linux/kernel/time/clocksource.c

1245 lines
34 KiB
C
Raw Normal View History

time: Add SPDX license identifiers Update the time(r) core files files with the correct SPDX license identifier based on the license text in the file itself. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This work is based on a script and data from Philippe Ombredanne, Kate Stewart and myself. The data has been created with two independent license scanners and manual inspection. The following files do not contain any direct license information and have been omitted from the big initial SPDX changes: timeconst.bc: The .bc files were not touched time.c, timer.c, timekeeping.c: Licence was deduced from EXPORT_SYMBOL_GPL As those files do not contain direct license references they fall under the project license, i.e. GPL V2 only. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: John Stultz <john.stultz@linaro.org> Acked-by: Corey Minyard <cminyard@mvista.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Russell King <rmk+kernel@armlinux.org.uk> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Nicolas Pitre <nicolas.pitre@linaro.org> Cc: David Riley <davidriley@chromium.org> Cc: Colin Cross <ccross@android.com> Cc: Mark Brown <broonie@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Link: https://lkml.kernel.org/r/20181031182252.879109557@linutronix.de
2018-11-01 02:21:09 +08:00
// SPDX-License-Identifier: GPL-2.0+
/*
* This file contains the functions which manage clocksource drivers.
*
* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/device.h>
#include <linux/clocksource.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
#include <linux/tick.h>
#include <linux/kthread.h>
#include "tick-internal.h"
#include "timekeeping_internal.h"
/**
* clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
* @mult: pointer to mult variable
* @shift: pointer to shift variable
* @from: frequency to convert from
* @to: frequency to convert to
* @maxsec: guaranteed runtime conversion range in seconds
*
* The function evaluates the shift/mult pair for the scaled math
* operations of clocksources and clockevents.
*
* @to and @from are frequency values in HZ. For clock sources @to is
* NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
* event @to is the counter frequency and @from is NSEC_PER_SEC.
*
* The @maxsec conversion range argument controls the time frame in
* seconds which must be covered by the runtime conversion with the
* calculated mult and shift factors. This guarantees that no 64bit
* overflow happens when the input value of the conversion is
* multiplied with the calculated mult factor. Larger ranges may
* reduce the conversion accuracy by chosing smaller mult and shift
* factors.
*/
void
clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
{
u64 tmp;
u32 sft, sftacc= 32;
/*
* Calculate the shift factor which is limiting the conversion
* range:
*/
tmp = ((u64)maxsec * from) >> 32;
while (tmp) {
tmp >>=1;
sftacc--;
}
/*
* Find the conversion shift/mult pair which has the best
* accuracy and fits the maxsec conversion range:
*/
for (sft = 32; sft > 0; sft--) {
tmp = (u64) to << sft;
tmp += from / 2;
do_div(tmp, from);
if ((tmp >> sftacc) == 0)
break;
}
*mult = tmp;
*shift = sft;
}
EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
/*[Clocksource internal variables]---------
* curr_clocksource:
* currently selected clocksource.
* suspend_clocksource:
* used to calculate the suspend time.
* clocksource_list:
* linked list with the registered clocksources
* clocksource_mutex:
* protects manipulations to curr_clocksource and the clocksource_list
* override_name:
* Name of the user-specified clocksource.
*/
static struct clocksource *curr_clocksource;
static struct clocksource *suspend_clocksource;
static LIST_HEAD(clocksource_list);
static DEFINE_MUTEX(clocksource_mutex);
static char override_name[CS_NAME_LEN];
static int finished_booting;
static u64 suspend_start;
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
static void clocksource_watchdog_work(struct work_struct *work);
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
static void clocksource_select(void);
static LIST_HEAD(watchdog_list);
static struct clocksource *watchdog;
static struct timer_list watchdog_timer;
static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
static DEFINE_SPINLOCK(watchdog_lock);
static int watchdog_running;
static atomic_t watchdog_reset_pending;
static inline void clocksource_watchdog_lock(unsigned long *flags)
2018-04-23 23:28:55 +08:00
{
spin_lock_irqsave(&watchdog_lock, *flags);
}
static inline void clocksource_watchdog_unlock(unsigned long *flags)
2018-04-23 23:28:55 +08:00
{
spin_unlock_irqrestore(&watchdog_lock, *flags);
}
static int clocksource_watchdog_kthread(void *data);
static void __clocksource_change_rating(struct clocksource *cs, int rating);
/*
* Interval: 0.5sec Threshold: 0.0625s
*/
#define WATCHDOG_INTERVAL (HZ >> 1)
#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)
static void clocksource_watchdog_work(struct work_struct *work)
{
/*
* We cannot directly run clocksource_watchdog_kthread() here, because
* clocksource_select() calls timekeeping_notify() which uses
* stop_machine(). One cannot use stop_machine() from a workqueue() due
* lock inversions wrt CPU hotplug.
