From: Ingo Molnar <mingo@elte.hu>
To: Andrew Morton <akpm@osdl.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>, Jim Gettys <jg@laptop.org>,
John Stultz <johnstul@us.ibm.com>,
David Woodhouse <dwmw2@infradead.org>,
Arjan van de Ven <arjan@infradead.org>,
Dave Jones <davej@redhat.com>
Subject: [patch] dynticks: core, NMI watchdog fix
Date: Mon, 2 Oct 2006 08:41:27 +0200 [thread overview]
Message-ID: <20061002064127.GA20841@elte.hu> (raw)
In-Reply-To: <20061001225724.985115000@cruncher.tec.linutronix.de>
Andrew: find below a fix for a bug that could cause lockups if NO_HZ,
lockdep and the NMI watchdog are all activated. This patch comes after
dynticks-core.patch. Compile and boot tested.
Ingo
----------------->
Subject: dynticks: core, NMI watchdog fix
From: Ingo Molnar <mingo@elte.hu>
fix an NMI-watchdog interaction: we dont want to call
hrtimer_update_jiffies() in NMI contexts ...
create __irq_enter() (which is symmetric to __irq_exit())
and use it in nmi_enter() and irq_enter().
[ Note: like __irq_exit() it needs to be a macro because
hardirq.h is included early on and types like struct
task_struct are not available yet. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
--
include/linux/hardirq.h | 12 +++++++++++-
kernel/softirq.c | 5 +----
2 files changed, 12 insertions(+), 5 deletions(-)
Index: linux/include/linux/hardirq.h
===================================================================
--- linux.orig/include/linux/hardirq.h
+++ linux/include/linux/hardirq.h
@@ -106,6 +106,16 @@ static inline void account_system_vtime(
* always balanced, so the interrupted value of ->hardirq_context
* will always be restored.
*/
+#define __irq_enter() \
+ do { \
+ account_system_vtime(current); \
+ add_preempt_count(HARDIRQ_OFFSET); \
+ trace_hardirq_enter(); \
+ } while (0)
+
+/*
+ * Enter irq context (on NO_HZ, update jiffies):
+ */
extern void irq_enter(void);
/*
@@ -123,7 +133,7 @@ extern void irq_enter(void);
*/
extern void irq_exit(void);
-#define nmi_enter() do { lockdep_off(); irq_enter(); } while (0)
+#define nmi_enter() do { lockdep_off(); __irq_enter(); } while (0)
#define nmi_exit() do { __irq_exit(); lockdep_on(); } while (0)
#endif /* LINUX_HARDIRQ_H */
Index: linux/kernel/softirq.c
===================================================================
--- linux.orig/kernel/softirq.c
+++ linux/kernel/softirq.c
@@ -278,10 +278,7 @@ EXPORT_SYMBOL(do_softirq);
*/
void irq_enter(void)
{
- account_system_vtime(current);
- add_preempt_count(HARDIRQ_OFFSET);
- trace_hardirq_enter();
-
+ __irq_enter();
#ifdef CONFIG_NO_HZ
if (idle_cpu(smp_processor_id()))
hrtimer_update_jiffies();
next prev parent reply other threads:[~2006-10-02 6:50 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-10-01 22:59 [patch 00/21] high resolution timers / dynamic ticks - V2 Thomas Gleixner
2006-10-01 22:59 ` [patch 01/21] GTOD: exponential update_wall_time Thomas Gleixner
2006-10-01 23:00 ` [patch 02/21] GTOD: persistent clock support, core Thomas Gleixner
2006-10-01 23:00 ` [patch 03/21] GTOD: persistent clock support, i386 Thomas Gleixner
2006-10-01 23:00 ` [patch 04/21] time: uninline jiffies.h Thomas Gleixner
