From: "John Kacur" <jkacur@gmail.com>
To: "Steven Rostedt" <rostedt@goodmis.org>
Cc: rt-users <linux-rt-users@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: tracing WARN_ON in rt kernel
Date: Wed, 6 Aug 2008 11:38:26 +0200 [thread overview]
Message-ID: <520f0cf10808060238r513c2f35l16c0da5511cea0f1@mail.gmail.com> (raw)
Hi Steve, the following is one for you.
The kernel is 2.6.26.1 plus the 2.6.26-rt1 patch (yes it applies
against 2.6.26.1) and some of the patches that were discussed in the
lists. I don't think it is relevant which patches, but if you need an
exact list I will provide it.
WARNING: at kernel/trace/trace_hist.c:396
tracing_hist_preempt_stop+0x23d/0x301()
Modules linked in:
Pid: 1, comm: init Not tainted 2.6.26.1-rt1.jk #4
Call Trace:
[<ffffffff802397f4>] warn_on_slowpath+0x5d/0x99
[<ffffffff80212a0d>] ? native_sched_clock+0x2b/0x76
[<ffffffff802127d5>] ? sched_clock+0x9/0xc
[<ffffffff80283231>] ? ftrace_now+0x9/0xb
[<ffffffff80288439>] ? tracing_hist_preempt_stop+0xd9/0x301
[<ffffffff8020b48c>] ? do_notify_resume+0x14/0x8ef
[<ffffffff80286499>] ? trace_hardirqs_on+0x1b/0x138
[<ffffffff8020b48c>] ? do_notify_resume+0x14/0x8ef
[<ffffffff8028859d>] tracing_hist_preempt_stop+0x23d/0x301
[<ffffffff8020c4db>] ? sysret_signal+0x30/0x4f
[<ffffffff80286499>] trace_hardirqs_on+0x1b/0x138
[<ffffffff8020b478>] ? do_notify_resume+0x0/0x8ef
[<ffffffff8020c4db>] ? sysret_signal+0x30/0x4f
[<ffffffff8020b4e6>] do_notify_resume+0x6e/0x8ef
[<ffffffff8046ce35>] ? rt_spin_lock+0xe/0x10
[<ffffffff8024ea2a>] ? remove_wait_queue+0x3e/0x43
[<ffffffff8023d214>] ? do_wait+0xb6b/0xbf7
[<ffffffff80212a0d>] ? native_sched_clock+0x2b/0x76
[<ffffffff802127d5>] ? sched_clock+0x9/0xc
[<ffffffff80283231>] ? ftrace_now+0x9/0xb
[<ffffffff80288637>] ? tracing_hist_preempt_stop+0x2d7/0x301
[<ffffffff8020c4b0>] ? sysret_signal+0x5/0x4f
[<ffffffff8046ca94>] ? trace_hardirqs_on_thunk+0x3a/0x3c
[<ffffffff8020c4db>] ? sysret_signal+0x30/0x4f
[<ffffffff8020c8b7>] ptregscall_common+0x67/0xb0
---------------------------
| preempt count: 00000000 ]
| 0-level deep critical section nesting:
----------------------------------------
This above is triggered by the WARN_ON in the following code in
function tracing_hist_preempt_stop()
#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
if (((!irqs_on && !irqs_disabled()) ||
(irqs_on && !preempt_count()) ||
(irqs_on == TRACE_STOP)) &&
per_cpu(hist_preemptirqsoff_tracing, cpu)) {
WARN_ON(!preempt_count() && !irqs_disabled());
if (1 || !stop_set)
stop = ftrace_now(cpu);
start = per_cpu(hist_preemptirqsoff_start, cpu);
latency = (long)nsecs_to_usecs(stop - start);
if (latency > 1000000) {
printk("%d: latency = %ld (%lu)\n", __LINE__, latency, latency);
printk("%d: start=%Ld stop=%Ld\n", __LINE__, start, stop);
}
barrier();
per_cpu(hist_preemptirqsoff_tracing, cpu) = 0;
latency_hist(PREEMPT_INTERRUPT_LATENCY, cpu, latency);
}
#endif
reply other threads:[~2008-08-06 9:38 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=520f0cf10808060238r513c2f35l16c0da5511cea0f1@mail.gmail.com \
--to=jkacur@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=rostedt@goodmis.org \
/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;
as well as URLs for NNTP newsgroup(s).