[RFC PATCH v3 12/21] watchdog/hardlockup/hpet: Adjust timer expiration on the number of monitored CPUs

[Ricardo Neri]

Each CPU should be monitored for hardlockups every watchdog_thresh seconds.
Since all the CPUs in the system are monitored by the same timer and the
timer interrupt is rotated among the monitored CPUs, the timer must expire
every watchdog_thresh/N seconds; where N is the number of monitored CPUs.
Use the new member of struct hld_data, ticks_per_cpu, to store the
aforementioned quantity.

The ticks-per-CPU quantity is updated every time the number of monitored
CPUs changes: when the watchdog is enabled or disabled for a specific CPU.
If the timer is used in periodic mode, it needs to be adjusted to reflect
the new expected expiration.

Cc: Ashok Raj <ashok.raj@xxxxxxxxx>
Cc: Andi Kleen <andi.kleen@xxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Jacob Pan <jacob.jun.pan@xxxxxxxxx>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@xxxxxxxxx>
Cc: Don Zickus <dzickus@xxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Frederic Weisbecker <frederic@xxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Babu Moger <babu.moger@xxxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Philippe Ombredanne <pombredanne@xxxxxxxx>
Cc: Colin Ian King <colin.king@xxxxxxxxxxxxx>
Cc: Byungchul Park <byungchul.park@xxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: "Luis R. Rodriguez" <mcgrof@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
Cc: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Suravee Suthikulpanit <Suravee.Suthikulpanit@xxxxxxx>
Cc: "Ravi V. Shankar" <ravi.v.shankar@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: iommu@xxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/hpet.h         |  1 +
 arch/x86/kernel/watchdog_hld_hpet.c | 46 +++++++++++++++++++++++++++--
 2 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 31fc27508cf3..64acacce095d 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -114,6 +114,7 @@ struct hpet_hld_data {
 	bool		has_periodic;
 	u32		num;
 	u64		ticks_per_second;
+	u64		ticks_per_cpu;
 	u32		handling_cpu;
 	u32		enabled_cpus;
 	struct msi_msg	msi_msg;
diff --git a/arch/x86/kernel/watchdog_hld_hpet.c b/arch/x86/kernel/watchdog_hld_hpet.c
index c20b378b8c0c..9a3431a54616 100644
--- a/arch/x86/kernel/watchdog_hld_hpet.c
+++ b/arch/x86/kernel/watchdog_hld_hpet.c
@@ -44,6 +44,13 @@ static void kick_timer(struct hpet_hld_data *hdata, bool force)
 	 * are able to update the comparator before the counter reaches such new
 	 * value.
 	 *
+	 * Each CPU must be monitored every watch_thresh seconds. Since the
+	 * timer targets one CPU at a time, it must expire every
+	 *
+	 *        ticks_per_cpu = watch_thresh * ticks_per_second /enabled_cpus
+	 *
+	 * as computed in update_ticks_per_cpu().
+	 *
 	 * Let it wrap around if needed.
 	 */
 
@@ -51,10 +58,10 @@ static void kick_timer(struct hpet_hld_data *hdata, bool force)
 		return;
 
 	if (hdata->has_periodic)
-		period = watchdog_thresh * hdata->ticks_per_second;
+		period = watchdog_thresh * hdata->ticks_per_cpu;
 
 	count = hpet_readl(HPET_COUNTER);
-	new_compare = count + watchdog_thresh * hdata->ticks_per_second;
+	new_compare = count + watchdog_thresh * hdata->ticks_per_cpu;
 	hpet_set_comparator(hdata->num, (u32)new_compare, (u32)period);
 }
 
@@ -233,6 +240,27 @@ static int setup_hpet_irq(struct hpet_hld_data *hdata)
 	return ret;
 }
 
+/**
+ * update_ticks_per_cpu() - Update the number of HPET ticks per CPU
+ * @hdata:     struct with the timer's the ticks-per-second and CPU mask
+ *
+ * From the overall ticks-per-second of the timer, compute the number of ticks
+ * after which the timer should expire to monitor each CPU every watch_thresh
+ * seconds. The ticks-per-cpu quantity is computed using the number of CPUs that
+ * the watchdog currently monitors.
+ */
+static void update_ticks_per_cpu(struct hpet_hld_data *hdata)
+{
+	u64 temp = hdata->ticks_per_second;
+
+	/* Only update if there are monitored CPUs. */
+	if (!hdata->enabled_cpus)
+		return;
+
+	do_div(temp, hdata->enabled_cpus);
+	hdata->ticks_per_cpu = temp;
+}
+
 /**
  * hardlockup_detector_hpet_enable() - Enable the hardlockup detector
  * @cpu:	CPU Index in which the watchdog will be enabled.
@@ -245,13 +273,23 @@ void hardlockup_detector_hpet_enable(unsigned int cpu)
 {
 	cpumask_set_cpu(cpu, to_cpumask(hld_data->cpu_monitored_mask));
 
-	if (!hld_data->enabled_cpus++) {
+	hld_data->enabled_cpus++;
+	update_ticks_per_cpu(hld_data);
+
+	if (hld_data->enabled_cpus == 1) {
 		hld_data->handling_cpu = cpu;
 		update_msi_destid(hld_data);
 		/* Force timer kick when detector is just enabled */
 		kick_timer(hld_data, true);
 		enable_timer(hld_data);
 	}
+
+	/*
+	 * When in periodic mode, we only kick the timer here. Hence,
+	 * as there are now more CPUs to monitor, we need to adjust the
+	 * periodic expiration.
+	 */
+	kick_timer(hld_data, hld_data->has_periodic);
 }
 
 /**
@@ -267,6 +305,8 @@ void hardlockup_detector_hpet_disable(unsigned int cpu)
 	cpumask_clear_cpu(cpu, to_cpumask(hld_data->cpu_monitored_mask));
 	hld_data->enabled_cpus--;
 
+	update_ticks_per_cpu(hld_data);
+
 	if (hld_data->handling_cpu != cpu)
 		return;
 
-- 
2.17.1