[PATCH 3/5] watchdog: Split up config options

From: Nicholas Piggin
Date: Mon May 22 2017 - 09:04:49 EST

Split SOFTLOCKUP_DETECTOR from LOCKUP_DETECTOR, and split
HARDLOCKUP_DETECTOR_PERF from HARDLOCKUP_DETECTOR.

LOCKUP_DETECTOR provides the boot, sysctl, and programming interfaces
for lockup detectors. An architecture that defines HAVE_NMI_WATCHDOG
need not use this this if it has a very basic watchdog or uses its own
options and interfaces (e.g., sparc). touch_nmi_watchdog() will
continue to call their arch_touch_nmi_watchdog().

HARDLOCKUP_DETECTOR_PERF is the perf-based lockup detector.

HARDLOCKUP_DETECTOR is the framework for arch NMI_WATCHDOG hard lockup
detectors that conform to the LOCKUP_DETECTOR interfaces.

Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx>
---
arch/powerpc/kernel/setup_64.c | 2 +-
arch/x86/kernel/apic/hw_nmi.c | 2 +-
include/linux/nmi.h | 35 ++++--
kernel/Makefile | 2 +-
kernel/sysctl.c | 18 ++--
kernel/watchdog.c | 238 ++++++++++++++++++++++++++---------------
kernel/watchdog_hld.c | 32 ------
lib/Kconfig.debug | 27 +++--
8 files changed, 212 insertions(+), 144 deletions(-)

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f35ff9dea4fb..ab650905f75a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -727,7 +727,7 @@ struct ppc_pci_io ppc_pci_io;
EXPORT_SYMBOL(ppc_pci_io);
#endif

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
u64 hw_nmi_get_sample_period(int watchdog_thresh)
{
return ppc_proc_freq * watchdog_thresh;
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c73c9fb281e1..d6f387780849 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -19,7 +19,7 @@
#include <linux/init.h>
#include <linux/delay.h>

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
u64 hw_nmi_get_sample_period(int watchdog_thresh)
{
return (u64)(cpu_khz) * 1000 * watchdog_thresh;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 66b2cf6cd77c..e783d96b9467 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -11,13 +11,21 @@
#endif

#ifdef CONFIG_LOCKUP_DETECTOR
+void lockup_detector_init(void);
+#else
+static inline void lockup_detector_init(void)
+{
+}
+#endif
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
extern void touch_softlockup_watchdog_sched(void);
extern void touch_softlockup_watchdog(void);
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern unsigned int softlockup_panic;
-extern unsigned int hardlockup_panic;
-void lockup_detector_init(void);
+extern int soft_watchdog_enabled;
+extern atomic_t watchdog_park_in_progress;
#else
static inline void touch_softlockup_watchdog_sched(void)
{
@@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void)
static inline void touch_all_softlockup_watchdogs(void)
{
}
-static inline void lockup_detector_init(void)
-{
-}
#endif

#ifdef CONFIG_DETECT_HUNG_TASK
@@ -61,14 +66,19 @@ static inline void reset_hung_task_detector(void)
#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)

-#if defined(CONFIG_HARDLOCKUP_DETECTOR)
-extern void hld_touch_nmi_watchdog(void);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
extern void hardlockup_detector_disable(void);
+extern unsigned int hardlockup_panic;
#else
-static inline void hld_touch_nmi_watchdog(void) {}
static inline void hardlockup_detector_disable(void) {}
#endif

+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
+extern void hld_touch_nmi_watchdog(void);
+#else
+static inline void hld_touch_nmi_watchdog(void) {}
+#endif
+
/**
* touch_nmi_watchdog - restart NMI watchdog timeout.
*
@@ -140,15 +150,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu)
}
#endif

