diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-06 02:46:42 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-06 02:46:42 +0200 |
commit | e7fda6c4c3c1a7d6996dd75fd84670fa0b5d448f (patch) | |
tree | daa51c16462c318b890acf7f01fba5827275dd74 /kernel | |
parent | Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kerne... (diff) | |
parent | timekeeping: Fixup typo in update_vsyscall_old definition (diff) | |
download | linux-e7fda6c4c3c1a7d6996dd75fd84670fa0b5d448f.tar.xz linux-e7fda6c4c3c1a7d6996dd75fd84670fa0b5d448f.zip |
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer and time updates from Thomas Gleixner:
"A rather large update of timers, timekeeping & co
- Core timekeeping code is year-2038 safe now for 32bit machines.
Now we just need to fix all in kernel users and the gazillion of
user space interfaces which rely on timespec/timeval :)
- Better cache layout for the timekeeping internal data structures.
- Proper nanosecond based interfaces for in kernel users.
- Tree wide cleanup of code which wants nanoseconds but does hoops
and loops to convert back and forth from timespecs. Some of it
definitely belongs into the ugly code museum.
- Consolidation of the timekeeping interface zoo.
- A fast NMI safe accessor to clock monotonic for tracing. This is a
long standing request to support correlated user/kernel space
traces. With proper NTP frequency correction it's also suitable
for correlation of traces accross separate machines.
- Checkpoint/restart support for timerfd.
- A few NOHZ[_FULL] improvements in the [hr]timer code.
- Code move from kernel to kernel/time of all time* related code.
- New clocksource/event drivers from the ARM universe. I'm really
impressed that despite an architected timer in the newer chips SoC
manufacturers insist on inventing new and differently broken SoC
specific timers.
[ Ed. "Impressed"? I don't think that word means what you think it means ]
- Another round of code move from arch to drivers. Looks like most
of the legacy mess in ARM regarding timers is sorted out except for
a few obnoxious strongholds.
- The usual updates and fixlets all over the place"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
timekeeping: Fixup typo in update_vsyscall_old definition
clocksource: document some basic timekeeping concepts
timekeeping: Use cached ntp_tick_length when accumulating error
timekeeping: Rework frequency adjustments to work better w/ nohz
timekeeping: Minor fixup for timespec64->timespec assignment
ftrace: Provide trace clocks monotonic
timekeeping: Provide fast and NMI safe access to CLOCK_MONOTONIC
seqcount: Add raw_write_seqcount_latch()
seqcount: Provide raw_read_seqcount()
timekeeping: Use tk_read_base as argument for timekeeping_get_ns()
timekeeping: Create struct tk_read_base and use it in struct timekeeper
timekeeping: Restructure the timekeeper some more
clocksource: Get rid of cycle_last
clocksource: Move cycle_last validation to core code
clocksource: Make delta calculation a function
wireless: ath9k: Get rid of timespec conversions
drm: vmwgfx: Use nsec based interfaces
drm: i915: Use nsec based interfaces
timekeeping: Provide ktime_get_raw()
hangcheck-timer: Use ktime_get_ns()
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 25 | ||||
-rw-r--r-- | kernel/acct.c | 10 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_main.c | 2 | ||||
-rw-r--r-- | kernel/delayacct.c | 62 | ||||
-rw-r--r-- | kernel/fork.c | 5 | ||||
-rw-r--r-- | kernel/time/Kconfig | 9 | ||||
-rw-r--r-- | kernel/time/Makefile | 19 | ||||
-rw-r--r-- | kernel/time/clocksource.c | 12 | ||||
-rw-r--r-- | kernel/time/hrtimer.c (renamed from kernel/hrtimer.c) | 125 | ||||
-rw-r--r-- | kernel/time/itimer.c (renamed from kernel/itimer.c) | 0 | ||||
-rw-r--r-- | kernel/time/ntp.c | 15 | ||||
-rw-r--r-- | kernel/time/ntp_internal.h | 2 | ||||
-rw-r--r-- | kernel/time/posix-cpu-timers.c (renamed from kernel/posix-cpu-timers.c) | 0 | ||||
-rw-r--r-- | kernel/time/posix-timers.c (renamed from kernel/posix-timers.c) | 2 | ||||
-rw-r--r-- | kernel/time/tick-internal.h | 2 | ||||
-rw-r--r-- | kernel/time/time.c (renamed from kernel/time.c) | 64 | ||||
-rw-r--r-- | kernel/time/timeconst.bc (renamed from kernel/timeconst.bc) | 0 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 1147 | ||||
-rw-r--r-- | kernel/time/timekeeping.h | 20 | ||||
-rw-r--r-- | kernel/time/timekeeping_debug.c | 2 | ||||
-rw-r--r-- | kernel/time/timekeeping_internal.h | 17 | ||||
-rw-r--r-- | kernel/time/timer.c (renamed from kernel/timer.c) | 34 | ||||
-rw-r--r-- | kernel/time/udelay_test.c | 168 | ||||
-rw-r--r-- | kernel/trace/trace.c | 11 | ||||
-rw-r--r-- | kernel/tsacct.c | 19 |
25 files changed, 1024 insertions, 748 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index f2a8b6246ce9..973a40cf8068 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -3,12 +3,11 @@ # obj-y = fork.o exec_domain.o panic.o \ - cpu.o exit.o itimer.o time.o softirq.o resource.o \ - sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ + cpu.o exit.o softirq.o resource.o \ + sysctl.o sysctl_binary.o capability.o ptrace.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ - extable.o params.o posix-timers.o \ - kthread.o sys_ni.o posix-cpu-timers.o \ - hrtimer.o nsproxy.o \ + extable.o params.o \ + kthread.o sys_ni.o nsproxy.o \ notifier.o ksysfs.o cred.o reboot.o \ async.o range.o groups.o smpboot.o @@ -110,22 +109,6 @@ targets += config_data.h $(obj)/config_data.h: $(obj)/config_data.gz FORCE $(call filechk,ikconfiggz) -$(obj)/time.o: $(obj)/timeconst.h - -quiet_cmd_hzfile = HZFILE $@ - cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@ - -targets += hz.bc -$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE - $(call if_changed,hzfile) - -quiet_cmd_bc = BC $@ - cmd_bc = bc -q $(filter-out FORCE,$^) > $@ - -targets += timeconst.h -$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE - $(call if_changed,bc) - ############################################################################### # # Roll all the X.509 certificates that we can find together and pull them into diff --git a/kernel/acct.c b/kernel/acct.c index 808a86ff229d..a1844f14c6d6 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -458,9 +458,7 @@ static void do_acct_process(struct bsd_acct_struct *acct, acct_t ac; mm_segment_t fs; unsigned long flim; - u64 elapsed; - u64 run_time; - struct timespec uptime; + u64 elapsed, run_time; struct tty_struct *tty; const struct cred *orig_cred; @@ -484,10 +482,8 @@ static void do_acct_process(struct bsd_acct_struct *acct, strlcpy(ac.ac_comm, current->comm, sizeof(ac.ac_comm)); /* calculate run_time in nsec*/ - do_posix_clock_monotonic_gettime(&uptime); - run_time = (u64)uptime.tv_sec*NSEC_PER_SEC + uptime.tv_nsec; - run_time -= (u64)current->group_leader->start_time.tv_sec * NSEC_PER_SEC - + current->group_leader->start_time.tv_nsec; + run_time = ktime_get_ns(); + run_time -= current->group_leader->start_time; /* convert nsec -> AHZ */ elapsed = nsec_to_AHZ(run_time); #if ACCT_VERSION==3 diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 2f7c760305ca..379650b984f8 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2472,7 +2472,7 @@ static void kdb_gmtime(struct timespec *tv, struct kdb_tm *tm) static void kdb_sysinfo(struct sysinfo *val) { struct timespec uptime; - do_posix_clock_monotonic_gettime(&uptime); + ktime_get_ts(&uptime); memset(val, 0, sizeof(*val)); val->uptime = uptime.tv_sec; val->loads[0] = avenrun[0]; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 54996b71e66d..ef90b04d783f 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -46,42 +46,25 @@ void __delayacct_tsk_init(struct task_struct *tsk) } /* - * Start accounting for a delay statistic using - * its starting timestamp (@start) + * Finish delay accounting for a statistic using its timestamps (@start), + * accumalator (@total) and @count */ - -static inline void delayacct_start(struct timespec *start) +static void delayacct_end(u64 *start, u64 *total, u32 *count) { - do_posix_clock_monotonic_gettime(start); -} - -/* - * Finish delay accounting for a statistic using - * its timestamps (@start, @end), accumalator (@total) and @count - */ - -static void delayacct_end(struct timespec *start, struct timespec *end, - u64 *total, u32 *count) -{ - struct timespec ts; - s64 ns; + s64 ns = ktime_get_ns() - *start; unsigned long flags; - do_posix_clock_monotonic_gettime(end); - ts = timespec_sub(*end, *start); - ns = timespec_to_ns(&ts); - if (ns < 0) - return; - - spin_lock_irqsave(¤t->delays->lock, flags); - *total += ns; - (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + if (ns > 0) { + spin_lock_irqsave(¤t->delays->lock, flags); + *total += ns; + (*count)++; + spin_unlock_irqrestore(¤t->delays->lock, flags); + } } void __delayacct_blkio_start(void) { - delayacct_start(¤t->delays->blkio_start); + current->delays->blkio_start = ktime_get_ns(); } void __delayacct_blkio_end(void) @@ -89,35 +72,29 @@ void __delayacct_blkio_end(void) if (current->delays->flags & DELAYACCT_PF_SWAPIN) /* Swapin block I/O */ delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_end, ¤t->delays->swapin_delay, ¤t->delays->swapin_count); else /* Other block I/O */ delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_end, ¤t->delays->blkio_delay, ¤t->delays->blkio_count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { - s64 tmp; - unsigned long t1; - unsigned long long t2, t3; - unsigned long flags; - struct timespec ts; cputime_t utime, stime, stimescaled, utimescaled; + unsigned long long t2, t3; + unsigned long flags, t1; + s64 tmp; - tmp = (s64)d->cpu_run_real_total; task_cputime(tsk, &utime, &stime); - cputime_to_timespec(utime + stime, &ts); - tmp += timespec_to_ns(&ts); + tmp = (s64)d->cpu_run_real_total; + tmp += cputime_to_nsecs(utime + stime); d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; - tmp = (s64)d->cpu_scaled_run_real_total; task_cputime_scaled(tsk, &utimescaled, &stimescaled); - cputime_to_timespec(utimescaled + stimescaled, &ts); - tmp += timespec_to_ns(&ts); + tmp = (s64)d->cpu_scaled_run_real_total; + tmp += cputime_to_nsecs(utimescaled + stimescaled); d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; @@ -169,13 +146,12 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) void __delayacct_freepages_start(void) { - delayacct_start(¤t->delays->freepages_start); + current->delays->freepages_start = ktime_get_ns(); } void __delayacct_freepages_end(void) { delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_end, ¤t->delays->freepages_delay, ¤t->delays->freepages_count); } diff --git a/kernel/fork.c b/kernel/fork.c index 962885edbe53..5f1bf3bebb4f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1261,9 +1261,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - do_posix_clock_monotonic_gettime(&p->start_time); - p->real_start_time = p->start_time; - monotonic_to_bootbased(&p->real_start_time); + p->start_time = ktime_get_ns(); + p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; if (clone_flags & CLONE_THREAD) diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index f448513a45ed..d626dc98e8df 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,6 +12,11 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool +# Clocksources require validation of the clocksource against the last +# cycle update - x86/TSC misfeature +config CLOCKSOURCE_VALIDATE_LAST_CYCLE + bool + # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool @@ -20,10 +25,6 @@ config GENERIC_TIME_VSYSCALL config GENERIC_TIME_VSYSCALL_OLD bool -# ktime_t scalar 64bit nsec representation -config KTIME_SCALAR - bool - # Old style timekeeping config ARCH_USES_GETTIMEOFFSET bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 57a413fd0ebf..7347426fa68d 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,3 +1,4 @@ +obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o posix-clock.o alarmtimer.o @@ -12,3 +13,21 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o +obj-$(CONFIG_TEST_UDELAY) += udelay_test.o + +$(obj)/time.o: $(obj)/timeconst.h + +quiet_cmd_hzfile = HZFILE $@ + cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@ + +targets += hz.bc +$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE + $(call if_changed,hzfile) + +quiet_cmd_bc = BC $@ + cmd_bc = bc -q $(filter-out FORCE,$^) > $@ + +targets += timeconst.h +$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE + $(call if_changed,bc) + diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index ba3e502c955a..2e949cc9c9f1 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -32,6 +32,7 @@ #include <linux/kthread.h> #include "tick-internal.h" +#include "timekeeping_internal.h" void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, @@ -249,7 +250,7 @@ void clocksource_mark_unstable(struct clocksource *cs) static void clocksource_watchdog(unsigned long data) { struct clocksource *cs; - cycle_t csnow, wdnow; + cycle_t csnow, wdnow, delta; int64_t wd_nsec, cs_nsec; int next_cpu, reset_pending; @@ -282,11 +283,12 @@ static void clocksource_watchdog(unsigned long data) continue; } - wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, - watchdog->mult, watchdog->shift); + delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask); + wd_nsec = clocksource_cyc2ns(delta, watchdog->mult, + watchdog->shift); - cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & - cs->mask, cs->mult, cs->shift); + delta = clocksource_delta(csnow, cs->cs_last, cs->mask); + cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); cs->cs_last = csnow; cs->wd_last = wdnow; diff --git a/kernel/hrtimer.c b/kernel/time/hrtimer.c index 3ab28993f6e0..1c2fe7de2842 100644 --- a/kernel/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -54,6 +54,8 @@ #include <trace/events/timer.h> +#include "timekeeping.h" + /* * The timer bases: * @@ -114,21 +116,18 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) */ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) { - ktime_t xtim, mono, boot; - struct timespec xts, tom, slp; - s32 tai_offset; + ktime_t xtim, mono, boot, tai; + ktime_t off_real, off_boot, off_tai; - get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp); - tai_offset = timekeeping_get_tai_offset(); + mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai); + boot = ktime_add(mono, off_boot); + xtim = ktime_add(mono, off_real); + tai = ktime_add(xtim, off_tai); - xtim = timespec_to_ktime(xts); - mono = ktime_add(xtim, timespec_to_ktime(tom)); - boot = ktime_add(mono, timespec_to_ktime(slp)); base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim; base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono; base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot; - base->clock_base[HRTIMER_BASE_TAI].softirq_time = - ktime_add(xtim, ktime_set(tai_offset, 0)); + base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai; } /* @@ -264,60 +263,6 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) * too large for inlining: */ #if BITS_PER_LONG < 64 -# ifndef CONFIG_KTIME_SCALAR -/** - * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable - * @kt: addend - * @nsec: the scalar nsec value to add - * - * Returns the sum of kt and nsec in ktime_t format - */ -ktime_t ktime_add_ns(const ktime_t kt, u64 nsec) -{ - ktime_t tmp; - - if (likely(nsec < NSEC_PER_SEC)) { - tmp.tv64 = nsec; - } else { - unsigned long rem = do_div(nsec, NSEC_PER_SEC); - - /* Make sure nsec fits into long */ - if (unlikely(nsec > KTIME_SEC_MAX)) - return (ktime_t){ .tv64 = KTIME_MAX }; - - tmp = ktime_set((long)nsec, rem); - } - - return ktime_add(kt, tmp); -} - -EXPORT_SYMBOL_GPL(ktime_add_ns); - -/** - * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable - * @kt: minuend - * @nsec: the scalar nsec value to subtract - * - * Returns the subtraction of @nsec from @kt in ktime_t format - */ -ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec) -{ - ktime_t tmp; - - if (likely(nsec < NSEC_PER_SEC)) { - tmp.tv64 = nsec; - } else { - unsigned long rem = do_div(nsec, NSEC_PER_SEC); - - tmp = ktime_set((long)nsec, rem); - } - - return ktime_sub(kt, tmp); -} - -EXPORT_SYMBOL_GPL(ktime_sub_ns); -# endif /* !CONFIG_KTIME_SCALAR */ - /* * Divide a ktime value by a nanosecond value */ @@ -337,6 +282,7 @@ u64 ktime_divns(const ktime_t kt, s64 div) return dclc; } +EXPORT_SYMBOL_GPL(ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* @@ -602,6 +548,11 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * + * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming + * and no expiry check happens. The timer gets enqueued into the rbtree. The + * reprogramming and expiry check is done in the hrtimer_interrupt or in the + * softirq. + * * Called with interrupts disabled and base->cpu_base.lock held */ static int hrtimer_reprogram(struct hrtimer *timer, @@ -662,25 +613,13 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) base->hres_active = 0; } -/* - * When High resolution timers are active, try to reprogram. Note, that in case - * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry - * check happens. The timer gets enqueued into the rbtree. The reprogramming - * and expiry check is done in the hrtimer_interrupt or in the softirq. - */ -static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) -{ - return base->cpu_base->hres_active && hrtimer_reprogram(timer, base); -} - static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; - return ktime_get_update_offsets(offs_real, offs_boot, offs_tai); + return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai); } /* @@ -755,8 +694,8 @@ static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline int hrtimer_switch_to_hres(void) { return 0; } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } -static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) +static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) { return 0; } @@ -1013,14 +952,25 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, leftmost = enqueue_hrtimer(timer, new_base); - /* - * Only allow reprogramming if the new base is on this CPU. - * (it might still be on another CPU if the timer was pending) - * - * XXX send_remote_softirq() ? - */ - if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases) - && hrtimer_enqueue_reprogram(timer, new_base)) { + if (!leftmost) { + unlock_hrtimer_base(timer, &flags); + return ret; + } + + if (!hrtimer_is_hres_active(timer)) { + /* + * Kick to reschedule the next tick to handle the new timer + * on dynticks target. + */ + wake_up_nohz_cpu(new_base->cpu_base->cpu); + } else if (new_base->cpu_base == &__get_cpu_var(hrtimer_bases) && + hrtimer_reprogram(timer, new_base)) { + /* + * Only allow reprogramming if the new base is on this CPU. + * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? + */ if (wakeup) { /* * We need to drop cpu_base->lock to avoid a @@ -1680,6 +1630,7 @@ static void init_hrtimers_cpu(int cpu) timerqueue_init_head(&cpu_base->clock_base[i].active); } + cpu_base->cpu = cpu; hrtimer_init_hres(cpu_base); } diff --git a/kernel/itimer.c b/kernel/time/itimer.c index 8d262b467573..8d262b467573 100644 --- a/kernel/itimer.c +++ b/kernel/time/itimer.c diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 33db43a39515..87a346fd6d61 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -466,7 +466,8 @@ static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); static void sync_cmos_clock(struct work_struct *work) { - struct timespec now, next; + struct timespec64 now; + struct timespec next; int fail = 1; /* @@ -485,9 +486,9 @@ static void sync_cmos_clock(struct work_struct *work) return; } - getnstimeofday(&now); + getnstimeofday64(&now); if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { - struct timespec adjust = now; + struct timespec adjust = timespec64_to_timespec(now); fail = -ENODEV; if (persistent_clock_is_local) @@ -531,7 +532,7 @@ void ntp_notify_cmos_timer(void) { } /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc, struct timespec *ts) +static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -554,7 +555,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) static inline void process_adjtimex_modes(struct timex *txc, - struct timespec *ts, + struct timespec64 *ts, s32 *time_tai) { if (txc->modes & ADJ_STATUS) @@ -640,7 +641,7 @@ int ntp_validate_timex(struct timex *txc) * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) { int result; @@ -684,7 +685,7 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) /* fill PPS status fields */ pps_fill_timex(txc); - txc->time.tv_sec = ts->tv_sec; + txc->time.tv_sec = (time_t)ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) txc->time.tv_usec /= NSEC_PER_USEC; diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 1950cb4ca2a4..bbd102ad9df7 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -7,6 +7,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern int second_overflow(unsigned long secs); extern int ntp_validate_timex(struct timex *); -extern int __do_adjtimex(struct timex *, struct timespec *, s32 *); +extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); extern void __hardpps(const struct timespec *, const struct timespec *); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 3b8946416a5f..3b8946416a5f 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c diff --git a/kernel/posix-timers.c b/kernel/time/posix-timers.c index 424c2d4265c9..42b463ad90f2 100644 --- a/kernel/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -49,6 +49,8 @@ #include <linux/export.h> #include <linux/hashtable.h> +#include "timekeeping.h" + /* * Management arrays for POSIX timers. Timers are now kept in static hash table * with 512 entries. diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 7ab92b19965a..c19c1d84b6f3 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -4,6 +4,8 @@ #include <linux/hrtimer.h> #include <linux/tick.h> +#include "timekeeping.h" + extern seqlock_t jiffies_lock; #define CS_NAME_LEN 32 diff --git a/kernel/time.c b/kernel/time/time.c index 7c7964c33ae7..f0294ba14634 100644 --- a/kernel/time.c +++ b/kernel/time/time.c @@ -42,6 +42,7 @@ #include <asm/unistd.h> #include "timeconst.h" +#include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some @@ -420,6 +421,68 @@ struct timeval ns_to_timeval(const s64 nsec) } EXPORT_SYMBOL(ns_to_timeval); +#if BITS_PER_LONG == 32 +/** + * set_normalized_timespec - set timespec sec and nsec parts and normalize + * + * @ts: pointer to timespec variable to be set + * @sec: seconds to set + * @nsec: nanoseconds to set + * + * Set seconds and nanoseconds field of a timespec variable and + * normalize to the timespec storage format + * + * Note: The tv_nsec part is always in the range of + * 0 <= tv_nsec < NSEC_PER_SEC + * For negative values only the tv_sec field is negative ! + */ +void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) +{ + while (nsec >= NSEC_PER_SEC) { + /* + * The following asm() prevents the compiler from + * optimising this loop into a modulo operation. See + * also __iter_div_u64_rem() in include/linux/time.h + */ + asm("" : "+rm"(nsec)); + nsec -= NSEC_PER_SEC; + ++sec; + } + while (nsec < 0) { + asm("" : "+rm"(nsec)); + nsec += NSEC_PER_SEC; + --sec; + } + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} +EXPORT_SYMBOL(set_normalized_timespec64); + +/** + * ns_to_timespec64 - Convert nanoseconds to timespec64 + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec64 representation of the nsec parameter. + */ +struct timespec64 ns_to_timespec64(const s64 nsec) +{ + struct timespec64 ts; + s32 rem; + + if (!nsec) + return (struct timespec64) {0, 0}; + + ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); + if (unlikely(rem < 0)) { + ts.tv_sec--; + rem += NSEC_PER_SEC; + } + ts.tv_nsec = rem; + + return ts; +} +EXPORT_SYMBOL(ns_to_timespec64); +#endif /* * When we convert to jiffies then we interpret incoming values * the following way: @@ -694,6 +757,7 @@ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } +EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /* * Add two timespec values and do a safety check for overflow. diff --git a/kernel/timeconst.bc b/kernel/time/timeconst.bc index 511bdf2cafda..511bdf2cafda 100644 --- a/kernel/timeconst.bc +++ b/kernel/time/timeconst.bc diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 32d8d6aaedb8..f36b02838a47 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -32,11 +32,34 @@ #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) -static struct timekeeper timekeeper; +/* + * The most important data for readout fits into a single 64 byte + * cache line. + */ +static struct { + seqcount_t seq; + struct timekeeper timekeeper; +} tk_core ____cacheline_aligned; + static DEFINE_RAW_SPINLOCK(timekeeper_lock); -static seqcount_t timekeeper_seq; static struct timekeeper shadow_timekeeper; +/** + * struct tk_fast - NMI safe timekeeper + * @seq: Sequence counter for protecting updates. The lowest bit + * is the index for the tk_read_base array + * @base: tk_read_base array. Access is indexed by the lowest bit of + * @seq. + * + * See @update_fast_timekeeper() below. + */ +struct tk_fast { + seqcount_t seq; + struct tk_read_base base[2]; +}; + +static struct tk_fast tk_fast_mono ____cacheline_aligned; + /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -45,49 +68,54 @@ bool __read_mostly persistent_clock_exist = false; static inline void tk_normalize_xtime(struct timekeeper *tk) { - while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) { - tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift; + while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) { + tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift; tk->xtime_sec++; } } -static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts) +static inline struct timespec64 tk_xtime(struct timekeeper *tk) +{ + struct timespec64 ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + return ts; +} + +static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; - tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift; + tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift; } -static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts) +static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; - tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift; + tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift; tk_normalize_xtime(tk); } -static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm) +static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { - struct timespec tmp; + struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ - set_normalized_timespec(&tmp, -tk->wall_to_monotonic.tv_sec, + set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); - WARN_ON_ONCE(tk->offs_real.tv64 != timespec_to_ktime(tmp).tv64); + WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64); tk->wall_to_monotonic = wtm; - set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec); - tk->offs_real = timespec_to_ktime(tmp); + set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); + tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } -static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t) +static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Verify consistency before modifying */ - WARN_ON_ONCE(tk->offs_boot.tv64 != timespec_to_ktime(tk->total_sleep_time).tv64); - - tk->total_sleep_time = t; - tk->offs_boot = timespec_to_ktime(t); + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /** @@ -107,9 +135,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; - old_clock = tk->clock; - tk->clock = clock; - tk->cycle_last = clock->cycle_last = clock->read(clock); + old_clock = tk->tkr.clock; + tk->tkr.clock = clock; + tk->tkr.read = clock->read; + tk->tkr.mask = clock->mask; + tk->tkr.cycle_last = tk->tkr.read(clock); /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -133,78 +163,212 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) - tk->xtime_nsec >>= -shift_change; + tk->tkr.xtime_nsec >>= -shift_change; else - tk->xtime_nsec <<= shift_change; + tk->tkr.xtime_nsec <<= shift_change; } - tk->shift = clock->shift; + tk->tkr.