mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 12:56:45 +07:00
108b249c45
Introduce a function that reads the exact nanoseconds value that is provided to the guest in kvmclock. This crystallizes the notion of kvmclock as a thin veneer over a stable TSC, that the guest will (hopefully) convert with NTP. In other words, kvmclock is *not* a paravirtualized host-to-guest NTP. Drop the get_kernel_ns() function, that was used both to get the base value of the master clock and to get the current value of kvmclock. The former use is replaced by ktime_get_boot_ns(), the latter is the purpose of get_kernel_ns(). This also allows KVM to provide a Hyper-V time reference counter that is synchronized with the time that is computed from the TSC page. Reviewed-by: Roman Kagan <rkagan@virtuozzo.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
145 lines
3.9 KiB
C
145 lines
3.9 KiB
C
/* paravirtual clock -- common code used by kvm/xen
|
|
|
|
This program is free software; you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; either version 2 of the License, or
|
|
(at your option) any later version.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with this program; if not, write to the Free Software
|
|
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/bootmem.h>
|
|
#include <asm/fixmap.h>
|
|
#include <asm/pvclock.h>
|
|
|
|
static u8 valid_flags __read_mostly = 0;
|
|
|
|
void pvclock_set_flags(u8 flags)
|
|
{
|
|
valid_flags = flags;
|
|
}
|
|
|
|
unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
|
|
{
|
|
u64 pv_tsc_khz = 1000000ULL << 32;
|
|
|
|
do_div(pv_tsc_khz, src->tsc_to_system_mul);
|
|
if (src->tsc_shift < 0)
|
|
pv_tsc_khz <<= -src->tsc_shift;
|
|
else
|
|
pv_tsc_khz >>= src->tsc_shift;
|
|
return pv_tsc_khz;
|
|
}
|
|
|
|
void pvclock_touch_watchdogs(void)
|
|
{
|
|
touch_softlockup_watchdog_sync();
|
|
clocksource_touch_watchdog();
|
|
rcu_cpu_stall_reset();
|
|
reset_hung_task_detector();
|
|
}
|
|
|
|
static atomic64_t last_value = ATOMIC64_INIT(0);
|
|
|
|
void pvclock_resume(void)
|
|
{
|
|
atomic64_set(&last_value, 0);
|
|
}
|
|
|
|
u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
|
|
{
|
|
unsigned version;
|
|
u8 flags;
|
|
|
|
do {
|
|
version = pvclock_read_begin(src);
|
|
flags = src->flags;
|
|
} while (pvclock_read_retry(src, version));
|
|
|
|
return flags & valid_flags;
|
|
}
|
|
|
|
cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
|
|
{
|
|
unsigned version;
|
|
cycle_t ret;
|
|
u64 last;
|
|
u8 flags;
|
|
|
|
do {
|
|
version = pvclock_read_begin(src);
|
|
ret = __pvclock_read_cycles(src, rdtsc_ordered());
|
|
flags = src->flags;
|
|
} while (pvclock_read_retry(src, version));
|
|
|
|
if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
|
|
src->flags &= ~PVCLOCK_GUEST_STOPPED;
|
|
pvclock_touch_watchdogs();
|
|
}
|
|
|
|
if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
|
|
(flags & PVCLOCK_TSC_STABLE_BIT))
|
|
return ret;
|
|
|
|
/*
|
|
* Assumption here is that last_value, a global accumulator, always goes
|
|
* forward. If we are less than that, we should not be much smaller.
|
|
* We assume there is an error marging we're inside, and then the correction
|
|
* does not sacrifice accuracy.
|
|
*
|
|
* For reads: global may have changed between test and return,
|
|
* but this means someone else updated poked the clock at a later time.
|
|
* We just need to make sure we are not seeing a backwards event.
|
|
*
|
|
* For updates: last_value = ret is not enough, since two vcpus could be
|
|
* updating at the same time, and one of them could be slightly behind,
|
|
* making the assumption that last_value always go forward fail to hold.
|
|
*/
|
|
last = atomic64_read(&last_value);
|
|
do {
|
|
if (ret < last)
|
|
return last;
|
|
last = atomic64_cmpxchg(&last_value, last, ret);
|
|
} while (unlikely(last != ret));
|
|
|
|
return ret;
|
|
}
|
|
|
|
void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
|
|
struct pvclock_vcpu_time_info *vcpu_time,
|
|
struct timespec *ts)
|
|
{
|
|
u32 version;
|
|
u64 delta;
|
|
struct timespec now;
|
|
|
|
/* get wallclock at system boot */
|
|
do {
|
|
version = wall_clock->version;
|
|
rmb(); /* fetch version before time */
|
|
now.tv_sec = wall_clock->sec;
|
|
now.tv_nsec = wall_clock->nsec;
|
|
rmb(); /* fetch time before checking version */
|
|
} while ((wall_clock->version & 1) || (version != wall_clock->version));
|
|
|
|
delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */
|
|
delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
|
|
|
|
now.tv_nsec = do_div(delta, NSEC_PER_SEC);
|
|
now.tv_sec = delta;
|
|
|
|
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
|
|
}
|