/* * Declare the memory-mapped vclock data pages. These come from hypervisors. * If we ever reintroduce something like direct access to an MMIO clock like * the HPET again, it will go here as well. * * A load from any of these pages will segfault if the clock in question is * disabled, so appropriate compiler barriers and checks need to be used * to prevent stray loads. * * These declarations MUST NOT be const. The compiler will assume that * an extern const variable has genuinely constant contents, and the * resulting code won't work, since the whole point is that these pages * change over time, possibly while we're accessing them.
*/
#ifdef CONFIG_PARAVIRT_CLOCK /* * This is the vCPU 0 pvclock page. We only use pvclock from the vDSO * if the hypervisor tells us that all vCPUs can get valid data from the * vCPU 0 page.
*/ externstruct pvclock_vsyscall_time_info pvclock_page
__attribute__((visibility("hidden"))); #endif
/* * Note: The kernel and hypervisor must guarantee that cpu ID * number maps 1:1 to per-CPU pvclock time info. * * Because the hypervisor is entirely unaware of guest userspace * preemption, it cannot guarantee that per-CPU pvclock time * info is updated if the underlying CPU changes or that that * version is increased whenever underlying CPU changes. * * On KVM, we are guaranteed that pvti updates for any vCPU are * atomic as seen by *all* vCPUs. This is an even stronger * guarantee than we get with a normal seqlock. * * On Xen, we don't appear to have that guarantee, but Xen still * supplies a valid seqlock using the version field. * * We only do pvclock vdso timing at all if * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to * mean that all vCPUs have matching pvti and that the TSC is * synced, so we can just look at vCPU 0's pvti.
*/
do {
version = pvclock_read_begin(pvti);
if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) return U64_MAX;
ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
} while (pvclock_read_retry(pvti, version));
if (hv_read_tsc_page_tsc(&hvclock_page, &tsc, &time)) return time & S64_MAX;
return U64_MAX;
} #endif
staticinline u64 __arch_get_hw_counter(s32 clock_mode, conststruct vdso_time_data *vd)
{ if (likely(clock_mode == VDSO_CLOCKMODE_TSC)) return (u64)rdtsc_ordered() & S64_MAX; /* * For any memory-mapped vclock type, we need to make sure that gcc * doesn't cleverly hoist a load before the mode check. Otherwise we * might end up touching the memory-mapped page even if the vclock in * question isn't enabled, which will segfault. Hence the barriers.
*/ #ifdef CONFIG_PARAVIRT_CLOCK if (clock_mode == VDSO_CLOCKMODE_PVCLOCK) {
barrier(); return vread_pvclock();
} #endif #ifdef CONFIG_HYPERV_TIMER if (clock_mode == VDSO_CLOCKMODE_HVCLOCK) {
barrier(); return vread_hvclock();
} #endif return U64_MAX;
}
/* * Clocksource read value validation to handle PV and HyperV clocksources * which can be invalidated asynchronously and indicate invalidation by * returning U64_MAX, which can be effectively tested by checking for a * negative value after casting it to s64. * * This effectively forces a S64_MAX mask on the calculations, unlike the * U64_MAX mask normally used by x86 clocksources.
*/ staticinlinebool arch_vdso_cycles_ok(u64 cycles)
{ return (s64)cycles >= 0;
} #define vdso_cycles_ok arch_vdso_cycles_ok
/* * x86 specific calculation of nanoseconds for the current cycle count * * The regular implementation assumes that clocksource reads are globally * monotonic. The TSC can be slightly off across sockets which can cause * the regular delta calculation (@cycles - @last) to return a huge time * jump. * * Therefore it needs to be verified that @cycles are greater than * @vd->cycles_last. If not then use @vd->cycles_last, which is the base * time of the current conversion period. * * This variant also uses a custom mask because while the clocksource mask of * all the VDSO capable clocksources on x86 is U64_MAX, the above code uses * U64_MASK as an exception value, additionally arch_vdso_cycles_ok() above * declares everything with the MSB/Sign-bit set as invalid. Therefore the * effective mask is S64_MAX.
*/ static __always_inline u64 vdso_calc_ns(conststruct vdso_clock *vc, u64 cycles, u64 base)
{
u64 delta = cycles - vc->cycle_last;
/* * Negative motion and deltas which can cause multiplication * overflow require special treatment. This check covers both as * negative motion is guaranteed to be greater than @vc::max_cycles * due to unsigned comparison. * * Due to the MSB/Sign-bit being used as invalid marker (see * arch_vdso_cycles_ok() above), the effective mask is S64_MAX, but that * case is also unlikely and will also take the unlikely path here.
*/ if (unlikely(delta > vc->max_cycles)) { /* * Due to the above mentioned TSC wobbles, filter out * negative motion. Per the above masking, the effective * sign bit is now bit 62.
*/ if (delta & (1ULL << 62)) return base >> vc->shift;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
