@@ -240,7 +240,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
{
struct mlx4_dev *dev = mdev->dev;
unsigned long flags;
- u64 ns;
+ u64 ns, zero = 0;
rwlock_init(&mdev->clock_lock);
@@ -265,7 +265,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
/* Calculate period in seconds to call the overflow watchdog - to make
* sure counter is checked at least once every wrap around.
*/
- ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask);
+ ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask, zero, &zero);
do_div(ns, NSEC_PER_SEC / 2 / HZ);
mdev->overflow_period = ns;
@@ -55,27 +55,32 @@ struct cyclecounter {
* @cycle_last: most recent cycle counter value seen by
* timecounter_read()
* @nsec: continuously increasing count
+ * @mask: bit mask for maintaining the 'frac' field
+ * @frac: accumulated fractional nanoseconds
*/
struct timecounter {
const struct cyclecounter *cc;
cycle_t cycle_last;
u64 nsec;
+ u64 mask;
+ u64 frac;
};
/**
* cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
* @cc: Pointer to cycle counter.
* @cycles: Cycles
- *
- * XXX - This could use some mult_lxl_ll() asm optimization. Same code
- * as in cyc2ns, but with unsigned result.
+ * @mask: bit mask for maintaining the 'frac' field
+ * @frac: pointer to storage for the fractional nanoseconds.
*/
static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
- cycle_t cycles)
+ cycle_t cycles, u64 mask, u64 *frac)
{
- u64 ret = (u64)cycles;
- ret = (ret * cc->mult) >> cc->shift;
- return ret;
+ u64 ns = (u64) cycles;
+
+ ns = (ns * cc->mult) + *frac;
+ *frac = ns & mask;
+ return ns >> cc->shift;
}
/**
@@ -25,6 +25,8 @@ void timecounter_init(struct timecounter *tc,
tc->cc = cc;
tc->cycle_last = cc->read(cc);
tc->nsec = start_tstamp;
+ tc->mask = (1ULL << cc->shift) - 1;
+ tc->frac = 0;
}
EXPORT_SYMBOL_GPL(timecounter_init);
@@ -51,7 +53,8 @@ static u64 timecounter_read_delta(struct timecounter *tc)
cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
/* convert to nanoseconds: */
- ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
+ ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta,
+ tc->mask, &tc->frac);
/* update time stamp of timecounter_read_delta() call: */
tc->cycle_last = cycle_now;
@@ -72,22 +75,36 @@ u64 timecounter_read(struct timecounter *tc)
}
EXPORT_SYMBOL_GPL(timecounter_read);
+/*
+ * This is like cyclecounter_cyc2ns(), but it is used for computing a
+ * time previous to the time stored in the cycle counter.
+ */
+static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
+ cycle_t cycles, u64 mask, u64 frac)
+{
+ u64 ns = (u64) cycles;
+
+ ns = ((ns * cc->mult) - frac) >> cc->shift;
+
+ return ns;
+}
+
u64 timecounter_cyc2time(struct timecounter *tc,
cycle_t cycle_tstamp)
{
- u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
- u64 nsec;
+ u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+ u64 nsec = tc->nsec, frac = tc->frac;
/*
* Instead of always treating cycle_tstamp as more recent
* than tc->cycle_last, detect when it is too far in the
* future and treat it as old time stamp instead.
*/
- if (cycle_delta > tc->cc->mask / 2) {
- cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
- nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
+ if (delta > tc->cc->mask / 2) {
+ delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+ nsec -= cc_cyc2ns_backwards(tc->cc, delta, tc->mask, frac);
} else {
- nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
+ nsec += cyclecounter_cyc2ns(tc->cc, delta, tc->mask, &frac);
}
return nsec;
@@ -150,7 +150,8 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
return;
}
- ns = cyclecounter_cyc2ns(timecounter->cc, cval - now);
+ ns = cyclecounter_cyc2ns(timecounter->cc, cval - now, timecounter->mask,
+ &timecounter->frac);
timer_arm(timer, ns);
}
The current timecounter implementation will drop a variable amount of resolution, depending on the magnitude of the time delta. In other words, reading the clock too often or too close to a time stamp conversion will introduce errors into the time values. This patch fixes the issue by introducing a fractional nanosecond field that accumulates the low order bits. Reported-by: Janusz Użycki <j.uzycki@elproma.com.pl> Signed-off-by: Richard Cochran <richardcochran@gmail.com> --- drivers/net/ethernet/mellanox/mlx4/en_clock.c | 4 ++-- include/linux/timecounter.h | 19 +++++++++------ kernel/time/timecounter.c | 31 +++++++++++++++++++------ virt/kvm/arm/arch_timer.c | 3 ++- 4 files changed, 40 insertions(+), 17 deletions(-)