Messages in this thread Patch in this message | | | Date | Fri, 17 Jun 2011 17:40:36 +0900 | From | Hidetoshi Seto <> | Subject | [PATCH 1/8] x86, mce: stop calling del_timer_sync() from interrupt |
| |
Function del_timer_sync() has WARN_ON(in_irq()) in it because calling it from interrupt context can cause deadlock if it interrupts the target timer running.
In MCE code, del_timer_sync() is used with on_each_cpu() in some parts for sysfs files: bank*, check_interval, cmci_disabled and ignore_ce.
However use of on_each_cpu() results in calling the function passed as the argument in the interrupt context. It means you can see a flood of warnings from del_timer_sync() by a simple file access, for example:
echo 300 > /sys/devices/system/machinecheck/machinecheck0/check_interval
Fortunately these MCE specific files are rare-used and AFAIK only few MCE geeks experience this warning on write.
To remove the warning (for my happy hacking), move timer deletion outside of the interrupt context ;-)
v2: update patch description
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> --- arch/x86/kernel/cpu/mcheck/mce.c | 22 ++++++++++++++++------ 1 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 08363b0..42fc8d2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1140,6 +1140,17 @@ static void mce_start_timer(unsigned long data) add_timer_on(t, smp_processor_id()); } +/* Must not be called from interrupt where del_timer_sync() can deadlock */ +static void mce_timer_delete_all(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + if (mce_available(&per_cpu(cpu_info, cpu))) + del_timer_sync(&per_cpu(mce_timer, cpu)); + } +} + static void mce_do_trigger(struct work_struct *work) { call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); @@ -1750,7 +1761,6 @@ static struct syscore_ops mce_syscore_ops = { static void mce_cpu_restart(void *data) { - del_timer_sync(&__get_cpu_var(mce_timer)); if (!mce_available(__this_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); @@ -1760,16 +1770,15 @@ static void mce_cpu_restart(void *data) /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { + mce_timer_delete_all(); on_each_cpu(mce_cpu_restart, NULL, 1); } /* Toggle features for corrected errors */ -static void mce_disable_ce(void *all) +static void mce_disable_cmci(void *data) { if (!mce_available(__this_cpu_ptr(&cpu_info))) return; - if (all) - del_timer_sync(&__get_cpu_var(mce_timer)); cmci_clear(); } @@ -1852,7 +1861,8 @@ static ssize_t set_ignore_ce(struct sys_device *s, if (mce_ignore_ce ^ !!new) { if (new) { /* disable ce features */ - on_each_cpu(mce_disable_ce, (void *)1, 1); + mce_timer_delete_all(); + on_each_cpu(mce_disable_cmci, NULL, 1); mce_ignore_ce = 1; } else { /* enable ce features */ @@ -1875,7 +1885,7 @@ static ssize_t set_cmci_disabled(struct sys_device *s, if (mce_cmci_disabled ^ !!new) { if (new) { /* disable cmci */ - on_each_cpu(mce_disable_ce, NULL, 1); + on_each_cpu(mce_disable_cmci, NULL, 1); mce_cmci_disabled = 1; } else { /* enable cmci */ -- 1.7.1
| |