-#ifdef CONFIG_LOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
u64 hw_nmi_get_sample_period(int watchdog_thresh);
+#endif
+
+#ifdef CONFIG_LOCKUP_DETECTOR
extern int nmi_watchdog_enabled;
-extern int soft_watchdog_enabled;
extern int watchdog_user_enabled;
extern int watchdog_thresh;
extern unsigned long watchdog_enabled;
+extern struct cpumask watchdog_cpumask;
extern unsigned long *watchdog_cpumask_bits;
-extern atomic_t watchdog_park_in_progress;
+extern int __read_mostly watchdog_suspended;
#ifdef CONFIG_SMP
extern int sysctl_softlockup_all_cpu_backtrace;
extern int sysctl_hardlockup_all_cpu_backtrace;
diff --git a/kernel/Makefile b/kernel/Makefile
index 72aa080f91f0..4cb8e8b23c6e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -82,7 +82,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4dfba1a76cc3..fa37faa89143 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -873,13 +873,21 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_nmi_watchdog,
.extra1 = &zero,
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
.extra2 = &one,
#else
.extra2 = &zero,
#endif
},
{
+ .procname = "watchdog_cpumask",
+ .data = &watchdog_cpumask_bits,
+ .maxlen = NR_CPUS,
+ .mode = 0644,
+ .proc_handler = proc_watchdog_cpumask,
+ },
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+ {
.procname = "soft_watchdog",
.data = &soft_watchdog_enabled,
.maxlen = sizeof (int),
@@ -889,13 +897,6 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
{
- .procname = "watchdog_cpumask",
- .data = &watchdog_cpumask_bits,
- .maxlen = NR_CPUS,
- .mode = 0644,
- .proc_handler = proc_watchdog_cpumask,
- },
- {
.procname = "softlockup_panic",
.data = &softlockup_panic,
.maxlen = sizeof(int),
@@ -904,6 +905,7 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
+#endif
#ifdef CONFIG_HARDLOCKUP_DETECTOR
{
.procname = "hardlockup_panic",
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 03e0b69bb5bf..deb010505646 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,15 +29,55 @@
#include <linux/kvm_para.h>
#include <linux/kthread.h>

+/* Watchdog configuration */
static DEFINE_MUTEX(watchdog_proc_mutex);

-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+int __read_mostly nmi_watchdog_enabled;
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
+
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+unsigned int __read_mostly hardlockup_panic =
+ CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+/*
+ * 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 hardlockup_detector_disable(void)
+{
+ watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+}
+
+static int __init hardlockup_panic_setup(char *str)
+{
+ if (!strncmp(str, "panic", 5))
+ hardlockup_panic = 1;
+ else if (!strncmp(str, "nopanic", 7))
+ hardlockup_panic = 0;
+ else if (!strncmp(str, "0", 1))
+ watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+ else if (!strncmp(str, "1", 1))
+ watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+ return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+
#else
unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
#endif
-int __read_mostly nmi_watchdog_enabled;
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
int __read_mostly soft_watchdog_enabled;
+#endif
+
int __read_mostly watchdog_user_enabled;
int __read_mostly watchdog_thresh = 10;

@@ -45,15 +85,9 @@ int __read_mostly watchdog_thresh = 10;
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
#endif
-static struct cpumask watchdog_cpumask __read_mostly;
+struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);

-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
- for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
-
/*
* The 'watchdog_running' variable is set to 1 when the watchdog threads
* are registered/started and is set to 0 when the watchdog threads are
@@ -72,7 +106,27 @@ static int __read_mostly watchdog_running;
* of 'watchdog_running' cannot change while the watchdog is deactivated
* temporarily (see related code in 'proc' handlers).
*/
-static int __read_mostly watchdog_suspended;
+int __read_mostly watchdog_suspended;
+
+/*
+ * These functions can be overridden if an architecture implements its
+ * own hardlockup detector.
+ */
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+ return 0;
+}
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+}
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+
+/* Helper for online, unparked cpus. */
+#define for_each_watchdog_cpu(cpu) \
+ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);

static u64 __read_mostly sample_period;

@@ -120,6 +174,7 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str)
return 1;
}
__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
static int __init hardlockup_all_cpu_backtrace_setup(char *str)
{
sysctl_hardlockup_all_cpu_backtrace =
@@ -128,6 +183,7 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str)
}
__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
#endif
+#endif

/*
* Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -213,18 +269,6 @@ void touch_softlockup_watchdog_sync(void)
__this_cpu_write(watchdog_touch_ts, 0);
}

