mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 17:10:50 +07:00
332962f2c8
Up to commit 5d33b883a
(clocksource: Always verify highres capability)
we had no sanity check when selecting a clocksource, which prevented
that a non highres capable clocksource is used when the system already
switched to highres/nohz mode.
The new sanity check works as Alex and Tim found out. It prevents the
TSC from being used. This happens because on x86 the boot process
looks like this:
tsc_start_freqency_validation(TSC);
clocksource_register(HPET);
clocksource_done_booting();
clocksource_select()
Selects HPET which is valid for high-res
switch_to_highres();
clocksource_register(TSC);
TSC is not selected, because it is not yet
flagged as VALID_HIGH_RES
clocksource_watchdog()
Validates TSC for highres, but that does not make TSC
the current clocksource.
Before the sanity check was added, we installed TSC unvalidated which
worked most of the time. If the TSC was really detected as unstable,
then the unstable logic removed it and installed HPET again.
The sanity check is correct and needed. So the watchdog needs to kick
a reselection of the clocksource, when it qualifies TSC as a valid
high res clocksource.
To solve this, we mark the clocksource which got the flag
CLOCK_SOURCE_VALID_FOR_HRES set by the watchdog with an new flag
CLOCK_SOURCE_RESELECT and trigger the watchdog thread. The watchdog
thread evaluates the flag and invokes clocksource_select() when set.
To avoid that the clocksource_done_booting() code, which is about to
install the first real clocksource anyway, needs to go through
clocksource_select and tick_oneshot_notify() pointlessly, split out
the clocksource_watchdog_kthread() list walk code and invoke the
select/notify only when called from clocksource_watchdog_kthread().
So clocksource_done_booting() can utilize the same splitout code
without the select/notify invocation and the clocksource_mutex
unlock/relock dance.
Reported-and-tested-by: Alex Shi <alex.shi@intel.com>
Cc: Hans Peter Anvin <hpa@linux.intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Tested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Davidlohr Bueso <davidlohr.bueso@hp.com>
Cc: John Stultz <john.stultz@linaro.org>
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1307042239150.11637@ionos.tec.linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
360 lines
11 KiB
C
360 lines
11 KiB
C
/* linux/include/linux/clocksource.h
|
|
*
|
|
* This file contains the structure definitions for clocksources.
|
|
*
|
|
* If you are not a clocksource, or timekeeping code, you should
|
|
* not be including this file!
|
|
*/
|
|
#ifndef _LINUX_CLOCKSOURCE_H
|
|
#define _LINUX_CLOCKSOURCE_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/timex.h>
|
|
#include <linux/time.h>
|
|
#include <linux/list.h>
|
|
#include <linux/cache.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/init.h>
|
|
#include <asm/div64.h>
|
|
#include <asm/io.h>
|
|
|
|
/* clocksource cycle base type */
|
|
typedef u64 cycle_t;
|
|
struct clocksource;
|
|
struct module;
|
|
|
|
#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
|
|
#include <asm/clocksource.h>
|
|
#endif
|
|
|
|
/**
|
|
* struct cyclecounter - hardware abstraction for a free running counter
|
|
* Provides completely state-free accessors to the underlying hardware.
|
|
* Depending on which hardware it reads, the cycle counter may wrap
|
|
* around quickly. Locking rules (if necessary) have to be defined
|
|
* by the implementor and user of specific instances of this API.
|
|
*
|
|
* @read: returns the current cycle value
|
|
* @mask: bitmask for two's complement
|
|
* subtraction of non 64 bit counters,
|
|
* see CLOCKSOURCE_MASK() helper macro
|
|
* @mult: cycle to nanosecond multiplier
|
|
* @shift: cycle to nanosecond divisor (power of two)
|
|
*/
|
|
struct cyclecounter {
|
|
cycle_t (*read)(const struct cyclecounter *cc);
|
|
cycle_t mask;
|
|
u32 mult;
|
|
u32 shift;
|
|
};
|
|
|
|
/**
|
|
* struct timecounter - layer above a %struct cyclecounter which counts nanoseconds
|
|
* Contains the state needed by timecounter_read() to detect
|
|
* cycle counter wrap around. Initialize with
|
|
* timecounter_init(). Also used to convert cycle counts into the
|
|
* corresponding nanosecond counts with timecounter_cyc2time(). Users
|
|
* of this code are responsible for initializing the underlying
|
|
* cycle counter hardware, locking issues and reading the time
|
|
* more often than the cycle counter wraps around. The nanosecond
|
|
* counter will only wrap around after ~585 years.