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; + tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - tk->mult = clock->mult; + tk->tkr.mult = clock->mult; + tk->ntp_err_mult = 0; } /* Timekeeper helper functions. */ #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET -u32 (*arch_gettimeoffset)(void); - -u32 get_arch_timeoffset(void) -{ - if (likely(arch_gettimeoffset)) - return arch_gettimeoffset(); - return 0; -} +static u32 default_arch_gettimeoffset(void) { return 0; } +u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; #else -static inline u32 get_arch_timeoffset(void) { return 0; } +static inline u32 arch_gettimeoffset(void) { return 0; } #endif -static inline s64 timekeeping_get_ns(struct timekeeper *tk) +static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) { - cycle_t cycle_now, cycle_delta; - struct clocksource *clock; + cycle_t cycle_now, delta; s64 nsec; /* read clocksource: */ - clock = tk->clock; - cycle_now = clock->read(clock); + cycle_now = tkr->read(tkr->clock); /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); - nsec = cycle_delta * tk->mult + tk->xtime_nsec; - nsec >>= tk->shift; + nsec = delta * tkr->mult + tkr->xtime_nsec; + nsec >>= tkr->shift; /* If arch requires, add in get_arch_timeoffset() */ - return nsec + get_arch_timeoffset(); + return nsec + arch_gettimeoffset(); } static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) { - cycle_t cycle_now, cycle_delta; - struct clocksource *clock; + struct clocksource *clock = tk->tkr.clock; + cycle_t cycle_now, delta; s64 nsec; /* read clocksource: */ - clock = tk->clock; - cycle_now = clock->read(clock); + cycle_now = tk->tkr.read(clock); /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); /* convert delta to nanoseconds. */ - nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); + nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); /* If arch requires, add in get_arch_timeoffset() */ - return nsec + get_arch_timeoffset(); + return nsec + arch_gettimeoffset(); +} + +/** + * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. + * @tk: The timekeeper from which we take the update + * @tkf: The fast timekeeper to update + * @tbase: The time base for the fast timekeeper (mono/raw) + * + * We want to use this from any context including NMI and tracing / + * instrumenting the timekeeping code itself. + * + * So we handle this differently than the other timekeeping accessor + * functions which retry when the sequence count has changed. The + * update side does: + * + * smp_wmb(); <- Ensure that the last base[1] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[0], tk); + * smp_wmb(); <- Ensure that the base[0] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[1], tk); + * + * The reader side does: + * + * do { + * seq = tkf->seq; + * smp_rmb(); + * idx = seq & 0x01; + * now = now(tkf->base[idx]); + * smp_rmb(); + * } while (seq != tkf->seq) + * + * As long as we update base[0] readers are forced off to + * base[1]. Once base[0] is updated readers are redirected to base[0] + * and the base[1] update takes place. + * + * So if a NMI hits the update of base[0] then it will use base[1] + * which is still consistent. In the worst case this can result is a + * slightly wrong timestamp (a few nanoseconds). See + * @ktime_get_mono_fast_ns. + */ +static void update_fast_timekeeper(struct timekeeper *tk) +{ + struct tk_read_base *base = tk_fast_mono.base; + + /* Force readers off to base[1] */ + raw_write_seqcount_latch(&tk_fast_mono.seq); + + /* Update base[0] */ + memcpy(base, &tk->tkr, sizeof(*base)); + + /* Force readers back to base[0] */ + raw_write_seqcount_latch(&tk_fast_mono.seq); + + /* Update base[1] */ + memcpy(base + 1, base, sizeof(*base)); } +/** + * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic + * + * This timestamp is not guaranteed to be monotonic across an update. + * The timestamp is calculated by: + * + * now = base_mono + clock_delta * slope + * + * So if the update lowers the slope, readers who are forced to the + * not yet updated second array are still using the old steeper slope. + * + * tmono + * ^ + * | o n + * | o n + * | u + * | o + * |o + * |12345678---> reader order + * + * o = old slope + * u = update + * n = new slope + * + * So reader 6 will observe time going backwards versus reader 5. + * + * While other CPUs are likely to be able observe that, the only way + * for a CPU local observation is when an NMI hits in the middle of + * the update. Timestamps taken from that NMI context might be ahead + * of the following timestamps. Callers need to be aware of that and + * deal with it. + */ +u64 notrace ktime_get_mono_fast_ns(void) +{ + struct tk_read_base *tkr; + unsigned int seq; + u64 now; + + do { + seq = raw_read_seqcount(&tk_fast_mono.seq); + tkr = tk_fast_mono.base + (seq & 0x01); + now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr); + + } while (read_seqcount_retry(&tk_fast_mono.seq, seq)); + return now; +} +EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); + +#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD + +static inline void update_vsyscall(struct timekeeper *tk) +{ + struct timespec xt; + + xt = timespec64_to_timespec(tk_xtime(tk)); + update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->tkr.clock, tk->tkr.mult, + tk->tkr.cycle_last); +} + +static inline void old_vsyscall_fixup(struct timekeeper *tk) +{ + s64 remainder; + + /* + * Store only full nanoseconds into xtime_nsec after rounding + * it up and add the remainder to the error difference. + * XXX - This is necessary to avoid small 1ns inconsistnecies caused + * by truncating the remainder in vsyscalls. However, it causes + * additional work to be done in timekeeping_adjust(). Once + * the vsyscall implementations are converted to use xtime_nsec + * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD + * users are removed, this can be killed. + */ + remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1); + tk->tkr.xtime_nsec -= remainder; + tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift; + tk->ntp_error += remainder << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift; +} +#else +#define old_vsyscall_fixup(tk) +#endif + static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) @@ -217,7 +381,7 @@ static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; @@ -247,6 +411,29 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); +/* + * Update the ktime_t based scalar nsec members of the timekeeper + */ +static inline void tk_update_ktime_data(struct timekeeper *tk) +{ + s64 nsec; + + /* + * The xtime based monotonic readout is: + * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); + * The ktime based monotonic readout is: + * nsec = base_mono + now(); + * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + */ + nsec = (s64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); + nsec *= NSEC_PER_SEC; + nsec += tk->wall_to_monotonic.tv_nsec; + tk->tkr.base_mono = ns_to_ktime(nsec); + + /* Update the monotonic raw base */ + tk->base_raw = timespec64_to_ktime(tk->raw_time); +} + /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { @@ -257,8 +444,13 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + tk_update_ktime_data(tk); + if (action & TK_MIRROR) - memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); + memcpy(&shadow_timekeeper, &tk_core.timekeeper, + sizeof(tk_core.timekeeper)); + + update_fast_timekeeper(tk); } /** @@ -270,49 +462,48 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - cycle_t cycle_now, cycle_delta; - struct clocksource *clock; + struct clocksource *clock = tk->tkr.clock; + cycle_t cycle_now, delta; s64 nsec; - clock = tk->clock; - cycle_now = clock->read(clock); - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - tk->cycle_last = clock->cycle_last = cycle_now; + cycle_now = tk->tkr.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); + tk->tkr.cycle_last = cycle_now; - tk->xtime_nsec += cycle_delta * tk->mult; + tk->tkr.xtime_nsec += delta * tk->tkr.mult; /* If arch requires, add in get_arch_timeoffset() */ - tk->xtime_nsec += (u64)get_arch_timeoffset() << tk->shift; + tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift; tk_normalize_xtime(tk); - nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); - timespec_add_ns(&tk->raw_time, nsec); + nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); + timespec64_add_ns(&tk->raw_time, nsec); } /** - * __getnstimeofday - Returns the time of day in a timespec. + * __getnstimeofday64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Updates the time of day in the timespec. * Returns 0 on success, or -ve when suspended (timespec will be undefined). */ -int __getnstimeofday(struct timespec *ts) +int __getnstimeofday64(struct timespec64 *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; s64 nsecs = 0; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsecs = timekeeping_get_ns(tk); + nsecs = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; - timespec_add_ns(ts, nsecs); + timespec64_add_ns(ts, nsecs); /* * Do not bail out early, in case there were callers still using @@ -322,116 +513,138 @@ int __getnstimeofday(struct timespec *ts) return -EAGAIN; return 0; } -EXPORT_SYMBOL(__getnstimeofday); +EXPORT_SYMBOL(__getnstimeofday64); /** - * getnstimeofday - Returns the time of day in a timespec. + * getnstimeofday64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec (WARN if suspended). */ -void getnstimeofday(struct timespec *ts) +void getnstimeofday64(struct timespec64 *ts) { - WARN_ON(__getnstimeofday(ts)); + WARN_ON(__getnstimeofday64(ts)); } -EXPORT_SYMBOL(getnstimeofday); +EXPORT_SYMBOL(getnstimeofday64); ktime_t ktime_get(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; - s64 secs, nsecs; + ktime_t base; + s64 nsecs; WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); - secs = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec; + seq = read_seqcount_begin(&tk_core.seq); + base = tk->tkr.base_mono; + nsecs = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); - /* - * Use ktime_set/ktime_add_ns to create a proper ktime on - * 32-bit architectures without CONFIG_KTIME_SCALAR. - */ - return ktime_add_ns(ktime_set(secs, 0), nsecs); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); -/** - * ktime_get_ts - get the monotonic clock in timespec format - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime - * clock and the wall_to_monotonic offset and stores the result - * in normalized timespec format in the variable pointed to by @ts. - */ -void ktime_get_ts(struct timespec *ts) +static ktime_t *offsets[TK_OFFS_MAX] = { + [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, + [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, +}; + +ktime_t ktime_get_with_offset(enum tk_offsets offs) { - struct timekeeper *tk = &timekeeper; - struct timespec tomono; - s64 nsec; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; + ktime_t base, *offset = offsets[offs]; + s64 nsecs; WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(tk); - tomono = tk->wall_to_monotonic; + seq = read_seqcount_begin(&tk_core.seq); + base = ktime_add(tk->tkr.base_mono, *offset); + nsecs = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsec + tomono.tv_nsec); -} -EXPORT_SYMBOL_GPL(ktime_get_ts); + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_with_offset); /** - * timekeeping_clocktai - Returns the TAI time of day in a timespec - * @ts: pointer to the timespec to be set - * - * Returns the time of day in a timespec. + * ktime_mono_to_any() - convert mononotic time to any other time + * @tmono: time to convert. + * @offs: which offset to use */ -void timekeeping_clocktai(struct timespec *ts) +ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { - struct timekeeper *tk = &timekeeper; + ktime_t *offset = offsets[offs]; unsigned long seq; - u64 nsecs; - - WARN_ON(timekeeping_suspended); + ktime_t tconv; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); + tconv = ktime_add(tmono, *offset); + } while (read_seqcount_retry(&tk_core.seq, seq)); - ts->tv_sec = tk->xtime_sec + tk->tai_offset; - nsecs = timekeeping_get_ns(tk); + return tconv; +} +EXPORT_SYMBOL_GPL(ktime_mono_to_any); - } while (read_seqcount_retry(&timekeeper_seq, seq)); +/** + * ktime_get_raw - Returns the raw monotonic time in ktime_t format + */ +ktime_t ktime_get_raw(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + s64 nsecs; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsecs); + do { + seq = read_seqcount_begin(&tk_core.seq); + base = tk->base_raw; + nsecs = timekeeping_get_ns_raw(tk); -} -EXPORT_SYMBOL(timekeeping_clocktai); + } while (read_seqcount_retry(&tk_core.seq, seq)); + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_raw); /** - * ktime_get_clocktai - Returns the TAI time of day in a ktime + * ktime_get_ts64 - get the monotonic clock in timespec64 format + * @ts: pointer to timespec variable * - * Returns the time of day in a ktime. + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by @ts. */ -ktime_t ktime_get_clocktai(void) +void ktime_get_ts64(struct timespec64 *ts) { - struct timespec ts; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 tomono; + s64 nsec; + unsigned int seq; + + WARN_ON(timekeeping_suspended); - timekeeping_clocktai(&ts); - return timespec_to_ktime(ts); + do { + seq = read_seqcount_begin(&tk_core.seq); + ts->tv_sec = tk->xtime_sec; + nsec = timekeeping_get_ns(&tk->tkr); + tomono = tk->wall_to_monotonic; + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + ts->tv_sec += tomono.tv_sec; + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsec + tomono.tv_nsec); } -EXPORT_SYMBOL(ktime_get_clocktai); +EXPORT_SYMBOL_GPL(ktime_get_ts64); #ifdef CONFIG_NTP_PPS @@ -446,23 +659,23 @@ EXPORT_SYMBOL(ktime_get_clocktai); */ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; s64 nsecs_raw, nsecs_real; WARN_ON_ONCE(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - *ts_raw = tk->raw_time; + *ts_raw = timespec64_to_timespec(tk->raw_time); ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; nsecs_raw = timekeeping_get_ns_raw(tk); - nsecs_real = timekeeping_get_ns(tk); + nsecs_real = timekeeping_get_ns(&tk->tkr); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -479,9 +692,9 @@ EXPORT_SYMBOL(getnstime_raw_and_real); */ void do_gettimeofday(struct timeval *tv) { - struct timespec now; + struct timespec64 now; - getnstimeofday(&now); + getnstimeofday64(&now); tv->tv_sec = now.tv_sec; tv->tv_usec = now.tv_nsec/1000; } @@ -495,15 +708,15 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(const struct timespec *tv) { - struct timekeeper *tk = &timekeeper; - struct timespec ts_delta, xt; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 ts_delta, xt, tmp; unsigned long flags; if (!timespec_valid_strict(tv)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); @@ -511,13 +724,14 @@ int do_settimeofday(const struct timespec *tv) ts_delta.tv_sec = tv->tv_sec - xt.tv_sec; ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec; - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, ts_delta)); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); - tk_set_xtime(tk, tv); + tmp = timespec_to_timespec64(*tv); + tk_set_xtime(tk, &tmp); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -535,33 +749,35 @@ EXPORT_SYMBOL(do_settimeofday); */ int timekeeping_inject_offset(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - struct timespec tmp; + struct timespec64 ts64, tmp; int ret = 0; if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; + ts64 = timespec_to_timespec64(*ts); + raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ - tmp = timespec_add(tk_xtime(tk), *ts); - if (!timespec_valid_strict(&tmp)) { + tmp = timespec64_add(tk_xtime(tk), ts64); + if (!timespec64_valid_strict(&tmp)) { ret = -EINVAL; goto error; } - tk_xtime_add(tk, ts); - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); + tk_xtime_add(tk, &ts64); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -578,14 +794,14 @@ EXPORT_SYMBOL(timekeeping_inject_offset); */ s32 timekeeping_get_tai_offset(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; s32 ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ret = tk->tai_offset; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -606,14 +822,14 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) */ void timekeeping_set_tai_offset(s32 tai_offset) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); __timekeeping_set_tai_offset(tk, tai_offset); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); clock_was_set(); } @@ -625,14 +841,14 @@ void timekeeping_set_tai_offset(s32 tai_offset) */ static int change_clocksource(void *data) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* @@ -641,7 +857,7 @@ static int change_clocksource(void *data) */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { - old = tk->clock; + old = tk->tkr.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); @@ -652,7 +868,7 @@ static int change_clocksource(void *data) } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return 0; @@ -667,29 +883,14 @@ static int change_clocksource(void *data) */ int timekeeping_notify(struct clocksource *clock) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; - if (tk->clock == clock) + if (tk->tkr.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); - return tk->clock == clock ? 0 : -1; -} - -/** - * ktime_get_real - get the real (wall-) time in ktime_t format - * - * returns the time in ktime_t format - */ -ktime_t ktime_get_real(void) -{ - struct timespec now; - - getnstimeofday(&now); - - return timespec_to_ktime(now); + return tk->tkr.clock == clock ? 0 : -1; } -EXPORT_SYMBOL_GPL(ktime_get_real); /** * getrawmonotonic - Returns the raw monotonic time in a timespec @@ -699,18 +900,20 @@ EXPORT_SYMBOL_GPL(ktime_get_real); */ void getrawmonotonic(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 ts64; unsigned long seq; s64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); nsecs = timekeeping_get_ns_raw(tk); - *ts = tk->raw_time; + ts64 = tk->raw_time; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - timespec_add_ns(ts, nsecs); + timespec64_add_ns(&ts64, nsecs); + *ts = timespec64_to_timespec(ts64); } EXPORT_SYMBOL(getrawmonotonic); @@ -719,16 +922,16 @@ EXPORT_SYMBOL(getrawmonotonic); */ int timekeeping_valid_for_hres(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; int ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -738,16 +941,16 @@ int timekeeping_valid_for_hres(void) */ u64 timekeeping_max_deferment(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; u64 ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - ret = tk->clock->max_idle_ns; + ret = tk->tkr.clock->max_idle_ns; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -787,14 +990,15 @@ void __weak read_boot_clock(struct timespec *ts) */ void __init timekeeping_init(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; - struct timespec now, boot, tmp; - - read_persistent_clock(&now); + struct timespec64 now, boot, tmp; + struct timespec ts; - if (!timespec_valid_strict(&now)) { + read_persistent_clock(&ts); + now = timespec_to_timespec64(ts); + if (!timespec64_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; @@ -802,8 +1006,9 @@ void __init timekeeping_init(void) } else if (now.tv_sec || now.tv_nsec) persistent_clock_exist = true; - read_boot_clock(&boot); - if (!timespec_valid_strict(&boot)) { + read_boot_clock(&ts); + boot = timespec_to_timespec64(ts); + if (!timespec64_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); boot.tv_sec = 0; @@ -811,7 +1016,7 @@ void __init timekeeping_init(void) } raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); @@ -822,24 +1027,21 @@ void __init timekeeping_init(void) tk_set_xtime(tk, &now); tk->raw_time.tv_sec = 0; tk->raw_time.tv_nsec = 0; + tk->base_raw.tv64 = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); - set_normalized_timespec(&tmp, -boot.tv_sec, -boot.tv_nsec); + set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); tk_set_wall_to_mono(tk, tmp); - tmp.tv_sec = 0; - tmp.tv_nsec = 0; - tk_set_sleep_time(tk, tmp); - - memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); + timekeeping_update(tk, TK_MIRROR); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began */ -static struct timespec timekeeping_suspend_time; +static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval @@ -849,17 +1051,17 @@ static struct timespec timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec *delta) + struct timespec64 *delta) { - if (!timespec_valid_strict(delta)) { + if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta)); - tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta)); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); + tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } @@ -875,7 +1077,8 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ void timekeeping_inject_sleeptime(struct timespec *delta) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 tmp; unsigned long flags; /* @@ -886,15 +1089,16 @@ void timekeeping_inject_sleeptime(struct timespec *delta) return; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); - __timekeeping_inject_sleeptime(tk, delta); + tmp = timespec_to_timespec64(*delta); + __timekeeping_inject_sleeptime(tk, &tmp); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -910,20 +1114,22 @@ void timekeeping_inject_sleeptime(struct timespec *delta) */ static void timekeeping_resume(void) { - struct timekeeper *tk = &timekeeper; - struct clocksource *clock = tk->clock; + struct timekeeper *tk = &tk_core.timekeeper; + struct clocksource *clock = tk->tkr.clock; unsigned long flags; - struct timespec ts_new, ts_delta; + struct timespec64 ts_new, ts_delta; + struct timespec tmp; cycle_t cycle_now, cycle_delta; bool suspendtime_found = false; - read_persistent_clock(&ts_new); + read_persistent_clock(&tmp); + ts_new = timespec_to_timespec64(tmp); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and @@ -937,15 +1143,16 @@ static void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = clock->read(clock); + cycle_now = tk->tkr.read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > clock->cycle_last) { + cycle_now > tk->tkr.cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, + tk->tkr.mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -960,10 +1167,10 @@ static void timekeeping_resume(void) } nsec += ((u64) cycle_delta * mult) >> shift; - ts_delta = ns_to_timespec(nsec); + ts_delta = ns_to_timespec64(nsec); suspendtime_found = true; - } else if (timespec_compare(&ts_new, &timekeeping_suspend_time) > 0) { - ts_delta = timespec_sub(ts_new, timekeeping_suspend_time); + } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { + ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); suspendtime_found = true; } @@ -971,11 +1178,11 @@ static void timekeeping_resume(void) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->cycle_last = clock->cycle_last = cycle_now; + tk->tkr.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); @@ -988,12 +1195,14 @@ static void timekeeping_resume(void) static int timekeeping_suspend(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - struct timespec delta, delta_delta; - static struct timespec old_delta; + struct timespec64 delta, delta_delta; + static struct timespec64 old_delta; + struct timespec tmp; - read_persistent_clock(&timekeeping_suspend_time); + read_persistent_clock(&tmp); + timekeeping_suspend_time = timespec_to_timespec64(tmp); /* * On some systems the persistent_clock can not be detected at @@ -1004,7 +1213,7 @@ static int timekeeping_suspend(void) persistent_clock_exist = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; @@ -1014,8 +1223,8 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(tk_xtime(tk), timekeeping_suspend_time); - delta_delta = timespec_sub(delta, old_delta); + delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction @@ -1025,11 +1234,11 @@ static int timekeeping_suspend(void) } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = - timespec_add(timekeeping_suspend_time, delta_delta); + timespec64_add(timekeeping_suspend_time, delta_delta); } timekeeping_update(tk, TK_MIRROR); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); @@ -1050,125 +1259,34 @@ static int __init timekeeping_init_ops(void) register_syscore_ops(&timekeeping_syscore_ops); return 0; } - device_initcall(timekeeping_init_ops); /* - * If the error is already larger, we look ahead even further - * to compensate for late or lost adjustments. + * Apply a multiplier adjustment to the timekeeper */ -static __always_inline int timekeeping_bigadjust(struct timekeeper *tk, - s64 error, s64 *interval, - s64 *offset) +static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, + s64 offset, + bool negative, + int adj_scale) { - s64 tick_error, i; - u32 look_ahead, adj; - s32 error2, mult; - - /* - * Use the current error value to determine how much to look ahead. - * The larger the error the slower we adjust for it to avoid problems - * with losing too many ticks, otherwise we would overadjust and - * produce an even larger error. The smaller the adjustment the - * faster we try to adjust for it, as lost ticks can do less harm - * here. This is tuned so that an error of about 1 msec is adjusted - * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). - */ - error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); - error2 = abs(error2); - for (look_ahead = 0; error2 > 0; look_ahead++) - error2 >>= 2; + s64 interval = tk->cycle_interval; + s32 mult_adj = 1; - /* - * Now calculate the error in (1 << look_ahead) ticks, but first - * remove the single look ahead already included in the error. - */ - tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1); - tick_error -= tk->xtime_interval >> 1; - error = ((error - tick_error) >> look_ahead) + tick_error; - - /* Finally calculate the adjustment shift value. */ - i = *interval; - mult = 1; - if (error < 0) { - error = -error; - *interval = -*interval; - *offset = -*offset; - mult = -1; + if (negative) { + mult_adj = -mult_adj; + interval = -interval; + offset = -offset; } - for (adj = 0; error > i; adj++) - error >>= 1; - - *interval <<= adj; - *offset <<= adj; - return mult << adj; -} - -/* - * Adjust the multiplier to reduce the error value, - * this is optimized for the most common adjustments of -1,0,1, - * for other values we can do a bit more work. - */ -static void timekeeping_adjust(struct timekeeper *tk, s64 offset) -{ - s64 error, interval = tk->cycle_interval; - int adj; + mult_adj <<= adj_scale; + interval <<= adj_scale; + offset <<= adj_scale; /* - * The point of this is to check if the error is greater than half - * an interval. - * - * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs. - * - * Note we subtract one in the shift, so that error is really error*2. - * This "saves" dividing(shifting) interval twice, but keeps the - * (error > interval) comparison as still measuring if error is - * larger than half an interval. - * - * Note: It does not "save" on aggravation when reading the code. - */ - error = tk->ntp_error >> (tk->ntp_error_shift - 1); - if (error > interval) { - /* - * We now divide error by 4(via shift), which checks if - * the error is greater than twice the interval. - * If it is greater, we need a bigadjust, if its smaller, - * we can adjust by 1. - */ - error >>= 2; - if (likely(error <= interval)) - adj = 1; - else - adj = timekeeping_bigadjust(tk, error, &interval, &offset); - } else { - if (error < -interval) { - /* See comment above, this is just switched for the negative */ - error >>= 2; - if (likely(error >= -interval)) { - adj = -1; - interval = -interval; - offset = -offset; - } else { - adj = timekeeping_bigadjust(tk, error, &interval, &offset); - } - } else { - goto out_adjust; - } - } - - if (unlikely(tk->clock->maxadj && - (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) { - printk_deferred_once(KERN_WARNING - "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->clock->name, (long)tk->mult + adj, - (long)tk->clock->mult + tk->clock->maxadj); - } - /* * So the following can be confusing. * - * To keep things simple, lets assume adj == 1 for now. + * To keep things simple, lets assume mult_adj == 1 for now. * - * When adj != 1, remember that the interval and offset values + * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier @@ -1212,12 +1330,78 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * * XXX - TODO: Doc ntp_error calculation. */ - tk->mult += adj; + tk->tkr.mult += mult_adj; tk->xtime_interval += interval; - tk->xtime_nsec -= offset; + tk->tkr.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; +} + +/* + * Calculate the multiplier adjustment needed to match the frequency + * specified by NTP + */ +static __always_inline void timekeeping_freqadjust(struct timekeeper *tk, + s64 offset) +{ + s64 interval = tk->cycle_interval; + s64 xinterval = tk->xtime_interval; + s64 tick_error; + bool negative; + u32 adj; + + /* Remove any current error adj from freq calculation */ + if (tk->ntp_err_mult) + xinterval -= tk->cycle_interval; + + tk->ntp_tick = ntp_tick_length(); + + /* Calculate current error per tick */ + tick_error = ntp_tick_length() >> tk->ntp_error_shift; + tick_error -= (xinterval + tk->xtime_remainder); + + /* Don't worry about correcting it if its small */ + if (likely((tick_error >= 0) && (tick_error <= interval))) + return; + + /* preserve the direction of correction */ + negative = (tick_error < 0); + + /* Sort out the magnitude of the correction */ + tick_error = abs(tick_error); + for (adj = 0; tick_error > interval; adj++) + tick_error >>= 1; + + /* scale the corrections */ + timekeeping_apply_adjustment(tk, offset, negative, adj); +} + +/* + * Adjust the timekeeper's multiplier to the correct frequency + * and also to reduce the accumulated error value. + */ +static void timekeeping_adjust(struct timekeeper *tk, s64 offset) +{ + /* Correct for the current frequency error */ + timekeeping_freqadjust(tk, offset); + + /* Next make a small adjustment to fix any cumulative error */ + if (!tk->ntp_err_mult && (tk->ntp_error > 0)) { + tk->ntp_err_mult = 1; + timekeeping_apply_adjustment(tk, offset, 0, 0); + } else if (tk->ntp_err_mult && (tk->ntp_error <= 0)) { + /* Undo any existing error adjustment */ + timekeeping_apply_adjustment(tk, offset, 1, 0); + tk->ntp_err_mult = 0; + } + + if (unlikely(tk->tkr.clock->maxadj && + (tk->tkr.mult > tk->tkr.clock->mult + tk->tkr.clock->maxadj))) { + printk_once(KERN_WARNING + "Adjusting %s more than 11%% (%ld vs %ld)\n", + tk->tkr.clock->name, (long)tk->tkr.mult, + (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); + } -out_adjust: /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource @@ -1232,12 +1416,11 @@ out_adjust: * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)tk->xtime_nsec < 0)) { - s64 neg = -(s64)tk->xtime_nsec; - tk->xtime_nsec = 0; + if (unlikely((s64)tk->tkr.