void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
{
unsigned long r, w;
u64 res, wrap;
char r_unit;
if (cd.rate > rate)
return;
BUG_ON(bits > 32);
WARN_ON(!irqs_disabled());
read_sched_clock = read;
sched_clock_mask = (1 << bits) - 1;
cd.rate = rate;
/* calculate the mult/shift to convert counter ticks to ns. */
clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
r = rate;
if (r >= 4000000) {
r /= 1000000;
r_unit = 'M';
} else if (r >= 1000) {
r /= 1000;
r_unit = 'k';
} else
r_unit = ' ';
/* calculate how many ns until we wrap */
wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
do_div(wrap, NSEC_PER_MSEC);
w = wrap;
/* calculate the ns resolution of this counter */
res = cyc_to_ns(1ULL, cd.mult, cd.shift);
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
bits, r, r_unit, res, w);
/*
* Start the timer to keep sched_clock() properly updated and
* sets the initial epoch.
*/
sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
update_sched_clock();
/*
* Ensure that sched_clock() starts off at 0ns
*/
cd.epoch_ns = 0;
/* Enable IRQ time accounting if we have a fast enough sched_clock */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
pr_debug("Registered %pF as sched_clock source\n", read);
}
static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
{
u64 epoch_ns;
u32 epoch_cyc;
if (cd.suspended)
return cd.epoch_ns;
/*
* Load the epoch_cyc and epoch_ns atomically. We do this by
* ensuring that we always write epoch_cyc, epoch_ns and
* epoch_cyc_copy in strict order, and read them in strict order.
* If epoch_cyc and epoch_cyc_copy are not equal, then we're in
* the middle of an update, and we should repeat the load.
*/
do {
epoch_cyc = cd.epoch_cyc;
smp_rmb();
epoch_ns = cd.epoch_ns;
smp_rmb();
} while (epoch_cyc != cd.epoch_cyc_copy);
cyc = read_sched_clock();
cyc = (cyc - epoch_cyc) & sched_clock_mask;
return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
}
void __init register_current_timer_delay(const struct delay_timer *timer)
{
u32 new_mult, new_shift;
u64 res;
clocks_calc_mult_shift(&new_mult, &new_shift, timer->freq,
NSEC_PER_SEC, 3600);
res = cyc_to_ns(1ULL, new_mult, new_shift);
if (res > 1000) {
pr_err("Ignoring delay timer %ps, which has insufficient resolution of %lluns\n",
timer, res);
return;
}
if (!delay_calibrated && (!delay_res || (res < delay_res))) {
pr_info("Switching to timer-based delay loop, resolution %lluns\n", res);
delay_timer = timer;
lpj_fine = timer->freq / HZ;
delay_res = res;
/* cpufreq may scale loops_per_jiffy, so keep a private copy */
arm_delay_ops.ticks_per_jiffy = lpj_fine;
arm_delay_ops.delay = __timer_delay;
arm_delay_ops.const_udelay = __timer_const_udelay;
arm_delay_ops.udelay = __timer_udelay;
} else {
pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
}
}
void __init init_sched_clock(struct clock_data *cd, void (*update)(void),
unsigned int clock_bits, unsigned long rate)
{
unsigned long r, w;
u64 res, wrap;
char r_unit;
sched_clock_update_fn = update;
/* calculate the mult/shift to convert counter ticks to ns. */
clocks_calc_mult_shift(&cd->mult, &cd->shift, rate, NSEC_PER_SEC, 60);
r = rate;
if (r >= 4000000) {
r /= 1000000;
r_unit = 'M';
} else {
r /= 1000;
r_unit = 'k';
}
/* calculate how many ns until we wrap */
wrap = cyc_to_ns((1ULL << clock_bits) - 1, cd->mult, cd->shift);
do_div(wrap, NSEC_PER_MSEC);
w = wrap;
/* calculate the ns resolution of this counter */
res = cyc_to_ns(1ULL, cd->mult, cd->shift);
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
clock_bits, r, r_unit, res, w);
/*
* Start the timer to keep sched_clock() properly updated and
* sets the initial epoch.
*/
sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
update();
/*
* Ensure that sched_clock() starts off at 0ns
*/
cd->epoch_ns = 0;
}
void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
{
unsigned long r, w;
u64 res, wrap;
char r_unit;
BUG_ON(bits > 32);
WARN_ON(!irqs_disabled());
WARN_ON(read_sched_clock != jiffy_sched_clock_read);
read_sched_clock = read;
sched_clock_mask = (1 << bits) - 1;
clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
r = rate;
if (r >= 4000000) {
r /= 1000000;
r_unit = 'M';
} else if (r >= 1000) {
r /= 1000;
r_unit = 'k';
} else
r_unit = ' ';
wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
do_div(wrap, NSEC_PER_MSEC);
w = wrap;
res = cyc_to_ns(1ULL, cd.mult, cd.shift);
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
bits, r, r_unit, res, w);
sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
update_sched_clock();
cd.epoch_ns = 0;
pr_debug("Registered %pF as sched_clock source\n", read);
}
static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
{
u64 epoch_ns;
u32 epoch_cyc;
do {
epoch_cyc = cd.epoch_cyc;
smp_rmb();
epoch_ns = cd.epoch_ns;
smp_rmb();
} while (epoch_cyc != cd.epoch_cyc_copy);
return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift);
}
static void notrace update_sched_clock(void)
{
unsigned long flags;
u32 cyc;
u64 ns;
cyc = read_sched_clock();
ns = cd.epoch_ns +
cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
cd.mult, cd.shift);
raw_local_irq_save(flags);
cd.epoch_cyc = cyc;
smp_wmb();
cd.epoch_ns = ns;
smp_wmb();
cd.epoch_cyc_copy = cyc;
raw_local_irq_restore(flags);
}
/*
* Atomically update the sched_clock epoch.
*/
static void notrace update_sched_clock(void)
{
unsigned long flags;
u32 cyc;
u64 ns;
cyc = read_sched_clock();
ns = cd.epoch_ns +
cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
cd.mult, cd.shift);
/*
* Write epoch_cyc and epoch_ns in a way that the update is
* detectable in cyc_to_fixed_sched_clock().
*/
raw_local_irq_save(flags);
cd.epoch_cyc_copy = cyc;
smp_wmb();
cd.epoch_ns = ns;
smp_wmb();
cd.epoch_cyc = cyc;
raw_local_irq_restore(flags);
}