*
* Also, we only ever run this work once or twice during the lifetime
* of the kernel, so there is no point in creating a more permanent
* kthread for this.
*
* If kthread_run fails the next watchdog scan over the
* watchdog_list will find the unstable clock again.
*/
kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
}
static void __clocksource_unstable(struct clocksource *cs)
{
cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
cs->flags |= CLOCK_SOURCE_UNSTABLE;
/*
* If the clocksource is registered clocksource_watchdog_kthread() will
* re-rate and re-select.
*/
if (list_empty(&cs->list)) {
cs->rating = 0;
2018-04-23 23:28:55 +08:00
return;
}
2018-04-23 23:28:55 +08:00
if (cs->mark_unstable)
cs->mark_unstable(cs);
/* kick clocksource_watchdog_kthread() */
if (finished_booting)
schedule_work(&watchdog_work);
}
/**
* clocksource_mark_unstable - mark clocksource unstable via watchdog
* @cs: clocksource to be marked unstable
*
* This function is called by the x86 TSC code to mark clocksources as unstable;
* it defers demotion and re-selection to a kthread.
*/
void clocksource_mark_unstable(struct clocksource *cs)
{
unsigned long flags;
spin_lock_irqsave(&watchdog_lock, flags);
if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
2018-04-23 23:28:55 +08:00
if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
list_add(&cs->wd_list, &watchdog_list);
__clocksource_unstable(cs);
}
spin_unlock_irqrestore(&watchdog_lock, flags);
}
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-17 05:43:17 +08:00
static void clocksource_watchdog(struct timer_list *unused)
{
struct clocksource *cs;
u64 csnow, wdnow, cslast, wdlast, delta;
int64_t wd_nsec, cs_nsec;
int next_cpu, reset_pending;
spin_lock(&watchdog_lock);
if (!watchdog_running)
goto out;
reset_pending = atomic_read(&watchdog_reset_pending);
list_for_each_entry(cs, &watchdog_list, wd_list) {
/* Clocksource already marked unstable? */
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
if (finished_booting)
schedule_work(&watchdog_work);
continue;
}
local_irq_disable();
csnow = cs->read(cs);
wdnow = watchdog->read(watchdog);
local_irq_enable();
/* Clocksource initialized ? */
if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
atomic_read(&watchdog_reset_pending)) {
cs->flags |= CLOCK_SOURCE_WATCHDOG;
cs->wd_last = wdnow;
cs->cs_last = csnow;
continue;
}
delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask);
wd_nsec = clocksource_cyc2ns(delta, watchdog->mult,
watchdog->shift);
delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
wdlast = cs->wd_last; /* save these in case we print them */
cslast = cs->cs_last;
cs->cs_last = csnow;
cs->wd_last = wdnow;
if (atomic_read(&watchdog_reset_pending))
continue;
/* Check the deviation from the watchdog clocksource. */
if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
smp_processor_id(), cs->name);
pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
watchdog->name, wdnow, wdlast, watchdog->mask);
pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
cs->name, csnow, cslast, cs->mask);
__clocksource_unstable(cs);
continue;
}
if (cs == curr_clocksource && cs->tick_stable)
cs->tick_stable(cs);
if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
(cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
(watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
/* Mark it valid for high-res. */
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
/*
* clocksource_done_booting() will sort it if
* finished_booting is not set yet.
*/
if (!finished_booting)
continue;
/*
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
* If this is not the current clocksource let
* the watchdog thread reselect it. Due to the
* change to high res this clocksource might
* be preferred now. If it is the current
* clocksource let the tick code know about
* that change.
*/
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
if (cs != curr_clocksource) {
cs->flags |= CLOCK_SOURCE_RESELECT;
schedule_work(&watchdog_work);
} else {
tick_clock_notify();
}
}
}
/*
* We only clear the watchdog_reset_pending, when we did a
* full cycle through all clocksources.
*/
if (reset_pending)
atomic_dec(&watchdog_reset_pending);
/*
* Cycle through CPUs to check if the CPUs stay synchronized
* to each other.