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr.xtime_nsec; + tk->tkr.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } - } /** @@ -1250,26 +1433,26 @@ out_adjust: */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { - u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift; unsigned int clock_set = 0; - while (tk->xtime_nsec >= nsecps) { + while (tk->tkr.xtime_nsec >= nsecps) { int leap; - tk->xtime_nsec -= nsecps; + tk->tkr.xtime_nsec -= nsecps; tk->xtime_sec++; /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { - struct timespec ts; + struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, - timespec_sub(tk->wall_to_monotonic, ts)); + timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); @@ -1301,9 +1484,9 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; - tk->cycle_last += interval; + tk->tkr.cycle_last += interval; - tk->xtime_nsec += tk->xtime_interval << shift; + tk->tkr.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ @@ -1317,48 +1500,20 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, tk->raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ - tk->ntp_error += ntp_tick_length() << shift; + tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } -#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD -static inline void old_vsyscall_fixup(struct timekeeper *tk) -{ - s64 remainder; - - /* - * Store only full nanoseconds into xtime_nsec after rounding - * it up and add the remainder to the error difference. - * XXX - This is necessary to avoid small 1ns inconsistnecies caused - * by truncating the remainder in vsyscalls. However, it causes - * additional work to be done in timekeeping_adjust(). Once - * the vsyscall implementations are converted to use xtime_nsec - * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD - * users are removed, this can be killed. - */ - remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); - tk->xtime_nsec -= remainder; - tk->xtime_nsec += 1ULL << tk->shift; - tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift; -} -#else -#define old_vsyscall_fixup(tk) -#endif - - - /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { - struct clocksource *clock; - struct timekeeper *real_tk = &timekeeper; + struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; cycle_t offset; int shift = 0, maxshift; @@ -1371,12 +1526,11 @@ void update_wall_time(void) if (unlikely(timekeeping_suspended)) goto out; - clock = real_tk->clock; - #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = (clock->read(clock) - clock->cycle_last) & clock->mask; + offset = clocksource_delta(tk->tkr.read(tk->tkr.clock), + tk->tkr.cycle_last, tk->tkr.mask); #endif /* Check if there's really nothing to do */ @@ -1418,9 +1572,7 @@ void update_wall_time(void) */ clock_set |= accumulate_nsecs_to_secs(tk); - write_seqcount_begin(&timekeeper_seq); - /* Update clock->cycle_last with the new value */ - clock->cycle_last = tk->cycle_last; + write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * @@ -1428,12 +1580,12 @@ void update_wall_time(void) * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this - * memcpy under the timekeeper_seq against one before we start + * memcpy under the tk_core.seq against one before we start * updating. */ memcpy(real_tk, tk, sizeof(*tk)); timekeeping_update(real_tk, clock_set); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) @@ -1454,83 +1606,16 @@ out: */ void getboottime(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; - struct timespec boottime = { - .tv_sec = tk->wall_to_monotonic.tv_sec + - tk->total_sleep_time.tv_sec, - .tv_nsec = tk->wall_to_monotonic.tv_nsec + - tk->total_sleep_time.tv_nsec - }; - - set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); -} -EXPORT_SYMBOL_GPL(getboottime); - -/** - * get_monotonic_boottime - Returns monotonic time since boot - * @ts: pointer to the timespec to be set - * - * Returns the monotonic time since boot in a timespec. - * - * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also - * includes the time spent in suspend. - */ -void get_monotonic_boottime(struct timespec *ts) -{ - struct timekeeper *tk = &timekeeper; - struct timespec tomono, sleep; - s64 nsec; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(tk); - tomono = tk->wall_to_monotonic; - sleep = tk->total_sleep_time; - - } while (read_seqcount_retry(&timekeeper_seq, seq)); - - ts->tv_sec += tomono.tv_sec + sleep.tv_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec); -} -EXPORT_SYMBOL_GPL(get_monotonic_boottime); - -/** - * ktime_get_boottime - Returns monotonic time since boot in a ktime - * - * Returns the monotonic time since boot in a ktime - * - * This is similar to CLOCK_MONTONIC/ktime_get, but also - * includes the time spent in suspend. - */ -ktime_t ktime_get_boottime(void) -{ - struct timespec ts; - - get_monotonic_boottime(&ts); - return timespec_to_ktime(ts); -} -EXPORT_SYMBOL_GPL(ktime_get_boottime); - -/** - * monotonic_to_bootbased - Convert the monotonic time to boot based. - * @ts: pointer to the timespec to be converted - */ -void monotonic_to_bootbased(struct timespec *ts) -{ - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; + ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); - *ts = timespec_add(*ts, tk->total_sleep_time); + *ts = ktime_to_timespec(t); } -EXPORT_SYMBOL_GPL(monotonic_to_bootbased); +EXPORT_SYMBOL_GPL(getboottime); unsigned long get_seconds(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } @@ -1538,43 +1623,44 @@ EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; - return tk_xtime(tk); + return timespec64_to_timespec(tk_xtime(tk)); } struct timespec current_kernel_time(void) { - struct timekeeper *tk = &timekeeper; - struct timespec now; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 now; unsigned long seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - return now; + return timespec64_to_timespec(now); } EXPORT_SYMBOL(current_kernel_time); struct timespec get_monotonic_coarse(void) { - struct timekeeper *tk = &timekeeper; - struct timespec now, mono; + struct timekeeper *tk = &tk_core.timekeeper; + struct timespec64 now, mono; unsigned long seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, + set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); - return now; + + return timespec64_to_timespec(now); } /* @@ -1587,29 +1673,38 @@ void do_timer(unsigned long ticks) } /** - * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic, - * and sleep offsets. - * @xtim: pointer to timespec to be set with xtime - * @wtom: pointer to timespec to be set with wall_to_monotonic - * @sleep: pointer to timespec to be set with time in suspend + * ktime_get_update_offsets_tick - hrtimer helper + * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset + * @offs_tai: pointer to storage for monotonic -> clock tai offset + * + * Returns monotonic time at last tick and various offsets */ -void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, - struct timespec *wtom, struct timespec *sleep) +ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, + ktime_t *offs_tai) { - struct timekeeper *tk = &timekeeper; - unsigned long seq; + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + u64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); - *xtim = tk_xtime(tk); - *wtom = tk->wall_to_monotonic; - *sleep = tk->total_sleep_time; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + seq = read_seqcount_begin(&tk_core.seq); + + base = tk->tkr.base_mono; + nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift; + + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + *offs_tai = tk->offs_tai; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); } #ifdef CONFIG_HIGH_RES_TIMERS /** - * ktime_get_update_offsets - hrtimer helper + * ktime_get_update_offsets_now - hrtimer helper * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset @@ -1617,57 +1712,37 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, * Returns current monotonic time and updates the offsets * Called from hrtimer_interrupt() or retrigger_next_event() */ -ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot, +ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { - struct timekeeper *tk = &timekeeper; - ktime_t now; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; - u64 secs, nsecs; + ktime_t base; + u64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); - secs = tk->xtime_sec; - nsecs = timekeeping_get_ns(tk); + base = tk->tkr.base_mono; + nsecs = timekeeping_get_ns(&tk->tkr); *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); - now = ktime_add_ns(ktime_set(secs, 0), nsecs); - now = ktime_sub(now, *offs_real); - return now; + return ktime_add_ns(base, nsecs); } #endif /** - * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format - */ -ktime_t ktime_get_monotonic_offset(void) -{ - struct timekeeper *tk = &timekeeper; - unsigned long seq; - struct timespec wtom; - - do { - seq = read_seqcount_begin(&timekeeper_seq); - wtom = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); - - return timespec_to_ktime(wtom); -} -EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); - -/** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct timex *txc) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - struct timespec ts; + struct timespec64 ts; s32 orig_tai, tai; int ret; @@ -1687,10 +1762,10 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday(&ts); + getnstimeofday64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai); @@ -1699,7 +1774,7 @@ int do_adjtimex(struct timex *txc) __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (tai != orig_tai) @@ -1719,11 +1794,11 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h new file mode 100644 index 000000000000..adc1fc98bde3 --- /dev/null +++ b/kernel/time/timekeeping.h @@ -0,0 +1,20 @@ +#ifndef _KERNEL_TIME_TIMEKEEPING_H +#define _KERNEL_TIME_TIMEKEEPING_H +/* + * Internal interfaces for kernel/time/ + */ +extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); +extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); + +extern int timekeeping_valid_for_hres(void); +extern u64 timekeeping_max_deferment(void); +extern int timekeeping_inject_offset(struct timespec *ts); +extern s32 timekeeping_get_tai_offset(void); +extern void timekeeping_set_tai_offset(s32 tai_offset); +extern void timekeeping_clocktai(struct timespec *ts); + +#endif diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 4d54f97558df..f6bd65236712 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -67,7 +67,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec *t) +void tk_debug_account_sleep_time(struct timespec64 *t) { sleep_time_bin[fls(t->tv_sec)]++; } diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 13323ea08ffa..4ea005a7f9da 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -3,12 +3,27 @@ /* * timekeeping debug functions */ +#include <linux/clocksource.h> #include <linux/time.h> #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec *t); +extern void tk_debug_account_sleep_time(struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif +#ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE +static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask) +{ + cycle_t ret = (now - last) & mask; + + return (s64) ret > 0 ? ret : 0; +} +#else +static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask) +{ + return (now - last) & mask; +} +#endif + #endif /* _TIMEKEEPING_INTERNAL_H */ diff --git a/kernel/timer.c b/kernel/time/timer.c index 3bb01a323b2a..aca5dfe2fa3d 100644 --- a/kernel/timer.c +++ b/kernel/time/timer.c @@ -82,6 +82,7 @@ struct tvec_base { unsigned long next_timer; unsigned long active_timers; unsigned long all_timers; + int cpu; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -409,6 +410,22 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) base->next_timer = timer->expires; } base->all_timers++; + + /* + * Check whether the other CPU is in dynticks mode and needs + * to be triggered to reevaluate the timer wheel. + * We are protected against the other CPU fiddling + * with the timer by holding the timer base lock. This also + * makes sure that a CPU on the way to stop its tick can not + * evaluate the timer wheel. + * + * Spare the IPI for deferrable timers on idle targets though. + * The next busy ticks will take care of it. Except full dynticks + * require special care against races with idle_cpu(), lets deal + * with that later. + */ + if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu)) + wake_up_nohz_cpu(base->cpu); } #ifdef CONFIG_TIMER_STATS @@ -948,22 +965,6 @@ void add_timer_on(struct timer_list *timer, int cpu) timer_set_base(timer, base); debug_activate(timer, timer->expires); internal_add_timer(base, timer); - /* - * Check whether the other CPU is in dynticks mode and needs - * to be triggered to reevaluate the timer wheel. - * We are protected against the other CPU fiddling - * with the timer by holding the timer base lock. This also - * makes sure that a CPU on the way to stop its tick can not - * evaluate the timer wheel. - * - * Spare the IPI for deferrable timers on idle targets though. - * The next busy ticks will take care of it. Except full dynticks - * require special care against races with idle_cpu(), lets deal - * with that later. - */ - if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu)) - wake_up_nohz_cpu(cpu); - spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); @@ -1568,6 +1569,7 @@ static int init_timers_cpu(int cpu) } spin_lock_init(&base->lock); tvec_base_done[cpu] = 1; + base->cpu = cpu; } else { base = per_cpu(tvec_bases, cpu); } diff --git a/kernel/time/udelay_test.c b/kernel/time/udelay_test.c new file mode 100644 index 000000000000..e622ba365a13 --- /dev/null +++ b/kernel/time/udelay_test.c @@ -0,0 +1,168 @@ +/* + * udelay() test kernel module + * + * Test is executed by writing and reading to /sys/kernel/debug/udelay_test + * Tests are configured by writing: USECS ITERATIONS + * Tests are executed by reading from the same file. + * Specifying usecs of 0 or negative values will run multiples tests. + * + * Copyright (C) 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/ktime.h> +#include <linux/module.h> +#include <linux/uaccess.h> + +#define DEFAULT_ITERATIONS 100 + +#define DEBUGFS_FILENAME "udelay_test" + +static DEFINE_MUTEX(udelay_test_lock); +static struct dentry *udelay_test_debugfs_file; +static int udelay_test_usecs; +static int udelay_test_iterations = DEFAULT_ITERATIONS; + +static int udelay_test_single(struct seq_file *s, int usecs, uint32_t iters) +{ + int min = 0, max = 0, fail_count = 0; + uint64_t sum = 0; + uint64_t avg; + int i; + /* Allow udelay to be up to 0.5% fast */ + int allowed_error_ns = usecs * 5; + + for (i = 0; i < iters; ++i) { + struct timespec ts1, ts2; + int time_passed; + + ktime_get_ts(&ts1); + udelay(usecs); + ktime_get_ts(&ts2); + time_passed = timespec_to_ns(&ts2) - timespec_to_ns(&ts1); + + if (i == 0 || time_passed < min) + min = time_passed; + if (i == 0 || time_passed > max) + max = time_passed; + if ((time_passed + allowed_error_ns) / 1000 < usecs) + ++fail_count; + WARN_ON(time_passed < 0); + sum += time_passed; + } + + avg = sum; + do_div(avg, iters); + seq_printf(s, "%d usecs x %d: exp=%d allowed=%d min=%d avg=%lld max=%d", + usecs, iters, usecs * 1000, + (usecs * 1000) - allowed_error_ns, min, avg, max); + if (fail_count) + seq_printf(s, " FAIL=%d", fail_count); + seq_puts(s, "\n"); + + return 0; +} + +static int udelay_test_show(struct seq_file *s, void *v) +{ + int usecs; + int iters; + int ret = 0; + + mutex_lock(&udelay_test_lock); + usecs = udelay_test_usecs; + iters = udelay_test_iterations; + mutex_unlock(&udelay_test_lock); + + if (usecs > 0 && iters > 0) { + return udelay_test_single(s, usecs, iters); + } else if (usecs == 0) { + struct timespec ts; + + ktime_get_ts(&ts); + seq_printf(s, "udelay() test (lpj=%ld kt=%ld.%09ld)\n", + loops_per_jiffy, ts.tv_sec, ts.tv_nsec); + seq_puts(s, "usage:\n"); + seq_puts(s, "echo USECS [ITERS] > " DEBUGFS_FILENAME "\n"); + seq_puts(s, "cat " DEBUGFS_FILENAME "\n"); + } + + return ret; +} + +static int udelay_test_open(struct inode *inode, struct file *file) +{ + return single_open(file, udelay_test_show, inode->i_private); +} + +static ssize_t udelay_test_write(struct file *file, const char __user *buf, + size_t count, loff_t *pos) +{ + char lbuf[32]; + int ret; + int usecs; + int iters; + + if (count >= sizeof(lbuf)) + return -EINVAL; + + if (copy_from_user(lbuf, buf, count)) + return -EFAULT; + lbuf[count] = '\0'; + + ret = sscanf(lbuf, "%d %d", &usecs, &iters); + if (ret < 1) + return -EINVAL; + else if (ret < 2) + iters = DEFAULT_ITERATIONS; + + mutex_lock(&udelay_test_lock); + udelay_test_usecs = usecs; + udelay_test_iterations = iters; + mutex_unlock(&udelay_test_lock); + + return count; +} + +static const struct file_operations udelay_test_debugfs_ops = { + .owner = THIS_MODULE, + .open = udelay_test_open, + .read = seq_read, + .write = udelay_test_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init udelay_test_init(void) +{ + mutex_lock(&udelay_test_lock); + udelay_test_debugfs_file = debugfs_create_file(DEBUGFS_FILENAME, + S_IRUSR, NULL, NULL, &udelay_test_debugfs_ops); + mutex_unlock(&udelay_test_lock); + + return 0; +} + +module_init(udelay_test_init); + +static void __exit udelay_test_exit(void) +{ + mutex_lock(&udelay_test_lock); + debugfs_remove(udelay_test_debugfs_file); + mutex_unlock(&udelay_test_lock); +} + +module_exit(udelay_test_exit); + +MODULE_AUTHOR("David Riley <davidriley@chromium.org>"); +MODULE_LICENSE("GPL"); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8bb80fe08767..8a528392b1f4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -820,11 +820,12 @@ static struct { const char *name; int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { - { trace_clock_local, "local", 1 }, - { trace_clock_global, "global", 1 }, - { trace_clock_counter, "counter", 0 }, - { trace_clock_jiffies, "uptime", 0 }, - { trace_clock, "perf", 1 }, + { trace_clock_local, "local", 1 }, + { trace_clock_global, "global", 1 }, + { trace_clock_counter, "counter", 0 }, + { trace_clock_jiffies, "uptime", 0 }, + { trace_clock, "perf", 1 }, + { ktime_get_mono_fast_ns, "mono", 1 }, ARCH_TRACE_CLOCKS }; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index a1dd9a1b1327..975cb49e32bf 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -31,20 +31,19 @@ void bacct_add_tsk(struct user_namespace *user_ns, struct taskstats *stats, struct task_struct *tsk) { const struct cred *tcred; - struct timespec uptime, ts; cputime_t utime, stime, utimescaled, stimescaled; - u64 ac_etime; + u64 delta; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); - /* calculate task elapsed time in timespec */ - do_posix_clock_monotonic_gettime(&uptime); - ts = timespec_sub(uptime, tsk->start_time); - /* rebase elapsed time to usec (should never be negative) */ - ac_etime = timespec_to_ns(&ts); - do_div(ac_etime, NSEC_PER_USEC); - stats->ac_etime = ac_etime; - stats->ac_btime = get_seconds() - ts.tv_sec; + /* calculate task elapsed time in nsec */ + delta = ktime_get_ns() - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime = delta; + /* Convert to seconds for btime */ + do_div(delta, USEC_PER_SEC); + stats->ac_btime = get_seconds() - delta; if (thread_group_leader(tsk)) { stats->ac_exitcode = tsk->exit_code; if (tsk->flags & PF_FORKNOEXEC) |