|
|
*
|
|
* @cc: the cycle counter used by this instance
|
|
* @cycle_last: most recent cycle counter value seen by
|
|
* timecounter_read()
|
|
* @nsec: continuously increasing count
|
|
*/
|
|
struct timecounter {
|
|
const struct cyclecounter *cc;
|
|
cycle_t cycle_last;
|
|
u64 nsec;
|
|
};
|
|
|
|
/**
|
|
* 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.
|
|
*/
|
|
static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
|
|
cycle_t cycles)
|
|
{
|
|
u64 ret = (u64)cycles;
|
|
ret = (ret * cc->mult) >> cc->shift;
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* timecounter_init - initialize a time counter
|
|
* @tc: Pointer to time counter which is to be initialized/reset
|
|
* @cc: A cycle counter, ready to be used.
|
|
* @start_tstamp: Arbitrary initial time stamp.
|
|
*
|
|
* After this call the current cycle register (roughly) corresponds to
|
|
* the initial time stamp. Every call to timecounter_read() increments
|
|
* the time stamp counter by the number of elapsed nanoseconds.
|
|
*/
|
|
extern void timecounter_init(struct timecounter *tc,
|
|
const struct cyclecounter *cc,
|
|
u64 start_tstamp);
|
|
|
|
/**
|
|
* timecounter_read - return nanoseconds elapsed since timecounter_init()
|
|
* plus the initial time stamp
|
|
* @tc: Pointer to time counter.
|
|
*
|
|
* In other words, keeps track of time since the same epoch as
|
|
* the function which generated the initial time stamp.
|
|
*/
|
|
extern u64 timecounter_read(struct timecounter *tc);
|
|
|
|
/**
|
|
* timecounter_cyc2time - convert a cycle counter to same
|
|
* time base as values returned by
|
|
* timecounter_read()
|
|
* @tc: Pointer to time counter.
|
|
* @cycle_tstamp: a value returned by tc->cc->read()
|
|
*
|
|
* Cycle counts that are converted correctly as long as they
|
|
* fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
|
|
* with "max cycle count" == cs->mask+1.
|
|
*
|
|
* This allows conversion of cycle counter values which were generated
|
|
* in the past.
|
|
*/
|
|
extern u64 timecounter_cyc2time(struct timecounter *tc,
|
|
cycle_t cycle_tstamp);
|
|
|
|
/**
|
|
* struct clocksource - hardware abstraction for a free running counter
|
|
* Provides mostly state-free accessors to the underlying hardware.
|
|
* This is the structure used for system time.
|
|
*
|
|
* @name: ptr to clocksource name
|
|
* @list: list head for registration
|
|
* @rating: rating value for selection (higher is better)
|
|
* To avoid rating inflation the following
|
|
* list should give you a guide as to how
|
|
* to assign your clocksource a rating
|
|
* 1-99: Unfit for real use
|
|
* Only available for bootup and testing purposes.
|
|
* 100-199: Base level usability.
|
|
* Functional for real use, but not desired.
|
|
* 200-299: Good.
|
|
* A correct and usable clocksource.
|
|
* 300-399: Desired.
|
|
* A reasonably fast and accurate clocksource.
|
|
* 400-499: Perfect
|
|
* The ideal clocksource. A must-use where
|
|
* available.
