1 files changed, 129 insertions, 37 deletions

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index f112af7aa62e..274fab99169d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -710,31 +710,29 @@ static void hpet_work(struct work_struct *w)
 	complete(&hpet_work->complete);
 }
 
-static int hpet_cpuhp_notify(struct notifier_block *n,
-		unsigned long action, void *hcpu)
+static int hpet_cpuhp_online(unsigned int cpu)
 {
-	unsigned long cpu = (unsigned long)hcpu;
 	struct hpet_work_struct work;
+
+	INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
+	init_completion(&work.complete);
+	/* FIXME: add schedule_work_on() */
+	schedule_delayed_work_on(cpu, &work.work, 0);
+	wait_for_completion(&work.complete);
+	destroy_delayed_work_on_stack(&work.work);
+	return 0;
+}
+
+static int hpet_cpuhp_dead(unsigned int cpu)
+{
 	struct hpet_dev *hdev = per_cpu(cpu_hpet_dev, cpu);
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-		INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
-		init_completion(&work.complete);
-		/* FIXME: add schedule_work_on() */
-		schedule_delayed_work_on(cpu, &work.work, 0);
-		wait_for_completion(&work.complete);
-		destroy_delayed_work_on_stack(&work.work);
-		break;
-	case CPU_DEAD:
-		if (hdev) {
-			free_irq(hdev->irq, hdev);
-			hdev->flags &= ~HPET_DEV_USED;
-			per_cpu(cpu_hpet_dev, cpu) = NULL;
-		}
-		break;
-	}
-	return NOTIFY_OK;
+	if (!hdev)
+		return 0;
+	free_irq(hdev->irq, hdev);
+	hdev->flags &= ~HPET_DEV_USED;
+	per_cpu(cpu_hpet_dev, cpu) = NULL;
+	return 0;
 }
 #else
 
@@ -750,21 +748,112 @@ static void hpet_reserve_msi_timers(struct hpet_data *hd)
 }
 #endif
 
-static int hpet_cpuhp_notify(struct notifier_block *n,
-		unsigned long action, void *hcpu)
-{
-	return NOTIFY_OK;
-}
+#define hpet_cpuhp_online	NULL
+#define hpet_cpuhp_dead		NULL
 
 #endif
 
 /*
  * Clock source related code
  */
+#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
+/*
+ * Reading the HPET counter is a very slow operation. If a large number of
+ * CPUs are trying to access the HPET counter simultaneously, it can cause
+ * massive delay and slow down system performance dramatically. This may
+ * happen when HPET is the default clock source instead of TSC. For a
+ * really large system with hundreds of CPUs, the slowdown may be so
+ * severe that it may actually crash the system because of a NMI watchdog
+ * soft lockup, for example.
+ *
+ * If multiple CPUs are trying to access the HPET counter at the same time,
+ * we don't actually need to read the counter multiple times. Instead, the
+ * other CPUs can use the counter value read by the first CPU in the group.
+ *
+ * This special feature is only enabled on x86-64 systems. It is unlikely
+ * that 32-bit x86 systems will have enough CPUs to require this feature
+ * with its associated locking overhead. And we also need 64-bit atomic
+ * read.
+ *
+ * The lock and the hpet value are stored together and can be read in a
+ * single atomic 64-bit read. It is explicitly assumed that arch_spinlock_t
+ * is 32 bits in size.
+ */
+union hpet_lock {
+	struct {
+		arch_spinlock_t lock;
+		u32 value;
+	};
+	u64 lockval;
+};
+
+static union hpet_lock hpet __cacheline_aligned = {
+	{ .lock = __ARCH_SPIN_LOCK_UNLOCKED, },
+};
+
+static cycle_t read_hpet(struct clocksource *cs)
+{
+	unsigned long flags;
+	union hpet_lock old, new;
+
+	BUILD_BUG_ON(sizeof(union hpet_lock) != 8);
+
+	/*
+	 * Read HPET directly if in NMI.
+	 */
+	if (in_nmi())
+		return (cycle_t)hpet_readl(HPET_COUNTER);
+
+	/*
+	 * Read the current state of the lock and HPET value atomically.
+	 */
+	old.lockval = READ_ONCE(hpet.lockval);
+
+	if (arch_spin_is_locked(&old.lock))
+		goto contended;
+
+	local_irq_save(flags);
+	if (arch_spin_trylock(&hpet.lock)) {
+		new.value = hpet_readl(HPET_COUNTER);
+		/*
+		 * Use WRITE_ONCE() to prevent store tearing.
+		 */
+		WRITE_ONCE(hpet.value, new.value);
+		arch_spin_unlock(&hpet.lock);
+		local_irq_restore(flags);
+		return (cycle_t)new.value;
+	}
+	local_irq_restore(flags);
+
+contended:
+	/*
+	 * Contended case
+	 * --------------
+	 * Wait until the HPET value change or the lock is free to indicate
+	 * its value is up-to-date.
+	 *
+	 * It is possible that old.value has already contained the latest
+	 * HPET value while the lock holder was in the process of releasing
+	 * the lock. Checking for lock state change will enable us to return
+	 * the value immediately instead of waiting for the next HPET reader
+	 * to come along.
+	 */
+	do {
+		cpu_relax();
+		new.lockval = READ_ONCE(hpet.lockval);
+	} while ((new.value == old.value) && arch_spin_is_locked(&new.lock));
+
+	return (cycle_t)new.value;
+}
+#else
+/*
+ * For UP or 32-bit.
+ */
 static cycle_t read_hpet(struct clocksource *cs)
 {
 	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
+#endif
 
 static struct clocksource clocksource_hpet = {
 	.name		= "hpet",
@@ -931,7 +1020,7 @@ out_nohpet:
  */
 static __init int hpet_late_init(void)
 {
-	int cpu;
+	int ret;
 
 	if (boot_hpet_disable)
 		return -ENODEV;
@@ -961,16 +1050,20 @@ static __init int hpet_late_init(void)
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return 0;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu) {
-		hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
-	}
-
 	/* This notifier should be called after workqueue is ready */
-	__hotcpu_notifier(hpet_cpuhp_notify, -20);
-	cpu_notifier_register_done();
-
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+				hpet_cpuhp_online, NULL);
+	if (ret)
+		return ret;
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+				hpet_cpuhp_dead);
+	if (ret)
+		goto err_cpuhp;
 	return 0;
+
+err_cpuhp:
+	cpuhp_remove_state(CPUHP_AP_X86_HPET_ONLINE);
+	return ret;
 }
 fs_initcall(hpet_late_init);
 
@@ -1020,7 +1113,6 @@ void hpet_disable(void)
  */
 #include <linux/mc146818rtc.h>
 #include <linux/rtc.h>
-#include <asm/rtc.h>
 
 #define DEFAULT_RTC_INT_FREQ	64
 #define DEFAULT_RTC_SHIFT	6
@@ -1244,7 +1336,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
 	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
-		get_rtc_time(&curr_time);
+		mc146818_get_time(&curr_time);
 
 	if (hpet_rtc_flags & RTC_UIE &&
 	    curr_time.tm_sec != hpet_prev_update_sec) {