public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Pingfan Liu <kernelfans@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: Pingfan Liu <kernelfans@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Jisheng Zhang <Jisheng.Zhang@synaptics.com>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Vlastimil Babka <vbabka@suse.cz>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Guilherme G. Piccoli" <gpiccoli@canonical.com>,
	Petr Mladek <pmladek@suse.com>,
	kexec@lists.infradead.org
Subject: [PATCH 2/3] kernel/watchdog: make watchdog_touch_ts more accurate by using nanosecond
Date: Wed, 18 Nov 2020 11:36:17 +0800	[thread overview]
Message-ID: <1605670578-23681-3-git-send-email-kernelfans@gmail.com> (raw)
In-Reply-To: <1605670578-23681-1-git-send-email-kernelfans@gmail.com>

The incoming statistics of irq average number will base on the delta of
watchdog_touch_ts. Improving the accuracy of watchdog_touch_ts from second
to nanosecond can help improve the accuracy of the statistics.

Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: kexec@lists.infradead.org
To: linux-kernel@vger.kernel.org
---
 kernel/watchdog.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5abb5b2..1cc619a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -207,7 +207,7 @@ static void __lockup_detector_cleanup(void);
  * the thresholds with a factor: we make the soft threshold twice the amount of
  * time the hard threshold is.
  */
-static int get_softlockup_thresh(void)
+static unsigned int get_softlockup_thresh(void)
 {
 	return watchdog_thresh * 2;
 }
@@ -217,9 +217,9 @@ static int get_softlockup_thresh(void)
  * resolution, and we don't need to waste time with a big divide when
  * 2^30ns == 1.074s.
  */
-static unsigned long get_timestamp(void)
+static unsigned long convert_seconds(unsigned long ns)
 {
-	return running_clock() >> 30LL;  /* 2^30 ~= 10^9 */
+	return ns >> 30LL;  /* 2^30 ~= 10^9 */
 }
 
 static void set_sample_period(void)
@@ -238,7 +238,7 @@ static void set_sample_period(void)
 /* Commands for resetting the watchdog */
 static void __touch_watchdog(void)
 {
-	__this_cpu_write(watchdog_touch_ts, get_timestamp());
+	__this_cpu_write(watchdog_touch_ts, running_clock());
 }
 
 /**
@@ -289,14 +289,15 @@ void touch_softlockup_watchdog_sync(void)
 	__this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
 }
 
-static int is_softlockup(unsigned long touch_ts)
+static unsigned long is_softlockup(unsigned long touch_ts)
 {
-	unsigned long now = get_timestamp();
+	unsigned long span, now = running_clock();
 
+	span = now - touch_ts;
 	if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
 		/* Warn about unreasonable delays. */
-		if (time_after(now, touch_ts + get_softlockup_thresh()))
-			return now - touch_ts;
+		if (time_after(convert_seconds(span), (unsigned long)get_softlockup_thresh()))
+			return span;
 	}
 	return 0;
 }
@@ -340,9 +341,8 @@ static int softlockup_fn(void *data)
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
-	unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
+	unsigned long duration, touch_ts = __this_cpu_read(watchdog_touch_ts);
 	struct pt_regs *regs = get_irq_regs();
-	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
 	if (!watchdog_enabled)
@@ -410,7 +410,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		}
 
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
-			smp_processor_id(), duration,
+			smp_processor_id(), (unsigned int)convert_seconds(duration),
 			current->comm, task_pid_nr(current));
 		print_modules();
 		print_irqtrace_events(current);
-- 
2.7.5


  parent reply	other threads:[~2020-11-18  3:37 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-22  5:56 [PATCH 0/3] warn and suppress irqflood Pingfan Liu
2020-10-22  5:56 ` [PATCH 1/3] kernel/watchdog: show irq percentage if irq floods Pingfan Liu
2020-10-22  5:56 ` [PATCH 2/3] kernel/watchdog: suppress max irq when " Pingfan Liu
2020-10-22  5:56 ` [PATCH 3/3] Documentation: introduce a param "irqflood_suppress" Pingfan Liu
2020-10-22  8:37 ` [PATCH 0/3] warn and suppress irqflood Thomas Gleixner
2020-10-25 11:12   ` Pingfan Liu
2020-10-25 12:21     ` [Skiboot] " Oliver O'Halloran
2020-10-25 13:11       ` Pingfan Liu
2020-10-25 13:51         ` Oliver O'Halloran
2020-10-26 15:06     ` Guilherme Piccoli
2020-10-26 19:59       ` Thomas Gleixner
2020-10-26 20:28         ` Guilherme Piccoli
2020-10-26 21:21           ` Thomas Gleixner
2020-10-27 12:28             ` Guilherme Piccoli
2020-10-28  6:02         ` Pingfan Liu
2020-10-28 11:58           ` Thomas Gleixner
2020-10-29  6:26             ` Pingfan Liu
2020-11-06  5:53             ` Pingfan Liu
2020-11-18  3:36             ` [PATCH 0/3] use soft lockup to detect irq flood Pingfan Liu
2020-11-18  3:36               ` [PATCH 1/3] x86/irq: account the unused irq Pingfan Liu
2020-11-18  3:36               ` Pingfan Liu [this message]
2020-11-18  3:36               ` [PATCH 3/3] kernel/watchdog: use soft lockup to detect irq flood Pingfan Liu
2021-03-02  7:45             ` [PATCH 0/3] warn and suppress irqflood Sai Prakash Ranjan
2021-06-05  2:32               ` Sai Prakash Ranjan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1605670578-23681-3-git-send-email-kernelfans@gmail.com \
    --to=kernelfans@gmail.com \
    --cc=Jisheng.Zhang@synaptics.com \
    --cc=akpm@linux-foundation.org \
    --cc=gpiccoli@canonical.com \
    --cc=kexec@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=pmladek@suse.com \
    --cc=tglx@linutronix.de \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox