From d65670a78cdbfae94f20a9e05ec705871d7cdf2b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 31 Oct 2011 17:06:35 -0400 Subject: clocksource: Avoid selecting mult values that might overflow when adjusted For some frequencies, the clocks_calc_mult_shift() function will unfortunately select mult values very close to 0xffffffff. This has the potential to overflow when NTP adjusts the clock, adding to the mult value. This patch adds a clocksource.maxadj value, which provides an approximation of an 11% adjustment(NTP limits adjustments to 500ppm and the tick adjustment is limited to 10%), which could be made to the clocksource.mult value. This is then used to both check that the current mult value won't overflow/underflow, as well as warning us if the timekeeping_adjust() code pushes over that 11% boundary. v2: Fix max_adjustment calculation, and improve WARN_ONCE messages. v3: Don't warn before maxadj has actually been set CC: Yong Zhang CC: David Daney CC: Thomas Gleixner CC: Chen Jie CC: zhangfx CC: stable@kernel.org Reported-by: Chen Jie Reported-by: zhangfx Tested-by: Yong Zhang Signed-off-by: John Stultz --- kernel/time/clocksource.c | 58 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 48 insertions(+), 10 deletions(-) (limited to 'kernel/time/clocksource.c') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index cf52fda2e096..cfc65e1eb9fb 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -491,6 +491,22 @@ 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 then 11% adjustments (110,000 ppm), + */ + ret = (u64)cs->mult * 11; + do_div(ret,100); + return (u32)ret; +} + /** * clocksource_max_deferment - Returns max time the clocksource can be deferred * @cs: Pointer to clocksource @@ -503,25 +519,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs) /* * Calculate the maximum number of cycles that we can pass to the * cyc2ns function without overflowing a 64-bit signed result. The - * maximum number of cycles is equal to ULLONG_MAX/cs->mult which - * is equivalent to the below. - * max_cycles < (2^63)/cs->mult - * max_cycles < 2^(log2((2^63)/cs->mult)) - * max_cycles < 2^(log2(2^63) - log2(cs->mult)) - * max_cycles < 2^(63 - log2(cs->mult)) - * max_cycles < 1 << (63 - log2(cs->mult)) + * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj) + * which is equivalent to the below. + * max_cycles < (2^63)/(cs->mult + cs->maxadj) + * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj))) + * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj)) + * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj)) + * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj)) * Please note that we add 1 to the result of the log2 to account for * any rounding errors, ensure the above inequality is satisfied and * no overflow will occur. */ - max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1)); + max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1)); /* * The actual maximum number of cycles we can defer the clocksource is * determined by the minimum of max_cycles and cs->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_t(u64, max_cycles, (u64) cs->mask); - max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift); + max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj, + cs->shift); /* * To ensure that the clocksource does not wrap whilst we are idle, @@ -640,7 +659,6 @@ static void clocksource_enqueue(struct clocksource *cs) void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; - /* * Calc the maximum number of seconds which we can run before * wrapping around. For clocksources which have a mask > 32bit @@ -661,6 +679,20 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, NSEC_PER_SEC / scale, sec * scale); + + /* + * for clocksources that have large mults, to avoid overflow. + * Since mult may be adjusted by ntp, add an safety extra margin + * + */ + cs->maxadj = clocksource_max_adjustment(cs); + while ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult)) { + cs->mult >>= 1; + cs->shift--; + cs->maxadj = clocksource_max_adjustment(cs); + } + cs->max_idle_ns = clocksource_max_deferment(cs); } EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); @@ -701,6 +733,12 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale); */ int clocksource_register(struct clocksource *cs) { + /* calculate max adjustment for given mult/shift */ + cs->maxadj = clocksource_max_adjustment(cs); + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + /* calculate max idle time permitted for this clocksource */ cs->max_idle_ns = clocksource_max_deferment(cs); -- cgit v1.2.3 From b1f919664d04a8d0ba29cb76673c7ca3325a2006 Mon Sep 17 00:00:00 2001 From: "Yang Honggang (Joseph)" Date: Thu, 1 Dec 2011 22:22:41 -0500 Subject: clocksource: Fix bug with max_deferment margin calculation In order to leave a margin of 12.5% we should >> 3 not >> 5. CC: stable@kernel.org Signed-off-by: Yang Honggang (Joseph) [jstultz: Modified commit subject] Signed-off-by: John Stultz --- kernel/time/clocksource.