[deliverable/linux.git] / arch / x86 / kernel / pvclock.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);
		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);
}
Commit	Line	Data
7af192c9 GH	1	/* paravirtual clock -- common code used by kvm/xen
	2
	3	This program is free software; you can redistribute it and/or modify
	4	it under the terms of the GNU General Public License as published by
	5	the Free Software Foundation; either version 2 of the License, or
	6	(at your option) any later version.
	7
	8	This program is distributed in the hope that it will be useful,
	9	but WITHOUT ANY WARRANTY; without even the implied warranty of
	10	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	11	GNU General Public License for more details.
	12
	13	You should have received a copy of the GNU General Public License
	14	along with this program; if not, write to the Free Software
	15	Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
	16	*/
	17
	18	#include <linux/kernel.h>
	19	#include <linux/percpu.h>
71056ae2 MT	20	#include <linux/notifier.h>
	21	#include <linux/sched.h>
	22	#include <linux/gfp.h>
	23	#include <linux/bootmem.h>
	24	#include <asm/fixmap.h>
7af192c9 GH	25	#include <asm/pvclock.h>
7af192c9 GH	26
424c32f1 GC	27	static u8 valid_flags __read_mostly = 0;
	28
	29	void pvclock_set_flags(u8 flags)
	30	{
	31	valid_flags = flags;
	32	}
	33
3807f345 GC	34	unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
3807f345 GC	35	{
a0854600	36	u64 pv_tsc_khz = 1000000ULL << 32;
3807f345	37
a0854600	38	do_div(pv_tsc_khz, src->tsc_to_system_mul);
3807f345	39	if (src->tsc_shift < 0)
a0854600	40	pv_tsc_khz <<= -src->tsc_shift;
3807f345	41	else
a0854600 HH	42	pv_tsc_khz >>= src->tsc_shift;
a0854600 HH	43	return pv_tsc_khz;
3807f345 GC	44	}
3807f345 GC	45
d63285e9 MT	46	void pvclock_touch_watchdogs(void)
	47	{
	48	touch_softlockup_watchdog_sync();
	49	clocksource_touch_watchdog();
	50	rcu_cpu_stall_reset();
8b414521	51	reset_hung_task_detector();
d63285e9 MT	52	}
d63285e9 MT	53
489fb490 GC	54	static atomic64_t last_value = ATOMIC64_INIT(0);
489fb490 GC	55
e7a3481c JF	56	void pvclock_resume(void)
	57	{
	58	atomic64_set(&last_value, 0);
	59	}
	60
2697902b MT	61	u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
	62	{
	63	unsigned version;
2697902b MT	64	u8 flags;
	65
	66	do {
3aed64f6	67	version = pvclock_read_begin(src);
ed911b43	68	flags = src->flags;
3aed64f6	69	} while (pvclock_read_retry(src, version));
2697902b MT	70
	71	return flags & valid_flags;
	72	}
	73
7af192c9 GH	74	cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
7af192c9 GH	75	{
7af192c9	76	unsigned version;
dce2db0a	77	cycle_t ret;
489fb490	78	u64 last;
42b5637d	79	u8 flags;
7af192c9 GH	80
7af192c9 GH	81	do {
3aed64f6 PB	82	version = pvclock_read_begin(src);
	83	ret = __pvclock_read_cycles(src);
	84	flags = src->flags;
	85	} while (pvclock_read_retry(src, version));
7af192c9	86
d63285e9 MT	87	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
	88	src->flags &= ~PVCLOCK_GUEST_STOPPED;
	89	pvclock_touch_watchdogs();
	90	}
	91
3a0d7256	92	if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
42b5637d	93	(flags & PVCLOCK_TSC_STABLE_BIT))
3a0d7256 GC	94	return ret;
3a0d7256 GC	95
489fb490 GC	96	/*
	97	* Assumption here is that last_value, a global accumulator, always goes
	98	* forward. If we are less than that, we should not be much smaller.
	99	* We assume there is an error marging we're inside, and then the correction
	100	* does not sacrifice accuracy.
	101	*
	102	* For reads: global may have changed between test and return,
	103	* but this means someone else updated poked the clock at a later time.
	104	* We just need to make sure we are not seeing a backwards event.
	105	*
	106	* For updates: last_value = ret is not enough, since two vcpus could be
	107	* updating at the same time, and one of them could be slightly behind,
	108	* making the assumption that last_value always go forward fail to hold.
	109	*/
	110	last = atomic64_read(&last_value);
	111	do {
	112	if (ret < last)
	113	return last;
	114	last = atomic64_cmpxchg(&last_value, last, ret);
	115	} while (unlikely(last != ret));
	116
7af192c9 GH	117	return ret;
	118	}
	119
	120	void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
	121	struct pvclock_vcpu_time_info *vcpu_time,
	122	struct timespec *ts)
	123	{
	124	u32 version;
	125	u64 delta;
	126	struct timespec now;
	127
	128	/* get wallclock at system boot */
	129	do {
	130	version = wall_clock->version;
	131	rmb(); /* fetch version before time */
	132	now.tv_sec = wall_clock->sec;
	133	now.tv_nsec = wall_clock->nsec;
	134	rmb(); /* fetch time before checking version */
	135	} while ((wall_clock->version & 1) \|\| (version != wall_clock->version));
	136
	137	delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */
	138	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
	139
	140	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
	141	now.tv_sec = delta;
	142
	143	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
	144	}