|
|
* @read: returns a cycle value, passes clocksource as argument
|
|
* @enable: optional function to enable the clocksource
|
|
* @disable: optional function to disable the clocksource
|
|
* @mask: bitmask for two's complement
|
|
* subtraction of non 64 bit counters
|
|
* @mult: cycle to nanosecond multiplier
|
|
* @shift: cycle to nanosecond divisor (power of two)
|
|
* @max_idle_ns: max idle time permitted by the clocksource (nsecs)
|
|
* @maxadj: maximum adjustment value to mult (~11%)
|
|
* @flags: flags describing special properties
|
|
* @archdata: arch-specific data
|
|
* @suspend: suspend function for the clocksource, if necessary
|
|
* @resume: resume function for the clocksource, if necessary
|
|
* @cycle_last: most recent cycle counter value seen by ::read()
|
|
* @owner: module reference, must be set by clocksource in modules
|
|
*/
|
|
struct clocksource {
|
|
/*
|
|
* Hotpath data, fits in a single cache line when the
|
|
* clocksource itself is cacheline aligned.
|
|
*/
|
|
cycle_t (*read)(struct clocksource *cs);
|
|
cycle_t cycle_last;
|
|
cycle_t mask;
|
|
u32 mult;
|
|
u32 shift;
|
|
u64 max_idle_ns;
|
|
u32 maxadj;
|
|
#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
|
|
struct arch_clocksource_data archdata;
|
|
#endif
|
|
|
|
const char *name;
|
|
struct list_head list;
|
|
int rating;
|
|
int (*enable)(struct clocksource *cs);
|
|
void (*disable)(struct clocksource *cs);
|
|
unsigned long flags;
|
|
void (*suspend)(struct clocksource *cs);
|
|
void (*resume)(struct clocksource *cs);
|
|
|
|
/* private: */
|
|
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
|
|
/* Watchdog related data, used by the framework */
|
|
struct list_head wd_list;
|
|
cycle_t cs_last;
|
|
cycle_t wd_last;
|
|
#endif
|
|
struct module *owner;
|
|
} ____cacheline_aligned;
|
|
|
|
/*
|
|
* Clock source flags bits::
|
|
*/
|
|
#define CLOCK_SOURCE_IS_CONTINUOUS 0x01
|
|
#define CLOCK_SOURCE_MUST_VERIFY 0x02
|
|
|
|
#define CLOCK_SOURCE_WATCHDOG 0x10
|
|
#define CLOCK_SOURCE_VALID_FOR_HRES 0x20
|
|
#define CLOCK_SOURCE_UNSTABLE 0x40
|
|
#define CLOCK_SOURCE_SUSPEND_NONSTOP 0x80
|
|
#define CLOCK_SOURCE_RESELECT 0x100
|
|
|
|
/* simplify initialization of mask field */
|
|
#define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
|
|
|
|
/**
|
|
* clocksource_khz2mult - calculates mult from khz and shift
|
|
* @khz: Clocksource frequency in KHz
|
|
* @shift_constant: Clocksource shift factor
|
|
*
|
|
* Helper functions that converts a khz counter frequency to a timsource
|
|
* multiplier, given the clocksource shift value
|
|
*/
|
|
static inline u32 clocksource_khz2mult(u32 khz, u32 shift_constant)
|
|
{
|
|
/* khz = cyc/(Million ns)
|
|
* mult/2^shift = ns/cyc
|
|
* mult = ns/cyc * 2^shift
|
|
* mult = 1Million/khz * 2^shift
|
|
* mult = 1000000 * 2^shift / khz
|
|
* mult = (1000000<<shift) / khz
|
|
*/
|
|
u64 tmp = ((u64)1000000) << shift_constant;
|
|
|
|
tmp += khz/2; /* round for do_div */
|
|
do_div(tmp, khz);
|
|
|
|
return (u32)tmp;
|
|
}
|
|
|
|
/**
|
|
* clocksource_hz2mult - calculates mult from hz and shift
|
|
* @hz: Clocksource frequency in Hz
|
|
* @shift_constant: Clocksource shift factor
|
|
*
|
|
* Helper functions that converts a hz counter
|
|
* frequency to a timsource multiplier, given the
|
|
* clocksource shift value
|
|
*/
|
|
static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
|
|
{
|
|
/* hz = cyc/(Billion ns)
|
|
* mult/2^shift = ns/cyc
|
|
* mult = ns/cyc * 2^shift
|
|
* mult = 1Billion/hz * 2^shift
|
|
* mult = 1000000000 * 2^shift / hz
|
|
* mult = (1000000000<<shift) / hz
|
|
*/
|
|
u64 tmp = ((u64)1000000000) << shift_constant;
|
|
|
|
tmp += hz/2; /* round for do_div */
|
|
do_div(tmp, hz);
|
|
|
|
return (u32)tmp;
|
|
}
|
|
|
|
/**
|
|
* clocksource_cyc2ns - converts clocksource cycles to nanoseconds
|
|
* @cycles: cycles
|
|
* @mult: cycle to nanosecond multiplier
|
|
* @shift: cycle to nanosecond divisor (power of two)
|
|
*
|
|
* Converts cycles to nanoseconds, using the given mult and shift.
