Currently hv_read_tsc_page_tsc() (ab)uses the (valid) time value of
U64_MAX as an error return. This breaks the clean wrap-around of the
clock.
Modify the function signature to return a boolean state and provide
another u64 pointer to store the actual time on success. This obviates
the need to steal one time value and restores the full counter width.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Tested-by: Michael Kelley <mikelley@microsoft.com> # Hyper-V
Link: https://lore.kernel.org/r/20230519102715.775630881@infradead.org
#ifdef CONFIG_HYPERV_TIMER
static u64 vread_hvclock(void)
{
- u64 ret = hv_read_tsc_page(&hvclock_page);
- if (likely(ret != U64_MAX))
- ret &= S64_MAX;
- return ret;
+ u64 tsc, time;
+
+ if (hv_read_tsc_page_tsc(&hvclock_page, &tsc, &time))
+ return time & S64_MAX;
+
+ return U64_MAX;
}
#endif
static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
int *mode)
{
- long v;
u64 tsc_pg_val;
+ long v;
switch (clock->vclock_mode) {
case VDSO_CLOCKMODE_HVCLOCK:
- tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
- tsc_timestamp);
- if (tsc_pg_val != U64_MAX) {
+ if (hv_read_tsc_page_tsc(hv_get_tsc_page(),
+ tsc_timestamp, &tsc_pg_val)) {
/* TSC page valid */
*mode = VDSO_CLOCKMODE_HVCLOCK;
v = (tsc_pg_val - clock->cycle_last) &
}
EXPORT_SYMBOL_GPL(hv_get_tsc_page);
-static u64 notrace read_hv_clock_tsc(void)
+static notrace u64 read_hv_clock_tsc(void)
{
- u64 current_tick = hv_read_tsc_page(hv_get_tsc_page());
+ u64 cur_tsc, time;
- if (current_tick == U64_MAX)
- current_tick = hv_get_register(HV_REGISTER_TIME_REF_COUNT);
+ /*
+ * The Hyper-V Top-Level Function Spec (TLFS), section Timers,
+ * subsection Refererence Counter, guarantees that the TSC and MSR
+ * times are in sync and monotonic. Therefore we can fall back
+ * to the MSR in case the TSC page indicates unavailability.
+ */
+ if (!hv_read_tsc_page_tsc(tsc_page, &cur_tsc, &time))
+ time = hv_get_register(HV_REGISTER_TIME_REF_COUNT);
- return current_tick;
+ return time;
}
static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg)
extern unsigned long hv_get_tsc_pfn(void);
extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline notrace u64
-hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
+static __always_inline bool
+hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+ u64 *cur_tsc, u64 *time)
{
u64 scale, offset;
u32 sequence;
do {
sequence = READ_ONCE(tsc_pg->tsc_sequence);
if (!sequence)
- return U64_MAX;
+ return false;
/*
* Make sure we read sequence before we read other values from
* TSC page.
} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
- return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
-}
-
-static inline notrace u64
-hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
-{
- u64 cur_tsc;
-
- return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
+ *time = mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
+ return true;
}
#else /* CONFIG_HYPERV_TIMER */
return NULL;
}
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
- u64 *cur_tsc)
+static __always_inline bool
+hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)
{
- return U64_MAX;
+ return false;
}
static inline int hv_stimer_cleanup(unsigned int cpu) { return 0; }