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/time/clocksource.c') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index cfc65e1eb9fb..da2f760e780c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -548,7 +548,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs) * note a margin of 12.5% is used because this can be computed with * a shift, versus say 10% which would require division. */ - return max_nsecs - (max_nsecs >> 5); + return max_nsecs - (max_nsecs >> 3); } #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET @@ -669,7 +669,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) * ~ 0.06ppm granularity for NTP. We apply the same 12.5% * margin as we do in clocksource_max_deferment() */ - sec = (cs->mask - (cs->mask >> 5)); + sec = (cs->mask - (cs->mask >> 3)); do_div(sec, freq); do_div(sec, scale); if (!sec) -- cgit v1.2.3 From d369a5d8fc70710236ae2d06a0e42dce483712df Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Wed, 14 Dec 2011 15:28:51 -0800 Subject: clocksource: convert sysdev_class to a regular subsystem After all sysdev classes are ported to regular driver core entities, the sysdev implementation will be entirely removed from the kernel. Cc: John Stultz Cc: Thomas Gleixner Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- kernel/time/clocksource.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'kernel/time/clocksource.c') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index cf52fda2e096..3f5c8512c033 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -23,8 +23,8 @@ * o Allow clocksource drivers to be unregistered */ +#include #include -#include #include #include #include /* for spin_unlock_irq() using preempt_count() m68k */ @@ -754,8 +754,8 @@ EXPORT_SYMBOL(clocksource_unregister); * Provides sysfs interface for listing current clocksource. */ static ssize_t -sysfs_show_current_clocksources(struct sys_device *dev, - struct sysdev_attribute *attr, char *buf) +sysfs_show_current_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t count = 0; @@ -775,8 +775,8 @@ sysfs_show_current_clocksources(struct sys_device *dev, * Takes input from sysfs interface for manually overriding the default * clocksource selection. */ -static ssize_t sysfs_override_clocksource(struct sys_device *dev, - struct sysdev_attribute *attr, +static ssize_t sysfs_override_clocksource(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { size_t ret = count; @@ -809,8 +809,8 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, * Provides sysfs interface for listing registered clocksources */ static ssize_t -sysfs_show_available_clocksources(struct sys_device *dev, - struct sysdev_attribute *attr, +sysfs_show_available_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) { struct clocksource *src; @@ -839,35 +839,36 @@ sysfs_show_available_clocksources(struct sys_device *dev, /* * Sysfs setup bits: */ -static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, +static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, sysfs_override_clocksource); -static SYSDEV_ATTR(available_clocksource, 0444, +static DEVICE_ATTR(available_clocksource, 0444, sysfs_show_available_clocksources, NULL); -static struct sysdev_class clocksource_sysclass = { +static struct bus_type clocksource_subsys = { .name = "clocksource", + .dev_name = "clocksource", }; -static struct sys_device device_clocksource = { +static struct device device_clocksource = { .id = 0, - .cls = &clocksource_sysclass, + .bus = &clocksource_subsys, }; static int __init init_clocksource_sysfs(void) { - int error = sysdev_class_register(&clocksource_sysclass); + int error = subsys_system_register(&clocksource_subsys, NULL); if (!error) - error = sysdev_register(&device_clocksource); + error = device_register(&device_clocksource); if (!error) - error = sysdev_create_file( + error = device_create_file( &device_clocksource, - &attr_current_clocksource); + &dev_attr_current_clocksource); if (!error) - error = sysdev_create_file( + error = device_create_file( &device_clocksource, - &attr_available_clocksource); + &dev_attr_available_clocksource); return error; } -- cgit v1.2.3 From b1b73d095084e754562961c443aa8f6587a55f8e Mon Sep 17 00:00:00 2001 From: Kusanagi Kouichi Date: Mon, 19 Dec 2011 18:13:19 +0900 Subject: time/clocksource: Fix kernel-doc warnings Fix various KernelDoc build warnings. Signed-off-by: Kusanagi Kouichi Cc: John Stultz Link: http://lkml.kernel.org/r/20111219091320.0D5AF6FC03D@msa105.auone-net.jp Signed-off-by: Ingo Molnar --- include/linux/clocksource.h | 11 ++++++++--- kernel/time/clocksource.c | 12 +++++++++--- 2 files changed, 17 insertions(+), 6 deletions(-) (limited to 'kernel/time/clocksource.c') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index c86c940d1de3..081147da0564 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -71,7 +71,7 @@ struct timecounter { /** * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds - * @tc: Pointer to cycle counter. + * @cc: Pointer to cycle counter. * @cycles: Cycles * * XXX - This could use some mult_lxl_ll() asm optimization. Same code @@ -114,7 +114,7 @@ extern u64 timecounter_read(struct timecounter *tc); * time base as values returned by * timecounter_read() * @tc: Pointer to time counter. - * @cycle: a value returned by tc->cc->read() + * @cycle_tstamp: a value returned by tc->cc->read() * * Cycle counts that are converted correctly as long as they * fall into the interval [-1/2 max cycle count, +1/2 max cycle count], @@ -156,11 +156,12 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) * @max_idle_ns: max idle time permitted by the clocksource (nsecs) - * @maxadj maximum adjustment value to mult (~11%) + * @maxadj: maximum adjustment value to mult (~11%) * @flags: flags describing special properties * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary + * @cycle_last: most recent cycle counter value seen by ::read() */ struct clocksource { /* @@ -187,6 +188,7 @@ struct clocksource { void (*suspend)(struct clocksource *cs); void (*resume)(struct clocksource *cs); + /* private: */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; @@ -261,6 +263,9 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant) /** * clocksource_cyc2ns - converts clocksource cycles to nanoseconds + * @cycles: cycles + * @mult: cycle to nanosecond multiplier + * @shift: cycle to nanosecond divisor (power of two) * * Converts cycles to nanoseconds, using the given mult and shift. * diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index da2f760e780c..d3ad022136e5 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -647,7 +647,7 @@ static void clocksource_enqueue(struct clocksource *cs) /** * __clocksource_updatefreq_scale - Used update clocksource with new freq - * @t: clocksource to be registered + * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale * @@ -699,7 +699,7 @@ EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); /** * __clocksource_register_scale - Used to install new clocksources - * @t: clocksource to be registered + * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale * @@ -727,7 +727,7 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale); /** * clocksource_register - Used to install new clocksources - * @t: clocksource to be registered + * @cs: clocksource to be registered * * Returns -EBUSY if registration fails, zero otherwise. */ @@ -761,6 +761,8 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating) /** * 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) { @@ -772,6 +774,7 @@ EXPORT_SYMBOL(clocksource_change_rating); /** * clocksource_unregister - remove a registered clocksource + * @cs: clocksource to be unregistered */ void clocksource_unregister(struct clocksource *cs) { @@ -787,6 +790,7 @@ EXPORT_SYMBOL(clocksource_unregister); /** * sysfs_show_current_clocksources - 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. @@ -807,6 +811,7 @@ sysfs_show_current_clocksources(struct sys_device *dev, /** * sysfs_override_clocksource - interface for manually overriding clocksource * @dev: unused + * @attr: unused * @buf: name of override clocksource * @count: length of buffer * @@ -842,6 +847,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, /** * sysfs_show_available_clocksources - 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 -- cgit v1.2.3