-/* watchdog detector functions */
-bool is_hardlockup(void)
-{
- unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
- if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
- return true;
-
- __this_cpu_write(hrtimer_interrupts_saved, hrint);
- return false;
-}
-
static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp();
@@ -237,21 +281,21 @@ static int is_softlockup(unsigned long touch_ts)
return 0;
}

-static void watchdog_interrupt_count(void)
+/* watchdog detector functions */
+bool is_hardlockup(void)
{
- __this_cpu_inc(hrtimer_interrupts);
-}
+ unsigned long hrint = __this_cpu_read(hrtimer_interrupts);

-/*
- * These two functions are mostly architecture specific
- * defining them as weak here.
- */
-int __weak watchdog_nmi_enable(unsigned int cpu)
-{
- return 0;
+ if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
+ return true;
+
+ __this_cpu_write(hrtimer_interrupts_saved, hrint);
+ return false;
}
-void __weak watchdog_nmi_disable(unsigned int cpu)
+
+static void watchdog_interrupt_count(void)
{
+ __this_cpu_inc(hrtimer_interrupts);
}

static int watchdog_enable_all_cpus(void);
@@ -502,57 +546,6 @@ static void watchdog_unpark_threads(void)
kthread_unpark(per_cpu(softlockup_watchdog, cpu));
}

-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
- int ret = 0;
-
- get_online_cpus();
- mutex_lock(&watchdog_proc_mutex);
- /*
- * Multiple suspend requests can be active in parallel (counted by
- * the 'watchdog_suspended' variable). If the watchdog threads are
- * running, the first caller takes care that they will be parked.
- * The state of 'watchdog_running' cannot change while a suspend
- * request is active (see related code in 'proc' handlers).
- */
- if (watchdog_running && !watchdog_suspended)
- ret = watchdog_park_threads();
-
- if (ret == 0)
- watchdog_suspended++;
- else {
- watchdog_disable_all_cpus();
- pr_err("Failed to suspend lockup detectors, disabled\n");
- watchdog_enabled = 0;
- }
-
- mutex_unlock(&watchdog_proc_mutex);
-
- return ret;
-}
-
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
-{
- mutex_lock(&watchdog_proc_mutex);
-
- watchdog_suspended--;
- /*
- * The watchdog threads are unparked if they were previously running
- * and if there is no more active suspend request.
- */
- if (watchdog_running && !watchdog_suspended)
- watchdog_unpark_threads();
-
- mutex_unlock(&watchdog_proc_mutex);
- put_online_cpus();
-}
-
static int update_watchdog_all_cpus(void)
{
int ret;
@@ -604,6 +597,81 @@ static void watchdog_disable_all_cpus(void)
}
}

+#else /* SOFTLOCKUP */
+static int watchdog_park_threads(void)
+{
+ return 0;
+}
+
+static void watchdog_unpark_threads(void)
+{
+}
+
+static int watchdog_enable_all_cpus(void)
+{
+ return 0;
+}
+
+static void watchdog_disable_all_cpus(void)
+{
+}
+
+static void set_sample_period(void)
+{
+}
+#endif /* SOFTLOCKUP */
+
+/*
+ * Suspend the hard and soft lockup detector by parking the watchdog threads.
+ */
+int lockup_detector_suspend(void)
+{
+ int ret = 0;
+
+ get_online_cpus();
+ mutex_lock(&watchdog_proc_mutex);
+ /*
+ * Multiple suspend requests can be active in parallel (counted by
+ * the 'watchdog_suspended' variable). If the watchdog threads are
+ * running, the first caller takes care that they will be parked.
+ * The state of 'watchdog_running' cannot change while a suspend
+ * request is active (see related code in 'proc' handlers).
+ */
+ if (watchdog_running && !watchdog_suspended)
+ ret = watchdog_park_threads();
+
+ if (ret == 0)
+ watchdog_suspended++;
+ else {
+ watchdog_disable_all_cpus();
+ pr_err("Failed to suspend lockup detectors, disabled\n");
+ watchdog_enabled = 0;
+ }
+
+ mutex_unlock(&watchdog_proc_mutex);
+
+ return ret;
+}
+
+/*
+ * Resume the hard and soft lockup detector by unparking the watchdog threads.
+ */
+void lockup_detector_resume(void)
+{
+ mutex_lock(&watchdog_proc_mutex);
+
+ watchdog_suspended--;
+ /*
+ * The watchdog threads are unparked if they were previously running
+ * and if there is no more active suspend request.
+ */
+ if (watchdog_running && !watchdog_suspended)
+ watchdog_unpark_threads();
+
+ mutex_unlock(&watchdog_proc_mutex);
+ put_online_cpus();
+}
+
#ifdef CONFIG_SYSCTL