*/
next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(cpu_online_mask);
clocksource: Prevent double add_timer_on() for watchdog_timer Kernel crashes inside QEMU/KVM are observed: kernel BUG at kernel/time/timer.c:1154! BUG_ON(timer_pending(timer) || !timer->function) in add_timer_on(). At the same time another cpu got: general protection fault: 0000 [#1] SMP PTI of poinson pointer 0xdead000000000200 in: __hlist_del at include/linux/list.h:681 (inlined by) detach_timer at kernel/time/timer.c:818 (inlined by) expire_timers at kernel/time/timer.c:1355 (inlined by) __run_timers at kernel/time/timer.c:1686 (inlined by) run_timer_softirq at kernel/time/timer.c:1699 Unfortunately kernel logs are badly scrambled, stacktraces are lost. Printing the timer->function before the BUG_ON() pointed to clocksource_watchdog(). The execution of clocksource_watchdog() can race with a sequence of clocksource_stop_watchdog() .. clocksource_start_watchdog(): expire_timers() detach_timer(timer, true); timer->entry.pprev = NULL; raw_spin_unlock_irq(&base->lock); call_timer_fn clocksource_watchdog() clocksource_watchdog_kthread() or clocksource_unbind() spin_lock_irqsave(&watchdog_lock, flags); clocksource_stop_watchdog(); del_timer(&watchdog_timer); watchdog_running = 0; spin_unlock_irqrestore(&watchdog_lock, flags); spin_lock_irqsave(&watchdog_lock, flags); clocksource_start_watchdog(); add_timer_on(&watchdog_timer, ...); watchdog_running = 1; spin_unlock_irqrestore(&watchdog_lock, flags); spin_lock(&watchdog_lock); add_timer_on(&watchdog_timer, ...); BUG_ON(timer_pending(timer) || !timer->function); timer_pending() -> true BUG() I.e. inside clocksource_watchdog() watchdog_timer could be already armed. Check timer_pending() before calling add_timer_on(). This is sufficient as all operations are synchronized by watchdog_lock. Fixes: 75c5158f70c0 ("timekeeping: Update clocksource with stop_machine") Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/158048693917.4378.13823603769948933793.stgit@buzz
2020-02-01 00:08:59 +08:00
/*
* Arm timer if not already pending: could race with concurrent
* pair clocksource_stop_watchdog() clocksource_start_watchdog().
*/
if (!timer_pending(&watchdog_timer)) {
watchdog_timer.expires += WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, next_cpu);
}
out:
spin_unlock(&watchdog_lock);
}
static inline void clocksource_start_watchdog(void)
{
if (watchdog_running || !watchdog || list_empty(&watchdog_list))
return;
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-17 05:43:17 +08:00
timer_setup(&watchdog_timer, clocksource_watchdog, 0);
watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
watchdog_running = 1;
}
static inline void clocksource_stop_watchdog(void)
{
if (!watchdog_running || (watchdog && !list_empty(&watchdog_list)))
return;
del_timer(&watchdog_timer);
watchdog_running = 0;
}
static inline void clocksource_reset_watchdog(void)
{
struct clocksource *cs;
list_for_each_entry(cs, &watchdog_list, wd_list)
cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
}
static void clocksource_resume_watchdog(void)
{
atomic_inc(&watchdog_reset_pending);
}
static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
INIT_LIST_HEAD(&cs->wd_list);
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a clocksource to be watched. */
list_add(&cs->wd_list, &watchdog_list);
cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
} else {
/* cs is a watchdog. */
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}
}
static void clocksource_select_watchdog(bool fallback)
{
struct clocksource *cs, *old_wd;
unsigned long flags;
spin_lock_irqsave(&watchdog_lock, flags);
/* save current watchdog */
old_wd = watchdog;
if (fallback)
watchdog = NULL;
list_for_each_entry(cs, &clocksource_list, list) {
/* cs is a clocksource to be watched. */
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
continue;
/* Skip current if we were requested for a fallback. */
if (fallback && cs == old_wd)
continue;
/* Pick the best watchdog. */
if (!watchdog || cs->rating > watchdog->rating)
watchdog = cs;
}
/* If we failed to find a fallback restore the old one. */
if (!watchdog)
watchdog = old_wd;
/* If we changed the watchdog we need to reset cycles. */
if (watchdog != old_wd)
clocksource_reset_watchdog();
/* Check if the watchdog timer needs to be started. */
clocksource_start_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
}
static void clocksource_dequeue_watchdog(struct clocksource *cs)
{
if (cs != watchdog) {
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a watched clocksource. */
list_del_init(&cs->wd_list);
/* Check if the watchdog timer needs to be stopped. */
clocksource_stop_watchdog();
}
}
}
static int __clocksource_watchdog_kthread(void)
{
struct clocksource *cs, *tmp;
unsigned long flags;
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
int select = 0;
spin_lock_irqsave(&watchdog_lock, flags);
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
list_del_init(&cs->wd_list);
2018-04-23 23:28:55 +08:00
__clocksource_change_rating(cs, 0);
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
select = 1;
}
if (cs->flags & CLOCK_SOURCE_RESELECT) {
cs->flags &= ~CLOCK_SOURCE_RESELECT;
select = 1;
}
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
}
/* Check if the watchdog timer needs to be stopped. */
clocksource_stop_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
return select;
}
static int clocksource_watchdog_kthread(void *data)
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
{
mutex_lock(&clocksource_mutex);
if (__clocksource_watchdog_kthread())
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
}
static bool clocksource_is_watchdog(struct clocksource *cs)
{
return cs == watchdog;
}
#else /* CONFIG_CLOCKSOURCE_WATCHDOG */
static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}
static void clocksource_select_watchdog(bool fallback) { }
static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
static inline void clocksource_resume_watchdog(void) { }
static inline int __clocksource_watchdog_kthread(void) { return 0; }
static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
void clocksource_mark_unstable(struct clocksource *cs) { }
static inline void clocksource_watchdog_lock(unsigned long *flags) { }
static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
2018-04-23 23:28:55 +08:00
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
static bool clocksource_is_suspend(struct clocksource *cs)
{
return cs == suspend_clocksource;
}
static void __clocksource_suspend_select(struct clocksource *cs)
{
/*
* Skip the clocksource which will be stopped in suspend state.
*/
if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP))
return;
/*
* The nonstop clocksource can be selected as the suspend clocksource to
* calculate the suspend time, so it should not supply suspend/resume
* interfaces to suspend the nonstop clocksource when system suspends.
*/
if (cs->suspend || cs->resume) {
pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n",
cs->name);
}
/* Pick the best rating. */
if (!suspend_clocksource || cs->rating > suspend_clocksource->rating)
suspend_clocksource = cs;
}
/**
* clocksource_suspend_select - Select the best clocksource for suspend timing
* @fallback: if select a fallback clocksource
*/
static void clocksource_suspend_select(bool fallback)
{
struct clocksource *cs, *old_suspend;
old_suspend = suspend_clocksource;
if (fallback)
suspend_clocksource = NULL;
list_for_each_entry(cs, &clocksource_list, list) {
/* Skip current if we were requested for a fallback. */
if (fallback && cs == old_suspend)
continue;
__clocksource_suspend_select(cs);
}
}
/**
* clocksource_start_suspend_timing - Start measuring the suspend timing
* @cs: current clocksource from timekeeping
* @start_cycles: current cycles from timekeeping
*
* This function will save the start cycle values of suspend timer to calculate
* the suspend time when resuming system.
*
* This function is called late in the suspend process from timekeeping_suspend(),
* that means processes are freezed, non-boot cpus and interrupts are disabled
* now. It is therefore possible to start the suspend timer without taking the
* clocksource mutex.
*/
void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
{
if (!suspend_clocksource)
return;
/*
* If current clocksource is the suspend timer, we should use the
* tkr_mono.cycle_last value as suspend_start to avoid same reading
* from suspend timer.
*/
if (clocksource_is_suspend(cs)) {
suspend_start = start_cycles;
return;
}
if (suspend_clocksource->enable &&
suspend_clocksource->enable(suspend_clocksource)) {
pr_warn_once("Failed to enable the non-suspend-able clocksource.\n");
return;
}
suspend_start = suspend_clocksource->read(suspend_clocksource);
}
/**
* clocksource_stop_suspend_timing - Stop measuring the suspend timing
* @cs: current clocksource from timekeeping
* @cycle_now: current cycles from timekeeping
*
* This function will calculate the suspend time from suspend timer.
*
* Returns nanoseconds since suspend started, 0 if no usable suspend clocksource.
*
* This function is called early in the resume process from timekeeping_resume(),
* that means there is only one cpu, no processes are running and the interrupts
* are disabled. It is therefore possible to stop the suspend timer without
* taking the clocksource mutex.
*/
u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
{
u64 now, delta, nsec = 0;
if (!suspend_clocksource)
return 0;
/*
* If current clocksource is the suspend timer, we should use the
* tkr_mono.cycle_last value from timekeeping as current cycle to
* avoid same reading from suspend timer.
