tick: Introduce hrtimer based broadcast

On some architectures, in certain CPU deep idle states the local timers stop.
An external clock device is used to wakeup these CPUs. The kernel support for the
wakeup of these CPUs is provided by the tick broadcast framework by using the
external clock device as the wakeup source.

However not all implementations of architectures provide such an external
clock device. This patch includes support in the broadcast framework to handle
the wakeup of the CPUs in deep idle states on such systems by queuing a hrtimer
on one of the CPUs, which is meant to handle the wakeup of CPUs in deep idle states.

This patchset introduces a pseudo clock device which can be registered by the
archs as tick_broadcast_device in the absence of a real external clock
device. Once registered, the broadcast framework will work as is for these
architectures as long as the archs take care of the BROADCAST_ENTER
notification failing for one of the CPUs. This CPU is made the stand by CPU to
handle wakeup of the CPUs in deep idle and it *must not enter deep idle states*.

The CPU with the earliest wakeup is chosen to be this CPU. Hence this way the
stand by CPU dynamically moves around and so does the hrtimer which is queued
to trigger at the next earliest wakeup time. This is consistent with the case where
an external clock device is present. The smp affinity of this clock device is
set to the CPU with the earliest wakeup. This patchset handles the hotplug of
the stand by CPU as well by moving the hrtimer on to the CPU handling the CPU_DEAD
notification.

Originally-from: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: deepthi@linux.vnet.ibm.com
Cc: paulmck@linux.vnet.ibm.com
Cc: fweisbec@gmail.com
Cc: paulus@samba.org
Cc: srivatsa.bhat@linux.vnet.ibm.com
Cc: svaidy@linux.vnet.ibm.com
Cc: peterz@infradead.org
Cc: benh@kernel.crashing.org
Cc: rafael.j.wysocki@intel.com
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20140207080632.17187.80532.stgit@preeti.in.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

4 files changed, 167 insertions, 4 deletions

diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index e0c5a6c418de..dbe9e1457168 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -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
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 9250130646f5..06151ef4a744 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -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
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 000000000000..92425279312b
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * 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
+         * restart the timer because we are in the callback, but we
+         * can set the expiry time and let the callback return
+         * HRTIMER_RESTART.
+         */
+        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);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 84c8fd91d744..63c7b2d9ed8e 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -643,6 +643,42 @@ 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
@@ -661,7 +697,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
          * states
          */
         if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-                return;
+                return 0;
 
         /*
          * We are called with preemtion disabled from the depth of the
@@ -672,7 +708,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
         dev = td->evtdev;
 
         if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-                return;
+                return 0;
 
         bc = tick_broadcast_device.evtdev;
 
@@ -680,7 +716,7 @@ 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
@@ -693,6 +729,16 @@ 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 and we remove the
+                 * CPU from the broadcast mask. We don't have to go
+                 * through the EXIT path as the local timer is not
+                 * shutdown.
+                 */
+                ret = broadcast_needs_cpu(bc, cpu);
+                if (ret)
+                        cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
         } else {
                 if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
                         clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -866,6 +912,8 @@ 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);
 }