|
|
*
|
|
* XXX - This could use some mult_lxl_ll() asm optimization
|
|
*/
|
|
static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
|
|
{
|
|
return ((u64) cycles * mult) >> shift;
|
|
}
|
|
|
|
|
|
extern int clocksource_register(struct clocksource*);
|
|
extern int clocksource_unregister(struct clocksource*);
|
|
extern void clocksource_touch_watchdog(void);
|
|
extern struct clocksource* clocksource_get_next(void);
|
|
extern void clocksource_change_rating(struct clocksource *cs, int rating);
|
|
extern void clocksource_suspend(void);
|
|
extern void clocksource_resume(void);
|
|
extern struct clocksource * __init __weak clocksource_default_clock(void);
|
|
extern void clocksource_mark_unstable(struct clocksource *cs);
|
|
|
|
extern void
|
|
clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec);
|
|
|
|
/*
|
|
* Don't call __clocksource_register_scale directly, use
|
|
* clocksource_register_hz/khz
|
|
*/
|
|
extern int
|
|
__clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq);
|
|
extern void
|
|
__clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq);
|
|
|
|
static inline int clocksource_register_hz(struct clocksource *cs, u32 hz)
|
|
{
|
|
return __clocksource_register_scale(cs, 1, hz);
|
|
}
|
|
|
|
static inline int clocksource_register_khz(struct clocksource *cs, u32 khz)
|
|
{
|
|
return __clocksource_register_scale(cs, 1000, khz);
|
|
}
|
|
|
|
static inline void __clocksource_updatefreq_hz(struct clocksource *cs, u32 hz)
|
|
{
|
|
__clocksource_updatefreq_scale(cs, 1, hz);
|
|
}
|
|
|
|
static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz)
|
|
{
|
|
__clocksource_updatefreq_scale(cs, 1000, khz);
|
|
}
|
|
|
|
|
|
extern int timekeeping_notify(struct clocksource *clock);
|
|
|
|
extern cycle_t clocksource_mmio_readl_up(struct clocksource *);
|
|
extern cycle_t clocksource_mmio_readl_down(struct clocksource *);
|
|
extern cycle_t clocksource_mmio_readw_up(struct clocksource *);
|
|
extern cycle_t clocksource_mmio_readw_down(struct clocksource *);
|
|
|
|
extern int clocksource_mmio_init(void __iomem *, const char *,
|
|
unsigned long, int, unsigned, cycle_t (*)(struct clocksource *));
|
|
|
|
extern int clocksource_i8253_init(void);
|
|
|
|
struct device_node;
|
|
typedef void(*clocksource_of_init_fn)(struct device_node *);
|
|
#ifdef CONFIG_CLKSRC_OF
|
|
extern void clocksource_of_init(void);
|
|
|
|
#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \
|
|
static const struct of_device_id __clksrc_of_table_##name \
|
|
__used __section(__clksrc_of_table) \
|
|
= { .compatible = compat, \
|
|
.data = (fn == (clocksource_of_init_fn)NULL) ? fn : fn }
|
|
#else
|
|
static inline void clocksource_of_init(void) {}
|
|
#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \
|
|
static const struct of_device_id __clksrc_of_table_##name \
|
|
__attribute__((unused)) \
|
|
= { .compatible = compat, \
|
|
.data = (fn == (clocksource_of_init_fn)NULL) ? fn : fn }
|
|
#endif
|
|
|
|
#endif /* _LINUX_CLOCKSOURCE_H */
|