*/
if (clocksource_is_suspend(cs))
now = cycle_now;
else
now = suspend_clocksource->read(suspend_clocksource);
if (now > suspend_start) {
delta = clocksource_delta(now, suspend_start,
suspend_clocksource->mask);
nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
suspend_clocksource->shift);
}
/*
* Disable the suspend timer to save power if current clocksource is
* not the suspend timer.
*/
if (!clocksource_is_suspend(cs) && suspend_clocksource->disable)
suspend_clocksource->disable(suspend_clocksource);
return nsec;
}
/**
* clocksource_suspend - suspend the clocksource(s)
*/
void clocksource_suspend(void)
{
struct clocksource *cs;
list_for_each_entry_reverse(cs, &clocksource_list, list)
if (cs->suspend)
cs->suspend(cs);
}
/**
* clocksource_resume - resume the clocksource(s)
*/
void clocksource_resume(void)
{
struct clocksource *cs;
list_for_each_entry(cs, &clocksource_list, list)
if (cs->resume)
cs->resume(cs);
clocksource_resume_watchdog();
}
/**
* clocksource_touch_watchdog - Update watchdog
*
* Update the watchdog after exception contexts such as kgdb so as not
clocksource: Prevent potential kgdb dead lock commit 0f8e8ef7 (clocksource: Simplify clocksource watchdog resume logic) introduced a potential kgdb dead lock. When the kernel is stopped by kgdb inside code which holds watchdog_lock then kgdb dead locks in clocksource_resume_watchdog(). clocksource_resume_watchdog() is called from kbdg via clocksource_touch_watchdog() to avoid that the clock source watchdog marks TSC unstable after the kernel has been stopped. Solve this by replacing spin_lock with a spin_trylock and just return in case the lock is held. Not resetting the watchdog might result in TSC becoming marked unstable, but that's an acceptable penalty for using kgdb. The timekeeping is anyway easily screwed up by kgdb when the system uses either jiffies or a clock source which wraps in short intervals (e.g. pm_timer wraps about every 4.6s), so we really do not have to worry about that occasional TSC marked unstable side effect. The second caller of clocksource_resume_watchdog() is clocksource_resume(). The trylock is safe here as well because the system is UP at this point, interrupts are disabled and nothing else can hold watchdog_lock(). Reported-by: Jason Wessel <jason.wessel@windriver.com> LKML-Reference: <1264480000-6997-4-git-send-email-jason.wessel@windriver.com> Cc: kgdb-bugreport@lists.sourceforge.net Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: John Stultz <johnstul@us.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2010-01-26 19:51:10 +08:00
* to incorrectly trip the watchdog. This might fail when the kernel
* was stopped in code which holds watchdog_lock.
*/
void clocksource_touch_watchdog(void)
{
clocksource_resume_watchdog();
}
/**
* clocksource_max_adjustment- Returns max adjustment amount
* @cs: Pointer to clocksource
*
*/
static u32 clocksource_max_adjustment(struct clocksource *cs)
{
u64 ret;
/*
* We won't try to correct for more than 11% adjustments (110,000 ppm),
*/
ret = (u64)cs->mult * 11;
do_div(ret,100);
return (u32)ret;
}
/**
* clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted
* @mult: cycle to nanosecond multiplier
* @shift: cycle to nanosecond divisor (power of two)
* @maxadj: maximum adjustment value to mult (~11%)
* @mask: bitmask for two's complement subtraction of non 64 bit counters
* @max_cyc: maximum cycle value before potential overflow (does not include
* any safety margin)
*
* NOTE: This function includes a safety margin of 50%, in other words, we
* return half the number of nanoseconds the hardware counter can technically
* cover. This is done so that we can potentially detect problems caused by
* delayed timers or bad hardware, which might result in time intervals that
* are larger than what the math used can handle without overflows.
*/
u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc)
{
u64 max_nsecs, max_cycles;
/*
* Calculate the maximum number of cycles that we can pass to the
* cyc2ns() function without overflowing a 64-bit result.
*/
max_cycles = ULLONG_MAX;
do_div(max_cycles, mult+maxadj);
/*
* The actual maximum number of cycles we can defer the clocksource is
* determined by the minimum of max_cycles and mask.
* Note: Here we subtract the maxadj to make sure we don't sleep for
* too long if there's a large negative adjustment.
*/
max_cycles = min(max_cycles, mask);
max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
/* return the max_cycles value as well if requested */
if (max_cyc)
*max_cyc = max_cycles;
/* Return 50% of the actual maximum, so we can detect bad values */
max_nsecs >>= 1;
return max_nsecs;
}
/**
* clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles
* @cs: Pointer to clocksource to be updated
*
*/
static inline void clocksource_update_max_deferment(struct clocksource *cs)
{
cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
cs->maxadj, cs->mask,
&cs->max_cycles);
}
#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
{
struct clocksource *cs;
if (!finished_booting || list_empty(&clocksource_list))
return NULL;
/*
* We pick the clocksource with the highest rating. If oneshot
* mode is active, we pick the highres valid clocksource with
* the best rating.