/*
@@ -810,9 +878,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
* a temporary cpumask, so we are likely not in a
* position to do much else to make things better.
*/
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
if (smpboot_update_cpumask_percpu_thread(
&watchdog_threads, &watchdog_cpumask) != 0)
pr_err("cpumask update failed\n");
+#endif
}
}
out:
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index e0d7a7c43fb5..ffd4fa59fbde 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -22,39 +22,7 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);

-/* boot commands */
-/*
- * Should we panic when a soft-lockup or hard-lockup occurs:
- */
-unsigned int __read_mostly hardlockup_panic =
- CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
static unsigned long hardlockup_allcpu_dumped;
-/*
- * 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 hardlockup_detector_disable(void)
-{
- watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-}
-
-static int __init hardlockup_panic_setup(char *str)
-{
- if (!strncmp(str, "panic", 5))
- hardlockup_panic = 1;
- else if (!strncmp(str, "nopanic", 7))
- hardlockup_panic = 0;
- else if (!strncmp(str, "0", 1))
- watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
- else if (!strncmp(str, "1", 1))
- watchdog_enabled |= NMI_WATCHDOG_ENABLED;
- return 1;
-}
-__setup("nmi_watchdog=", hardlockup_panic_setup);

void hld_touch_nmi_watchdog(void)
{
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e4587ebe52c7..c69e12ce823a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -801,10 +801,25 @@ config LOCKUP_DETECTOR
The frequency of hrtimer and NMI events and the soft and hard lockup
thresholds can be controlled through the sysctl watchdog_thresh.

+config SOFTLOCKUP_DETECTOR
+ bool "Detect Soft Lockups"
+ depends on LOCKUP_DETECTOR
+
+config HARDLOCKUP_DETECTOR_PERF
+ bool
+ select SOFTLOCKUP_DETECTOR
+
+#
+# arch/ can define HAVE_NMI_WATCHDOG to provide their own NMI watchdog
+# rather than the perf based detector.
+#
+# The arch may do its own thing, or select HARDLOCKUP_DETECTOR, which
+#
config HARDLOCKUP_DETECTOR
- def_bool y
- depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
- depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
+ bool "Detect Hard Lockups"
+ depends on LOCKUP_DETECTOR
+ depends on !HAVE_NMI_WATCHDOG || (PERF_EVENTS && HAVE_PERF_EVENTS_NMI)
+ select HARDLOCKUP_DETECTOR_PERF if !HAVE_NMI_WATCHDOG

config BOOTPARAM_HARDLOCKUP_PANIC
bool "Panic (Reboot) On Hard Lockups"
@@ -826,7 +841,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE

config BOOTPARAM_SOFTLOCKUP_PANIC
bool "Panic (Reboot) On Soft Lockups"
- depends on LOCKUP_DETECTOR
+ depends on SOFTLOCKUP_DETECTOR
help
Say Y here to enable the kernel to panic on "soft lockups",
which are bugs that cause the kernel to loop in kernel
@@ -843,7 +858,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC

config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
int
- depends on LOCKUP_DETECTOR
+ depends on SOFTLOCKUP_DETECTOR
range 0 1
default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
@@ -851,7 +866,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
config DETECT_HUNG_TASK
bool "Detect Hung Tasks"
depends on DEBUG_KERNEL
- default LOCKUP_DETECTOR
+ default SOFTLOCKUP_DETECTOR
help
Say Y here to enable the kernel to detect "hung tasks",
which are bugs that cause the task to be stuck in
--
2.11.0