From 9aaef96f61d93062556d34e15731f7d5869dd82e Mon Sep 17 00:00:00 2001
From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Date: Fri, 17 Jun 2011 04:40:36 -0400
Subject: [PATCH] x86, mce: Do not call del_timer_sync() in IRQ context
del_timer_sync() can cause a deadlock when called in interrupt context.
It is used with on_each_cpu() in some parts for sysfs files like bank*,
check_interval, cmci_disabled and ignore_ce.
However, use of on_each_cpu() results in calling the function passed
as the argument in interrupt context. This causes a flood of nested
warnings from del_timer_sync() (it runs on each CPU) caused even by a
simple file access like:
$ echo 300 > /sys/devices/system/machinecheck/machinecheck0/check_interval
Fortunately, these MCE-specific files are rarely used and AFAIK only few
MCE geeks experience this warning.
To remove the warning, move timer deletion outside of the interrupt
context.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
---
arch/x86/kernel/cpu/mcheck/mce.c | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 08363b042122..5b5cceec94c5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1140,6 +1140,15 @@ static void mce_start_timer(unsigned long data)
add_timer_on(t, smp_processor_id());
}
+/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+static void mce_timer_delete_all(void)
+{
+ int cpu;
+
+ for_each_online_cpu(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 +1759,6 @@ 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 +1768,15 @@ 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 +1859,8 @@ 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 +1883,7 @@ 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 */