*/
list_for_each_entry(cs, &clocksource_list, list) {
if (skipcur && cs == curr_clocksource)
continue;
if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES))
continue;
return cs;
}
return NULL;
}
static void __clocksource_select(bool skipcur)
{
bool oneshot = tick_oneshot_mode_active();
struct clocksource *best, *cs;
/* Find the best suitable clocksource */
best = clocksource_find_best(oneshot, skipcur);
if (!best)
return;
if (!strlen(override_name))
goto found;
/* Check for the override clocksource. */
list_for_each_entry(cs, &clocksource_list, list) {
if (skipcur && cs == curr_clocksource)
continue;
if (strcmp(cs->name, override_name) != 0)
continue;
/*
* Check to make sure we don't switch to a non-highres
* capable clocksource if the tick code is in oneshot
* mode (highres or nohz)
*/
if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
/* Override clocksource cannot be used. */
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
pr_warn("Override clocksource %s is unstable and not HRT compatible - cannot switch while in HRT/NOHZ mode\n",
cs->name);
override_name[0] = 0;
} else {
/*
* The override cannot be currently verified.
* Deferring to let the watchdog check.
*/
pr_info("Override clocksource %s is not currently HRT compatible - deferring\n",
cs->name);
}
} else
/* Override clocksource can be used. */
best = cs;
break;
}
found:
if (curr_clocksource != best && !timekeeping_notify(best)) {
pr_info("Switched to clocksource %s\n", best->name);
curr_clocksource = best;
}
}
/**
* clocksource_select - Select the best clocksource available
*
* Private function. Must hold clocksource_mutex when called.
*
* Select the clocksource with the best rating, or the clocksource,
* which is selected by userspace override.
*/
static void clocksource_select(void)
{
__clocksource_select(false);
}
static void clocksource_select_fallback(void)
{
__clocksource_select(true);
}
#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
static inline void clocksource_select(void) { }
static inline void clocksource_select_fallback(void) { }
#endif
/*
* clocksource_done_booting - Called near the end of core bootup
*
* Hack to avoid lots of clocksource churn at boot time.
* We use fs_initcall because we want this to start before
* device_initcall but after subsys_initcall.
*/
static int __init clocksource_done_booting(void)
{
mutex_lock(&clocksource_mutex);
curr_clocksource = clocksource_default_clock();
finished_booting = 1;
/*
* Run the watchdog first to eliminate unstable clock sources
*/
__clocksource_watchdog_kthread();
clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
}
fs_initcall(clocksource_done_booting);
/*
* Enqueue the clocksource sorted by rating
*/
static void clocksource_enqueue(struct clocksource *cs)
{
struct list_head *entry = &clocksource_list;
struct clocksource *tmp;
list_for_each_entry(tmp, &clocksource_list, list) {
/* Keep track of the place, where to insert */
if (tmp->rating < cs->rating)
break;
entry = &tmp->list;
}
list_add(&cs->list, entry);
}
/**
* __clocksource_update_freq_scale - Used update clocksource with new freq
* @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
* This should only be called from the clocksource->enable() method.
*
* This *SHOULD NOT* be called directly! Please use the
* __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper
* functions.
*/
void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
{
u64 sec;
/*
* Default clocksources are *special* and self-define their mult/shift.
* But, you're not special, so you should specify a freq value.
*/
if (freq) {
/*
* Calc the maximum number of seconds which we can run before
* wrapping around. For clocksources which have a mask > 32-bit
* we need to limit the max sleep time to have a good
* conversion precision. 10 minutes is still a reasonable
* amount. That results in a shift value of 24 for a
* clocksource with mask >= 40-bit and f >= 4GHz. That maps to
* ~ 0.06ppm granularity for NTP.
*/
sec = cs->mask;
do_div(sec, freq);
do_div(sec, scale);
if (!sec)
sec = 1;
else if (sec > 600 && cs->mask > UINT_MAX)
sec = 600;
clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
NSEC_PER_SEC / scale, sec * scale);
}
/*
* Ensure clocksources that have large 'mult' values don't overflow
* when adjusted.