2006-10-01 23:00 ` [patch 05/21] time: fix msecs_to_jiffies() bug Thomas Gleixner
2006-10-01 23:00 ` [patch 06/21] time: fix timeout overflow Thomas Gleixner
2006-10-01 23:00 ` [patch 07/21] cleanup: uninline irq_enter() and move it into a function Thomas Gleixner
2006-10-01 23:00 ` [patch 08/21] dynticks: extend next_timer_interrupt() to use a reference jiffie Thomas Gleixner
2006-10-01 23:00 ` [patch 09/21] hrtimers: namespace and enum cleanup Thomas Gleixner
2006-10-01 23:00 ` [patch 10/21] hrtimers: clean up locking Thomas Gleixner
2006-10-01 23:00 ` [patch 11/21] hrtimers: state tracking Thomas Gleixner
2006-10-01 23:00 ` [patch 12/21] hrtimers: clean up callback tracking Thomas Gleixner
2006-10-01 23:01 ` [patch 13/21] hrtimers: Move and add documentation Thomas Gleixner
2006-10-01 23:01 ` [patch 14/21] clockevents: core Thomas Gleixner
2006-10-01 23:01 ` [patch 15/21] clockevents: drivers for i386 Thomas Gleixner
2006-10-01 23:01 ` [patch 16/21] high-res timers: core Thomas Gleixner
2006-10-02 11:50 ` Paulo Marques
2006-10-01 23:01 ` [patch 17/21] dynticks: core Thomas Gleixner
2006-10-02 6:41 ` Ingo Molnar [this message]
2006-10-02 8:54 ` [patch] dynticks: core, NMI watchdog fix, #2 Ingo Molnar
2006-10-01 23:01 ` [patch 18/21] dyntick: add nohz stats to /proc/stat Thomas Gleixner
2006-10-01 23:01 ` [patch 19/21] dynticks: i386 arch code Thomas Gleixner
2006-10-01 23:01 ` [patch 20/21] high-res timers, dynticks: enable i386 support Thomas Gleixner
2006-10-01 23:01 ` [patch 21/21] debugging feature: timer stats Thomas Gleixner
2006-10-02 5:11 ` [patch 00/21] high resolution timers / dynamic ticks - V2 Valdis.Kletnieks
2006-10-02 13:02 ` Valdis.Kletnieks
2006-10-02 13:43 ` Thomas Gleixner
2006-10-02 18:25 ` Valdis.Kletnieks
2006-10-02 18:38 ` john stultz
2006-10-02 19:08 ` Valdis.Kletnieks
2006-10-02 19:23 ` john stultz
2006-10-02 18:43 ` [patch] dynticks core: Fix idle time accounting Thomas Gleixner
2006-10-02 20:17 ` Valdis.Kletnieks
2006-10-02 21:22 ` Thomas Gleixner
2006-10-02 21:35 ` Valdis.Kletnieks
2006-10-03 20:02 ` Thomas Gleixner
2006-10-03 21:05 ` Thomas Gleixner
2006-10-04 2:33 ` Valdis.Kletnieks
2006-10-04 7:56 ` Ingo Molnar
2006-10-04 9:58 ` Valdis.Kletnieks
2006-10-03 3:23 ` [patch 00/21] high resolution timers / dynamic ticks - V2 Andrew Morton
2006-10-03 4:00 ` Andrew Morton
2006-10-03 8:38 ` Thomas Gleixner
2006-10-03 8:47 ` Ingo Molnar
2006-10-03 10:35 ` [patch] clockevents: drivers for i386, fix #2 Ingo Molnar
2006-10-04 3:36 ` Andrew Morton
2006-10-04 6:46 ` Ingo Molnar
2006-10-04 7:32 ` Andrew Morton
2006-10-04 7:41 ` Ingo Molnar
2006-10-04 8:01 ` Andrew Morton
2006-10-04 7:55 ` Ingo Molnar
2006-10-04 8:15 ` Andrew Morton
2006-10-04 10:53 ` Ingo Molnar
2006-10-04 11:19 ` Thomas Gleixner
2006-10-04 16:02 ` Andrew Morton
2006-10-04 16:20 ` Thomas Gleixner
2006-10-04 16:35 ` Ingo Molnar
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=20061002064127.GA20841@elte.hu \
--to=mingo@elte.hu \
--cc=akpm@osdl.org \
--cc=arjan@infradead.org \
--cc=davej@redhat.com \
--cc=dwmw2@infradead.org \
--cc=jg@laptop.org \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
/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