Merge commit 'ccbf62d8a284cf181ac28c8e8407dd077d90dd4b' into for-next

backmerge to avoid kernel/acct.c conflict

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

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

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];

kernel/delayacct.c

@@ -45,16 +45,6 @@ void __delayacct_tsk_init(struct task_struct *tsk)
 		spin_lock_init(&tsk->delays->lock);
 }
 
-/*
- * Start accounting for a delay statistic using
- * its starting timestamp (@start)
- */
-
-static inline void delayacct_start(struct timespec *start)
-{
-	do_posix_clock_monotonic_gettime(start);
-}
-
 /*
  * Finish delay accounting for a statistic using
  * its timestamps (@start, @end), accumalator (@total) and @count
@@ -67,7 +57,7 @@ static void delayacct_end(struct timespec *start, struct timespec *end,
 	s64 ns;
 	unsigned long flags;
 
-	do_posix_clock_monotonic_gettime(end);
+	ktime_get_ts(end);
 	ts = timespec_sub(*end, *start);
 	ns = timespec_to_ns(&ts);
 	if (ns < 0)
@@ -81,7 +71,7 @@ static void delayacct_end(struct timespec *start, struct timespec *end,
 
 void __delayacct_blkio_start(void)
 {
-	delayacct_start(&current->delays->blkio_start);
+	ktime_get_ts(&current->delays->blkio_start);
 }
 
 void __delayacct_blkio_end(void)
@@ -169,7 +159,7 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
 
 void __delayacct_freepages_start(void)
 {
-	delayacct_start(&current->delays->freepages_start);
+	ktime_get_ts(&current->delays->freepages_start);
 }
 
 void __delayacct_freepages_end(void)

kernel/fork.c

@@ -1262,9 +1262,8 @@ 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)

kernel/time/Kconfig

@@ -20,10 +20,6 @@ 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

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)
+

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);
 }
 

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;

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 */

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.

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

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.

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

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)]++;
 }

kernel/time/timekeeping_internal.h

@@ -6,7 +6,7 @@
 #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

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);
 	}

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");

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)