*/
cs->maxadj = clocksource_max_adjustment(cs);
while (freq && ((cs->mult + cs->maxadj < cs->mult)
|| (cs->mult - cs->maxadj > cs->mult))) {
cs->mult >>= 1;
cs->shift--;
cs->maxadj = clocksource_max_adjustment(cs);
}
/*
* Only warn for *special* clocksources that self-define
* their mult/shift values and don't specify a freq.
*/
WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
"timekeeping: Clocksource %s might overflow on 11%% adjustment\n",
cs->name);
clocksource_update_max_deferment(cs);
pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
}
EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
/**
* __clocksource_register_scale - Used to install new clocksources
* @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
* Returns -EBUSY if registration fails, zero otherwise.
*
* This *SHOULD NOT* be called directly! Please use the
* clocksource_register_hz() or clocksource_register_khz helper functions.
*/
int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
{
2018-04-23 23:28:55 +08:00
unsigned long flags;
clocksource_arch_init(cs);
if (cs->vdso_clock_mode < 0 ||
cs->vdso_clock_mode >= VDSO_CLOCKMODE_MAX) {
pr_warn("clocksource %s registered with invalid VDSO mode %d. Disabling VDSO support.\n",
cs->name, cs->vdso_clock_mode);
cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
}
/* Initialize mult/shift and max_idle_ns */
__clocksource_update_freq_scale(cs, scale, freq);
/* Add clocksource to the clocksource list */
mutex_lock(&clocksource_mutex);
2018-04-23 23:28:55 +08:00
clocksource_watchdog_lock(&flags);
clocksource_enqueue(cs);
clocksource_enqueue_watchdog(cs);
2018-04-23 23:28:55 +08:00
clocksource_watchdog_unlock(&flags);
clocksource_select();
clocksource_select_watchdog(false);
__clocksource_suspend_select(cs);
mutex_unlock(&clocksource_mutex);
return 0;
}
EXPORT_SYMBOL_GPL(__clocksource_register_scale);
static void __clocksource_change_rating(struct clocksource *cs, int rating)
{
list_del(&cs->list);
cs->rating = rating;
clocksource_enqueue(cs);
}
/**
* clocksource_change_rating - Change the rating of a registered clocksource
* @cs: clocksource to be changed
* @rating: new rating
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
2018-04-23 23:28:55 +08:00
unsigned long flags;
mutex_lock(&clocksource_mutex);
2018-04-23 23:28:55 +08:00
clocksource_watchdog_lock(&flags);
__clocksource_change_rating(cs, rating);
2018-04-23 23:28:55 +08:00
clocksource_watchdog_unlock(&flags);
clocksource: Reselect clocksource when watchdog validated high-res capability 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>
2013-07-05 04:46:45 +08:00
clocksource_select();
clocksource_select_watchdog(false);
clocksource_suspend_select(false);
mutex_unlock(&clocksource_mutex);
}
EXPORT_SYMBOL(clocksource_change_rating);
/*
* Unbind clocksource @cs. Called with clocksource_mutex held
*/
static int clocksource_unbind(struct clocksource *cs)
{
2018-04-23 23:28:55 +08:00
unsigned long flags;
if (clocksource_is_watchdog(cs)) {
/* Select and try to install a replacement watchdog. */
clocksource_select_watchdog(true);
if (clocksource_is_watchdog(cs))
return -EBUSY;
}
if (cs == curr_clocksource) {
/* Select and try to install a replacement clock source */
clocksource_select_fallback();
if (curr_clocksource == cs)
return -EBUSY;
}
2018-04-23 23:28:55 +08:00
if (clocksource_is_suspend(cs)) {
/*
* Select and try to install a replacement suspend clocksource.
* If no replacement suspend clocksource, we will just let the
* clocksource go and have no suspend clocksource.
*/
clocksource_suspend_select(true);
}
2018-04-23 23:28:55 +08:00
clocksource_watchdog_lock(&flags);
clocksource_dequeue_watchdog(cs);
list_del_init(&cs->list);
2018-04-23 23:28:55 +08:00
clocksource_watchdog_unlock(&flags);
return 0;
}
/**
* clocksource_unregister - remove a registered clocksource
* @cs: clocksource to be unregistered
*/
int clocksource_unregister(struct clocksource *cs)
{
int ret = 0;
mutex_lock(&clocksource_mutex);
if (!list_empty(&cs->list))
ret = clocksource_unbind(cs);
mutex_unlock(&clocksource_mutex);
return ret;
}
EXPORT_SYMBOL(clocksource_unregister);
#ifdef CONFIG_SYSFS
/**
* current_clocksource_show - sysfs interface for current clocksource
* @dev: unused
* @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing current clocksource.
