@@ -62,6 +62,11 @@ enum clock_event_mode {
#define CLOCK_EVT_FEAT_DYNIRQ 0x000020
#define CLOCK_EVT_FEAT_PERCPU 0x000040
+/*
+ * Clockevent device is based on a hrtimer for broadcast
+ */
+#define CLOCK_EVT_FEAT_HRTIMER 0x000080
+
/**
* struct clock_event_device - clock event device descriptor
* @event_handler: Assigned by the framework to be called by the low
@@ -83,6 +88,7 @@ enum clock_event_mode {
* @name: ptr to clock event name
* @rating: variable to rate clock event devices
* @irq: IRQ number (only for non CPU local devices)
+ * @bound_on: Bound on CPU
* @cpumask: cpumask to indicate for which CPUs this device works
* @list: list head for the management code
* @owner: module reference
@@ -113,6 +119,7 @@ struct clock_event_device {
const char *name;
int rating;
int irq;
+ int bound_on;
const struct cpumask *cpumask;
struct list_head list;
struct module *owner;
@@ -180,9 +187,11 @@ extern int tick_receive_broadcast(void);
#endif
#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void tick_setup_hrtimer_broadcast(void);
extern int tick_check_broadcast_expired(void);
#else
static inline int tick_check_broadcast_expired(void) { return 0; }
+static void tick_setup_hrtimer_broadcast(void) {};
#endif
#ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -3,7 +3,7 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o tick-broadcast-hrtimer.o
obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o
obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o
obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o
new file mode 100644
@@ -0,0 +1,105 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *bc)
+{
+ switch (mode) {
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ /*
+ * Note, we cannot cancel the timer here as we might
+ * run into the following live lock scenario:
+ *
+ * cpu 0 cpu1
+ * lock(broadcast_lock);
+ * hrtimer_interrupt()
+ * bc_handler()
+ * tick_handle_oneshot_broadcast();
+ * lock(broadcast_lock);
+ * hrtimer_cancel()
+ * wait_for_callback()
+ */
+ hrtimer_try_to_cancel(&bctimer);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+ /*
+ * We try to cancel the timer first. If the callback is on
+ * flight on some other cpu then we let it handle it. If we
+ * were able to cancel the timer nothing can rearm it as we
+ * own broadcast_lock.
+ *
+ * However we can also be called from the event handler of
+ * ce_broadcast_hrtimer itself when it expires. We cannot therefore
+ * restart the timer since it is on flight on the same CPU. But
+ * due to the same reason we can reset it.
+ */
+ if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+ /* Bind the "device" to the cpu */
+ bc->bound_on = smp_processor_id();
+ } else if (bc->bound_on == smp_processor_id()) {
+ hrtimer_set_expires(&bctimer, expires);
+ }
+ return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+ .set_mode = bc_set_mode,
+ .set_next_ktime = bc_set_next,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_KTIME |
+ CLOCK_EVT_FEAT_HRTIMER,
+ .rating = 0,
+ .bound_on = -1,
+ .min_delta_ns = 1,
+ .max_delta_ns = KTIME_MAX,
+ .min_delta_ticks = 1,
+ .max_delta_ticks = KTIME_MAX,
+ .mult = 1,
+ .shift = 0,
+ .cpumask = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+ ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+ if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+ return HRTIMER_NORESTART;
+
+ return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ bctimer.function = bc_handler;
+ clockevents_register_device(&ce_broadcast_hrtimer);
+}
@@ -630,6 +630,42 @@ again:
raw_spin_unlock(&tick_broadcast_lock);
}
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+ if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+ return 0;
+ if (bc->next_event.tv64 == KTIME_MAX)
+ return 0;
+ return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+ struct clock_event_device *dev)
+{
+ /*
+ * For hrtimer based broadcasting we cannot shutdown the cpu
+ * local device if our own event is the first one to expire or
+ * if we own the broadcast timer.
+ */
+ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+ if (broadcast_needs_cpu(bc, smp_processor_id()))
+ return;
+ if (dev->next_event.tv64 < bc->next_event.tv64)
+ return;
+ }
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+ return;
+ /* This moves the broadcast assignment to this cpu */
+ clockevents_program_event(bc, bc->next_event, 1);
+}
+
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
@@ -667,7 +703,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
- clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+ broadcast_shutdown_local(bc, dev);
/*
* We only reprogram the broadcast timer if we
* did not mark ourself in the force mask and
@@ -680,6 +716,11 @@ int tick_broadcast_oneshot_control(unsigned long reason)
dev->next_event.tv64 < bc->next_event.tv64)
tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
}
+ /*
+ * If the current CPU owns the hrtimer broadcast
+ * mechanism, it cannot go deep idle.
+ */
+ ret = broadcast_needs_cpu(bc, cpu);
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -853,6 +894,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+ broadcast_move_bc(cpu);
+
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}