[PATCH] powerpc/watchdog: Use hrtimers for per-CPU heartbeat

[Nicholas Piggin]

Using a jiffies timer creates a dependency on the tick_do_timer_cpu
incrementing jiffies. If that CPU has locked up and jiffies is not
incrementing, the watchdog heartbeat timer for all CPUs stops and
creates false positives and confusing warnings on local CPUs, and
also causes the SMP detector to stop, so the root cause is never
detected.

Fix this by using hrtimer based timers for the watchdog heartbeat,
like the generic kernel hardlockup detector.

Reported-by: Ravikumar Bangoria <ravi.bangoria at in.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 arch/powerpc/kernel/watchdog.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 3c6ab22a0c4e..59a0e5942f6b 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -77,7 +77,7 @@ static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */
 
 static u64 wd_timer_period_ms __read_mostly;  /* interval between heartbeat */
 
-static DEFINE_PER_CPU(struct timer_list, wd_timer);
+static DEFINE_PER_CPU(struct hrtimer, wd_hrtimer);
 static DEFINE_PER_CPU(u64, wd_timer_tb);
 
 /* SMP checker bits */
@@ -293,21 +293,21 @@ void soft_nmi_interrupt(struct pt_regs *regs)
 	nmi_exit();
 }
 
-static void wd_timer_reset(unsigned int cpu, struct timer_list *t)
-{
-	t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms);
-	if (wd_timer_period_ms > 1000)
-		t->expires = __round_jiffies_up(t->expires, cpu);
-	add_timer_on(t, cpu);
-}
-
-static void wd_timer_fn(struct timer_list *t)
+static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
 	int cpu = smp_processor_id();
 
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return HRTIMER_NORESTART;
+
+	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+		return HRTIMER_NORESTART;
+
 	watchdog_timer_interrupt(cpu);
 
-	wd_timer_reset(cpu, t);
+	hrtimer_forward_now(hrtimer, ms_to_ktime(wd_timer_period_ms));
+
+	return HRTIMER_RESTART;
 }
 
 void arch_touch_nmi_watchdog(void)
@@ -325,19 +325,21 @@ EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 static void start_watchdog_timer_on(unsigned int cpu)
 {
-	struct timer_list *t = per_cpu_ptr(&wd_timer, cpu);
+	struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer);
 
 	per_cpu(wd_timer_tb, cpu) = get_tb();
 
-	timer_setup(t, wd_timer_fn, TIMER_PINNED);
-	wd_timer_reset(cpu, t);
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = watchdog_timer_fn;
+	hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static void stop_watchdog_timer_on(unsigned int cpu)
 {
-	struct timer_list *t = per_cpu_ptr(&wd_timer, cpu);
+	struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer);
 
-	del_timer_sync(t);
+	hrtimer_cancel(hrtimer);
 }
 
 static int start_wd_on_cpu(unsigned int cpu)
-- 
2.20.1