hw/openrisc: Fixed undercounting of TTCR in continuous mode

In the existing design, TTCR is prone to undercounting when running in
continuous mode. This manifests as a timer interrupt appearing to
trigger a few cycles prior to the deadline set in SPR_TTMR_TP.

When the timer triggers, the virtual time delta in nanoseconds between
the time when the timer was set, and when it triggers is calculated.
This nanoseconds value is then divided by TIMER_PERIOD (50) to compute
an increment of cycles to apply to TTCR.

However, this calculation rounds down the number of cycles causing the
undercounting.

A simplistic solution would be to instead round up the number of cycles,
however this will result in the accumulation of timing error over time.

This patch corrects the issue by calculating the time delta in
nanoseconds between when the timer was last reset and the timer event.
This approach allows the TTCR value to be rounded up, but without
accumulating error over time.

Signed-off-by: Joel Holdsworth <jholdsworth@nvidia.com>
[stafford: Incremented version in vmstate_or1k_timer, checkpatch fixes]
Signed-off-by: Stafford Horne <shorne@gmail.com>

hw/openrisc/cputimer.c

@@ -29,7 +29,8 @@
 /* Tick Timer global state to allow all cores to be in sync */
 typedef struct OR1KTimerState {
     uint32_t ttcr;
-    uint64_t last_clk;
+    uint32_t ttcr_offset;
+    uint64_t clk_offset;
 } OR1KTimerState;
 
 static OR1KTimerState *or1k_timer;
@@ -37,6 +38,8 @@ static OR1KTimerState *or1k_timer;
 void cpu_openrisc_count_set(OpenRISCCPU *cpu, uint32_t val)
 {
     or1k_timer->ttcr = val;
+    or1k_timer->ttcr_offset = val;
+    or1k_timer->clk_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
 }
 
 uint32_t cpu_openrisc_count_get(OpenRISCCPU *cpu)
@@ -53,9 +56,8 @@ void cpu_openrisc_count_update(OpenRISCCPU *cpu)
         return;
     }
     now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
-    or1k_timer->ttcr += (uint32_t)((now - or1k_timer->last_clk)
-                                    / TIMER_PERIOD);
-    or1k_timer->last_clk = now;
+    or1k_timer->ttcr = or1k_timer->ttcr_offset +
+        DIV_ROUND_UP(now - or1k_timer->clk_offset, TIMER_PERIOD);
 }
 
 /* Update the next timeout time as difference between ttmr and ttcr */
@@ -69,7 +71,7 @@ void cpu_openrisc_timer_update(OpenRISCCPU *cpu)
     }
 
     cpu_openrisc_count_update(cpu);
-    now = or1k_timer->last_clk;
+    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
 
     if ((cpu->env.ttmr & TTMR_TP) <= (or1k_timer->ttcr & TTMR_TP)) {
         wait = TTMR_TP - (or1k_timer->ttcr & TTMR_TP) + 1;
@@ -110,7 +112,8 @@ static void openrisc_timer_cb(void *opaque)
     case TIMER_NONE:
         break;
     case TIMER_INTR:
-        or1k_timer->ttcr = 0;
+        /* Zero the count by applying a negative offset to the counter */
+        or1k_timer->ttcr_offset -= (cpu->env.ttmr & TTMR_TP);
         break;
     case TIMER_SHOT:
         cpu_openrisc_count_stop(cpu);
@@ -137,17 +140,18 @@ static void openrisc_count_reset(void *opaque)
 /* Reset the global timer state. */
 static void openrisc_timer_reset(void *opaque)
 {
-    or1k_timer->ttcr = 0x00000000;
-    or1k_timer->last_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    OpenRISCCPU *cpu = opaque;
+    cpu_openrisc_count_set(cpu, 0);
 }
 
 static const VMStateDescription vmstate_or1k_timer = {
     .name = "or1k_timer",
-    .version_id = 1,
-    .minimum_version_id = 1,
+    .version_id = 2,
+    .minimum_version_id = 2,
     .fields = (const VMStateField[]) {
         VMSTATE_UINT32(ttcr, OR1KTimerState),
-        VMSTATE_UINT64(last_clk, OR1KTimerState),
+        VMSTATE_UINT32(ttcr_offset, OR1KTimerState),
+        VMSTATE_UINT64(clk_offset, OR1KTimerState),
         VMSTATE_END_OF_LIST()
     }
 };