve to 'cc)

Yes, it would be nice to make the dump stack contigent on the
tracepoints...that's what you want?

If so, maybe we could have TP_fast_assign fill a buffer which is output
via TP_printk, or else TP_printk could take an optional callback
function...

Thanks,

-Jason


>  kernel/trace_watchdog.h |   43 +++++++++++++++++++++++++++++++++++++++++++
>  kernel/watchdog.c       |   23 +++++++++++------------
>  2 files changed, 54 insertions(+), 12 deletions(-)
>  create mode 100644 kernel/trace_watchdog.h
> 
> diff --git a/kernel/trace_watchdog.h b/kernel/trace_watchdog.h
> new file mode 100644
> index 0000000..1401d27f
> --- /dev/null
> +++ b/kernel/trace_watchdog.h
> @@ -0,0 +1,43 @@
> +#undef TRACE_SYSTEM
> +#define TRACE_SYSTEM watchdog
> +
> +#if !defined(_TRACE_WATCHDOG_H) || defined(TRACE_HEADER_MULTI_READ)
> +#define _TRACE_WATCHDOG_H
> +
> +#include <linux/tracepoint.h>
> +#include <linux/stacktrace.h>
> +
> +TRACE_EVENT(soft_stall,
> +	TP_PROTO(unsigned long stall),
> +	TP_ARGS(stall),
> +	TP_STRUCT__entry(
> +		__field(unsigned long, stall)
> +	),
> +	TP_fast_assign(
> +		__entry->stall = stall;
> +	),
> +	TP_printk("Soft stall: %lums", __entry->stall)
> +);
> +
> +#ifdef CONFIG_HARDLOCKUP_DETECTOR
> +TRACE_EVENT(hard_stall,
> +	TP_PROTO(unsigned long stall),
> +	TP_ARGS(stall),
> +	TP_STRUCT__entry(
> +		__field(unsigned long, stall)
> +	),
> +	TP_fast_assign(
> +		__entry->stall = stall;
> +	),
> +	TP_printk("Hard stall: %lu", __entry->stall)
> +);
> +#endif /* CONFIG_HARDLOCKUP_DETECTOR */
> +
> +#endif /* _TRACE_WATCHDOG_H */
> +
> +#undef TRACE_INCLUDE_PATH
> +#undef TRACE_INCLUDE_FILE
> +#define TRACE_INCLUDE_PATH .
> +
> +#define TRACE_INCLUDE_FILE trace_watchdog
> +#include <trace/define_trace.h>
> diff --git a/kernel/watchdog.c b/kernel/watchdog.c
> index d4c51cc..18385ed 100644
> --- a/kernel/watchdog.c
> +++ b/kernel/watchdog.c
> @@ -27,6 +27,9 @@
>  #include <asm/irq_regs.h>
>  #include <linux/perf_event.h>
>  
> +#define CREATE_TRACE_POINTS
> +#include "trace_watchdog.h"
> +
>  int watchdog_enabled = 1;
>  int __read_mostly watchdog_thresh = 10;
>  static unsigned long worst_softstall;
> @@ -208,7 +211,7 @@ void touch_softlockup_watchdog_sync(void)
>  
>  #ifdef CONFIG_HARDLOCKUP_DETECTOR
>  /* watchdog detector functions */
> -static void update_hardstall(unsigned long stall, int this_cpu)
> +static void update_hardstall(unsigned long stall)
>  {
>  	int update_stall = 0;
>  
> @@ -222,10 +225,8 @@ static void update_hardstall(unsigned long stall, int this_cpu)
>  	}
>  
>  	if (update_stall) {
> -		printk(KERN_WARNING "LOCKUP may be in progress!"
> -			"Worst hard stall seen on CPU#%d: %lu interrupts missed\n",
> -			this_cpu, stall);
> -		dump_stack();
> +		trace_hard_stall(stall);
> +		trace_dump_stack();
>  	}
>  }
>  
> @@ -245,12 +246,12 @@ static int is_hardlockup(int this_cpu)
>  	if (ints_missed >= hardlockup_thresh)
>  		return 1;
>  
> -	update_hardstall(ints_missed, this_cpu);
> +	update_hardstall(ints_missed);
>  	return 0;
>  }
>  #endif
>  
> -static void update_softstall(unsigned long stall, int this_cpu)
> +static void update_softstall(unsigned long stall)
>  {
>  	int update_stall = 0;
>  	if (stall > get_softstall_thresh() &&
> @@ -264,10 +265,8 @@ static void update_softstall(unsigned long stall, int this_cpu)
>  	}
>  
>  	if (update_stall) {
> -		printk(KERN_WARNING "LOCKUP may be in progress!"
> -				"Worst soft stall seen on CPU#%d: %lums\n",
> -				this_cpu, stall);
> -		dump_stack();
> +		trace_soft_stall(stall);
> +		trace_dump_stack();
>  	}
>  }
>  
> @@ -280,7 +279,7 @@ static int is_softlockup(unsigned long touch_ts, int this_cpu)
>  	if (time_after(now, touch_ts + 1000 * get_softlockup_thresh()))
>  		return stall;
>  
> -	update_softstall(stall, this_cpu);
> +	update_softstall(stall);
>  
>  	return 0;
>  }
> -- 
> 1.7.3.1
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/