| Message ID | 1440703987-29012-6-git-send-email-lvivier@redhat.com |
|---|---|
| State | New |
| Headers | show |
ping ? On 27/08/2015 21:33, Laurent Vivier wrote: > Originally, timers were ticks based, and it made sense to > add ticks to current time to know when to trigger an alarm. > > But since commit: > > 7447545 change all other clock references to use nanosecond resolution accessors > > All timers use nanoseconds and we need to convert ticks to nanoseconds, by > doing something like: > > y = muldiv64(x, get_ticks_per_sec(), TIMER_FREQ) > > where x is the number of device ticks and y the number of system ticks. > > y is used as nanoseconds in timer functions, > it works because 1 tick is 1 nanosecond. > (get_ticks_per_sec() is 10^9) > > But as openrisc timer frequency is 20 MHz, we can also do: > > y = x * 50; /* 20 MHz period is 50 ns */ > > Signed-off-by: Laurent Vivier <lvivier@redhat.com> > --- > hw/openrisc/cputimer.c | 7 +++---- > 1 file changed, 3 insertions(+), 4 deletions(-) > > diff --git a/hw/openrisc/cputimer.c b/hw/openrisc/cputimer.c > index 9c54945..560cb91 100644 > --- a/hw/openrisc/cputimer.c > +++ b/hw/openrisc/cputimer.c > @@ -22,7 +22,7 @@ > #include "hw/hw.h" > #include "qemu/timer.h" > > -#define TIMER_FREQ (20 * 1000 * 1000) /* 20MHz */ > +#define TIMER_PERIOD 50 /* 50 ns period for 20 MHz timer */ > > /* The time when TTCR changes */ > static uint64_t last_clk; > @@ -36,8 +36,7 @@ void cpu_openrisc_count_update(OpenRISCCPU *cpu) > return; > } > now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); > - cpu->env.ttcr += (uint32_t)muldiv64(now - last_clk, TIMER_FREQ, > - get_ticks_per_sec()); > + cpu->env.ttcr += (uint32_t)((now - last_clk) / TIMER_PERIOD); > last_clk = now; > } > > @@ -59,7 +58,7 @@ void cpu_openrisc_timer_update(OpenRISCCPU *cpu) > } else { > wait = (cpu->env.ttmr & TTMR_TP) - (cpu->env.ttcr & TTMR_TP); > } > - next = now + muldiv64(wait, get_ticks_per_sec(), TIMER_FREQ); > + next = now + (uint64_t)wait * TIMER_PERIOD; > timer_mod(cpu->env.timer, next); > } > >
diff --git a/hw/openrisc/cputimer.c b/hw/openrisc/cputimer.c index 9c54945..560cb91 100644 --- a/hw/openrisc/cputimer.c +++ b/hw/openrisc/cputimer.c @@ -22,7 +22,7 @@ #include "hw/hw.h" #include "qemu/timer.h" -#define TIMER_FREQ (20 * 1000 * 1000) /* 20MHz */ +#define TIMER_PERIOD 50 /* 50 ns period for 20 MHz timer */ /* The time when TTCR changes */ static uint64_t last_clk; @@ -36,8 +36,7 @@ void cpu_openrisc_count_update(OpenRISCCPU *cpu) return; } now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - cpu->env.ttcr += (uint32_t)muldiv64(now - last_clk, TIMER_FREQ, - get_ticks_per_sec()); + cpu->env.ttcr += (uint32_t)((now - last_clk) / TIMER_PERIOD); last_clk = now; } @@ -59,7 +58,7 @@ void cpu_openrisc_timer_update(OpenRISCCPU *cpu) } else { wait = (cpu->env.ttmr & TTMR_TP) - (cpu->env.ttcr & TTMR_TP); } - next = now + muldiv64(wait, get_ticks_per_sec(), TIMER_FREQ); + next = now + (uint64_t)wait * TIMER_PERIOD; timer_mod(cpu->env.timer, next); }
Originally, timers were ticks based, and it made sense to add ticks to current time to know when to trigger an alarm. But since commit: 7447545 change all other clock references to use nanosecond resolution accessors All timers use nanoseconds and we need to convert ticks to nanoseconds, by doing something like: y = muldiv64(x, get_ticks_per_sec(), TIMER_FREQ) where x is the number of device ticks and y the number of system ticks. y is used as nanoseconds in timer functions, it works because 1 tick is 1 nanosecond. (get_ticks_per_sec() is 10^9) But as openrisc timer frequency is 20 MHz, we can also do: y = x * 50; /* 20 MHz period is 50 ns */ Signed-off-by: Laurent Vivier <lvivier@redhat.com> --- hw/openrisc/cputimer.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)