[Qemu-devel] [PATCH v4 5/5] hpet 'driftfix': add code in hpet_timer() to compensate delayed callbacks and coalesced interrupts

[Ulrich Obergfell <uobergfe@redhat.com>]

Loss of periodic timer interrupts caused by delayed callbacks and by
interrupt coalescing is compensated by gradually injecting additional
interrupts during subsequent timer intervals, starting at a rate of
one additional interrupt per interval. The injection of additional
interrupts is based on a backlog of unaccounted HPET clock periods
(new HPETTimer field 'ticks_not_accounted'). The backlog increases
due to delayed callbacks and coalesced interrupts, and it decreases
if an interrupt was injected successfully. If the backlog increases
while compensation is still in progress, the rate at which additional
interrupts are injected is increased too. A limit is imposed on the
backlog and on the rate.

Injecting additional timer interrupts to compensate lost interrupts
can alleviate long term time drift. However, on a short time scale,
this method can have the side effect of making virtual machine time
intermittently pass slower and faster than real time (depending on
the guest's time keeping algorithm). Compensation is disabled by
default and can be enabled for guests where this behaviour may be
acceptable.

Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com>
---
 hw/hpet.c |   70 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/hw/hpet.c b/hw/hpet.c
index e57c654..519fc6b 100644
--- a/hw/hpet.c
+++ b/hw/hpet.c
@@ -31,6 +31,7 @@
 #include "hpet_emul.h"
 #include "sysbus.h"
 #include "mc146818rtc.h"
+#include <assert.h>
 
 //#define HPET_DEBUG
 #ifdef HPET_DEBUG
@@ -41,6 +42,9 @@
 
 #define HPET_MSI_SUPPORT        0
 
+#define MAX_TICKS_NOT_ACCOUNTED     (uint64_t)500000000 /* 5 sec */
+#define MAX_IRQ_RATE                (uint32_t)10
+
 struct HPETState;
 typedef struct HPETTimer {  /* timers */
     uint8_t tn;             /*timer number*/
@@ -324,14 +328,35 @@ static const VMStateDescription vmstate_hpet = {
     }
 };
 
+static void hpet_timer_driftfix_reset(HPETTimer *t)
+{
+    if (t->state->driftfix && timer_is_periodic(t)) {
+        t->ticks_not_accounted = t->prev_period = t->period;
+        t->irq_rate = 1;
+        t->divisor = 1;
+    }
+}
+
+static bool hpet_timer_has_tick_backlog(HPETTimer *t)
+{
+    uint64_t backlog = 0;
+
+    if (t->ticks_not_accounted >= t->period + t->prev_period) {
+        backlog = t->ticks_not_accounted - (t->period + t->prev_period);
+    }
+    return (backlog >= t->period);
+}
+
 /*
  * timer expiration callback
  */
 static void hpet_timer(void *opaque)
 {
     HPETTimer *t = opaque;
+    HPETState *s = t->state;
     uint64_t diff;
-
+    int irq_delivered = 0;
+    uint32_t period_count = 0;
     uint64_t period = t->period;
     uint64_t cur_tick = hpet_get_ticks(t->state);
 
@@ -339,13 +364,37 @@ static void hpet_timer(void *opaque)
         if (t->config & HPET_TN_32BIT) {
             while (hpet_time_after(cur_tick, t->cmp)) {
                 t->cmp = (uint32_t)(t->cmp + t->period);
+                t->ticks_not_accounted += t->period;
+                period_count++;
             }
         } else {
             while (hpet_time_after64(cur_tick, t->cmp)) {
                 t->cmp += period;
+                t->ticks_not_accounted += period;
+                period_count++;
             }
         }
         diff = hpet_calculate_diff(t, cur_tick);
+        if (s->driftfix) {
+            if (t->ticks_not_accounted > MAX_TICKS_NOT_ACCOUNTED) {
+                t->ticks_not_accounted = t->period + t->prev_period;
+            }
+            if (hpet_timer_has_tick_backlog(t)) {
+                if (t->irq_rate == 1 || period_count > 1) {
+                    t->irq_rate++;
+                    t->irq_rate = MIN(t->irq_rate, MAX_IRQ_RATE);
+                }
+                if (t->divisor == 0) {
+                    assert(period_count);
+                }
+                if (period_count) {
+                    t->divisor = t->irq_rate;
+                }
+                diff /= t->divisor--;
+            } else {
+                t->irq_rate = 1;
+            }
+        }
         qemu_mod_timer(t->qemu_timer,
                        qemu_get_clock_ns(vm_clock) + (int64_t)ticks_to_ns(diff));
     } else if (t->config & HPET_TN_32BIT && !timer_is_periodic(t)) {
@@ -356,7 +405,22 @@ static void hpet_timer(void *opaque)
             t->wrap_flag = 0;
         }
     }
-    update_irq(t, 1);
+    if (s->driftfix && timer_is_periodic(t) && period != 0) {
+        if (t->ticks_not_accounted >= t->period + t->prev_period) {
+            irq_delivered = update_irq(t, 1);
+            if (irq_delivered) {
+                t->ticks_not_accounted -= t->prev_period;
+                t->prev_period = t->period;
+            } else {
+                if (period_count) {
+                    t->irq_rate++;
+                    t->irq_rate = MIN(t->irq_rate, MAX_IRQ_RATE);
+                }
+            }
+        }
+    } else {
+        update_irq(t, 1);
+    }
 }
 
 static void hpet_set_timer(HPETTimer *t)
@@ -525,6 +589,7 @@ static void hpet_ram_writel(void *opaque, target_phys_addr_t addr,
                 timer->period = (uint32_t)timer->period;
             }
             if (activating_bit(old_val, new_val, HPET_TN_ENABLE)) {
+                hpet_timer_driftfix_reset(timer);
                 hpet_set_timer(timer);
             } else if (deactivating_bit(old_val, new_val, HPET_TN_ENABLE)) {
                 hpet_del_timer(timer);
@@ -599,6 +664,7 @@ static void hpet_ram_writel(void *opaque, target_phys_addr_t addr,
                     ticks_to_ns(s->hpet_counter) - qemu_get_clock_ns(vm_clock);
                 for (i = 0; i < s->num_timers; i++) {
                     if ((&s->timer[i])->cmp != ~0ULL) {
+                        hpet_timer_driftfix_reset(&s->timer[i]);
                         hpet_set_timer(&s->timer[i]);
                     }
                 }
-- 
1.6.2.5