*/
static ssize_t current_clocksource_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
ssize_t count = 0;
mutex_lock(&clocksource_mutex);
count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name);
mutex_unlock(&clocksource_mutex);
return count;
}
ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
{
size_t ret = cnt;
/* strings from sysfs write are not 0 terminated! */
if (!cnt || cnt >= CS_NAME_LEN)
return -EINVAL;
/* strip of \n: */
if (buf[cnt-1] == '\n')
cnt--;
if (cnt > 0)
memcpy(dst, buf, cnt);
dst[cnt] = 0;
return ret;
}
/**
* current_clocksource_store - interface for manually overriding clocksource
* @dev: unused
* @attr: unused
* @buf: name of override clocksource
* @count: length of buffer
*
* Takes input from sysfs interface for manually overriding the default
* clocksource selection.
*/
static ssize_t current_clocksource_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
ssize_t ret;
mutex_lock(&clocksource_mutex);
ret = sysfs_get_uname(buf, override_name, count);
if (ret >= 0)
clocksource_select();
mutex_unlock(&clocksource_mutex);
return ret;
}
static DEVICE_ATTR_RW(current_clocksource);
/**
* unbind_clocksource_store - interface for manually unbinding clocksource
* @dev: unused
* @attr: unused
* @buf: unused
* @count: length of buffer
*
* Takes input from sysfs interface for manually unbinding a clocksource.
*/
static ssize_t unbind_clocksource_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct clocksource *cs;
char name[CS_NAME_LEN];
ssize_t ret;
ret = sysfs_get_uname(buf, name, count);
if (ret < 0)
return ret;
ret = -ENODEV;
mutex_lock(&clocksource_mutex);
list_for_each_entry(cs, &clocksource_list, list) {
if (strcmp(cs->name, name))
continue;
ret = clocksource_unbind(cs);
break;
}
mutex_unlock(&clocksource_mutex);
return ret ? ret : count;
}
static DEVICE_ATTR_WO(unbind_clocksource);
/**
* available_clocksource_show - sysfs interface for listing clocksource
* @dev: unused
* @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing registered clocksources
*/
static ssize_t available_clocksource_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct clocksource *src;
ssize_t count = 0;
mutex_lock(&clocksource_mutex);
list_for_each_entry(src, &clocksource_list, list) {
/*
* Don't show non-HRES clocksource if the tick code is
* in one shot mode (highres=on or nohz=on)
*/
if (!tick_oneshot_mode_active() ||
(src->flags & CLOCK_SOURCE_VALID_FOR_HRES))
count += snprintf(buf + count,
max((ssize_t)PAGE_SIZE - count, (ssize_t)0),
"%s ", src->name);
}
mutex_unlock(&clocksource_mutex);
count += snprintf(buf + count,
max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n");
return count;
}
static DEVICE_ATTR_RO(available_clocksource);
static struct attribute *clocksource_attrs[] = {
&dev_attr_current_clocksource.attr,
&dev_attr_unbind_clocksource.attr,
&dev_attr_available_clocksource.attr,
NULL
};
ATTRIBUTE_GROUPS(clocksource);
static struct bus_type clocksource_subsys = {
.name = "clocksource",
.dev_name = "clocksource",
};
static struct device device_clocksource = {
.id = 0,
.bus = &clocksource_subsys,
.groups = clocksource_groups,
};
static int __init init_clocksource_sysfs(void)
{
int error = subsys_system_register(&clocksource_subsys, NULL);
if (!error)
error = device_register(&device_clocksource);
return error;
}
device_initcall(init_clocksource_sysfs);
#endif /* CONFIG_SYSFS */
/**
* boot_override_clocksource - boot clock override
* @str: override name
*
* Takes a clocksource= boot argument and uses it
* as the clocksource override name.
*/
static int __init boot_override_clocksource(char* str)
{
mutex_lock(&clocksource_mutex);
if (str)
strlcpy(override_name, str, sizeof(override_name));
mutex_unlock(&clocksource_mutex);
return 1;
}
__setup("clocksource=", boot_override_clocksource);
/**
* boot_override_clock - Compatibility layer for deprecated boot option
* @str: override name
*
* DEPRECATED! Takes a clock= boot argument and uses it
* as the clocksource override name
*/
static int __init boot_override_clock(char* str)
{
if (!strcmp(str, "pmtmr")) {
pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n");
return boot_override_clocksource("acpi_pm");
}
pr_warn("clock= boot option is deprecated - use clocksource=xyz\n");
return boot_override_clocksource(str);
}
__setup("clock=", boot_override_clock);