[PATCH 4/5] watchdog: control hard lockup detection default

From: Don Zickus
Date: Mon Aug 11 2014 - 10:50:19 EST


From: Ulrich Obergfell <uobergfe@xxxxxxxxxx>

In some cases we don't want hard lockup detection enabled by default.
An example is when running as a guest. Introduce

watchdog_enable_hardlockup_detector(bool)

allowing those cases to disable hard lockup detection. This must be
executed early by the boot processor from e.g. smp_prepare_boot_cpu,
in order to allow kernel command line arguments to override it, as
well as to avoid hard lockup detection being enabled before we've
had a chance to indicate that it's unwanted. In summary,

initial boot: default=enabled
smp_prepare_boot_cpu
watchdog_enable_hardlockup_detector(false): default=disabled
cmdline has 'nmi_watchdog=1': default=enabled

The running kernel still has the ability to enable/disable at any
time with /proc/sys/kernel/nmi_watchdog us usual. However even
when the default has been overridden /proc/sys/kernel/nmi_watchdog
will initially show '1'. To truly turn it on one must disable/enable
it, i.e.
echo 0 > /proc/sys/kernel/nmi_watchdog
echo 1 > /proc/sys/kernel/nmi_watchdog

This patch will be immediately useful for KVM with the next patch
of this series. Other hypervisor guest types may find it useful as
well.

Signed-off-by: Ulrich Obergfell <uobergfe@xxxxxxxxxx>
Signed-off-by: Andrew Jones <drjones@xxxxxxxxxx>
Signed-off-by: Don Zickus <dzickus@xxxxxxxxxx>
---
include/linux/nmi.h | 9 +++++++++
kernel/watchdog.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 447775e..72aacf4 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -17,11 +17,20 @@
#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
#include <asm/nmi.h>
extern void touch_nmi_watchdog(void);
+extern void watchdog_enable_hardlockup_detector(bool val);
+extern bool watchdog_hardlockup_detector_is_enabled(void);
#else
static inline void touch_nmi_watchdog(void)
{
touch_softlockup_watchdog();
}
+static inline void watchdog_enable_hardlockup_detector(bool)
+{
+}
+static inline bool watchdog_hardlockup_detector_is_enabled(void)
+{
+ return true;
+}
#endif

/*
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 0838685..8cb24dc 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -59,6 +59,25 @@ static unsigned long soft_lockup_nmi_warn;
static int hardlockup_panic =
CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;

+static bool hardlockup_detector_enabled = true;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void watchdog_enable_hardlockup_detector(bool val)
+{
+ hardlockup_detector_enabled = val;
+}
+
+bool watchdog_hardlockup_detector_is_enabled(void)
+{
+ return hardlockup_detector_enabled;
+}
+
static int __init hardlockup_panic_setup(char *str)
{
if (!strncmp(str, "panic", 5))
@@ -67,6 +86,14 @@ static int __init hardlockup_panic_setup(char *str)
hardlockup_panic = 0;
else if (!strncmp(str, "0", 1))
watchdog_user_enabled = 0;
+ else if (!strncmp(str, "1", 1) || !strncmp(str, "2", 1)) {
+ /*
+ * Setting 'nmi_watchdog=1' or 'nmi_watchdog=2' (legacy option)
+ * has the same effect.
+ */
+ watchdog_user_enabled = 1;
+ watchdog_enable_hardlockup_detector(true);
+ }
return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -462,6 +489,15 @@ static int watchdog_nmi_enable(unsigned int cpu)
struct perf_event_attr *wd_attr;
struct perf_event *event = per_cpu(watchdog_ev, cpu);

+ /*
+ * Some kernels need to default hard lockup detection to
+ * 'disabled', for example a guest on a hypervisor.
+ */
+ if (!watchdog_hardlockup_detector_is_enabled()) {
+ event = ERR_PTR(-ENOENT);
+ goto handle_err;
+ }
+
/* is it already setup and enabled? */
if (event && event->state > PERF_EVENT_STATE_OFF)
goto out;
@@ -476,6 +512,7 @@ static int watchdog_nmi_enable(unsigned int cpu)
/* Try to register using hardware perf events */
event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);

+handle_err:
/* save cpu0 error for future comparision */
if (cpu == 0 && IS_ERR(event))
cpu0_err = PTR_ERR(event);
@@ -621,11 +658,13 @@ int proc_dowatchdog(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int err, old_thresh, old_enabled;
+ bool old_hardlockup;
static DEFINE_MUTEX(watchdog_proc_mutex);

mutex_lock(&watchdog_proc_mutex);
old_thresh = ACCESS_ONCE(watchdog_thresh);
old_enabled = ACCESS_ONCE(watchdog_user_enabled);
+ old_hardlockup = watchdog_hardlockup_detector_is_enabled();

err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (err || !write)
@@ -637,15 +676,22 @@ int proc_dowatchdog(struct ctl_table *table, int write,
* disabled. The 'watchdog_running' variable check in
* watchdog_*_all_cpus() function takes care of this.
*/
- if (watchdog_user_enabled && watchdog_thresh)
+ if (watchdog_user_enabled && watchdog_thresh) {
+ /*
+ * Prevent a change in watchdog_thresh accidentally overriding
+ * the enablement of the hardlockup detector.
+ */
+ if (watchdog_user_enabled != old_enabled)
+ watchdog_enable_hardlockup_detector(true);
err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
- else
+ } else
watchdog_disable_all_cpus();

/* Restore old values on failure */
if (err) {
watchdog_thresh = old_thresh;
watchdog_user_enabled = old_enabled;
+ watchdog_enable_hardlockup_detector(old_hardlockup);
}
out:
mutex_unlock(&watchdog_proc_mutex);
--
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/