Merge branch 'fortglx/3.10/time' of git://git.linaro.org/people/jstultz/linux into timers/core

kernel/hrtimer.c

@@ -83,6 +83,12 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get_boottime,
 			.resolution = KTIME_LOW_RES,
 		},
+		{
+			.index = HRTIMER_BASE_TAI,
+			.clockid = CLOCK_TAI,
+			.get_time = &ktime_get_clocktai,
+			.resolution = KTIME_LOW_RES,
+		},
 	}
 };
 
@@ -90,6 +96,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
+	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
@@ -106,8 +113,10 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
 	ktime_t xtim, mono, boot;
 	struct timespec xts, tom, slp;
+	s32 tai_offset;
 
 	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
+	tai_offset = timekeeping_get_tai_offset();
 
 	xtim = timespec_to_ktime(xts);
 	mono = ktime_add(xtim, timespec_to_ktime(tom));
@@ -115,6 +124,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 	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));
 }
 
 /*
@@ -651,8 +662,9 @@ 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);
+	return ktime_get_update_offsets(offs_real, offs_boot, offs_tai);
 }
 
 /*

kernel/posix-timers.c

@@ -221,6 +221,11 @@ static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
+{
+	timekeeping_clocktai(tp);
+	return 0;
+}
 
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
@@ -261,6 +266,16 @@ static __init int init_posix_timers(void)
 		.clock_getres	= posix_get_coarse_res,
 		.clock_get	= posix_get_monotonic_coarse,
 	};
+	struct k_clock clock_tai = {
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_get_tai,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
+	};
 	struct k_clock clock_boottime = {
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_get_boottime,
@@ -278,6 +293,7 @@ static __init int init_posix_timers(void)
 	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
 	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
 	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
+	posix_timers_register_clock(CLOCK_TAI, &clock_tai);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,

kernel/time.c

@@ -138,13 +138,14 @@ int persistent_clock_is_local;
  */
 static inline void warp_clock(void)
 {
-	struct timespec adjust;
+	if (sys_tz.tz_minuteswest != 0) {
+		struct timespec adjust;
 
-	adjust = current_kernel_time();
-	if (sys_tz.tz_minuteswest != 0)
 		persistent_clock_is_local = 1;
-	adjust.tv_sec += sys_tz.tz_minuteswest * 60;
-	do_settimeofday(&adjust);
+		adjust.tv_sec = sys_tz.tz_minuteswest * 60;
+		adjust.tv_nsec = 0;
+		timekeeping_inject_offset(&adjust);
+	}
 }
 
 /*

kernel/time/ntp.c

@@ -53,9 +53,6 @@ static int			time_state = TIME_OK;
 /* clock status bits:							*/
 static int			time_status = STA_UNSYNC;
 
-/* TAI offset (secs):							*/
-static long			time_tai;
-
 /* time adjustment (nsecs):						*/
 static s64			time_offset;
 
@@ -415,7 +412,6 @@ int second_overflow(unsigned long secs)
 		else if (secs % 86400 == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
-			time_tai++;
 			printk(KERN_NOTICE
 				"Clock: inserting leap second 23:59:60 UTC\n");
 		}
@@ -425,7 +421,6 @@ int second_overflow(unsigned long secs)
 			time_state = TIME_OK;
 		else if ((secs + 1) % 86400 == 0) {
 			leap = 1;
-			time_tai--;
 			time_state = TIME_WAIT;
 			printk(KERN_NOTICE
 				"Clock: deleting leap second 23:59:59 UTC\n");
@@ -579,7 +574,9 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
  * Called with ntp_lock held, so we can access and modify
  * all the global NTP state:
  */
-static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts)
+static inline void process_adjtimex_modes(struct timex *txc,
+						struct timespec *ts,
+						s32 *time_tai)
 {
 	if (txc->modes & ADJ_STATUS)
 		process_adj_status(txc, ts);
@@ -613,7 +610,7 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
 	}
 
 	if (txc->modes & ADJ_TAI && txc->constant > 0)
-		time_tai = txc->constant;
+		*time_tai = txc->constant;
 
 	if (txc->modes & ADJ_OFFSET)
 		ntp_update_offset(txc->offset);
@@ -632,6 +629,7 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
 int do_adjtimex(struct timex *txc)
 {
 	struct timespec ts;
+	u32 time_tai, orig_tai;
 	int result;
 
 	/* Validate the data before disabling interrupts */
@@ -671,6 +669,7 @@ int do_adjtimex(struct timex *txc)
 	}
 
 	getnstimeofday(&ts);
+	orig_tai = time_tai = timekeeping_get_tai_offset();
 
 	raw_spin_lock_irq(&ntp_lock);
 
@@ -687,7 +686,7 @@ int do_adjtimex(struct timex *txc)
 
 		/* If there are input parameters, then process them: */
 		if (txc->modes)
-			process_adjtimex_modes(txc, &ts);
+			process_adjtimex_modes(txc, &ts, &time_tai);
 
 		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
@@ -716,6 +715,9 @@ int do_adjtimex(struct timex *txc)
 
 	raw_spin_unlock_irq(&ntp_lock);
 
+	if (time_tai != orig_tai)
+		timekeeping_set_tai_offset(time_tai);
+
 	txc->time.tv_sec = ts.tv_sec;
 	txc->time.tv_usec = ts.tv_nsec;
 	if (!(time_status & STA_NANO))

kernel/time/tick-internal.h

@@ -4,6 +4,8 @@
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
 
+extern seqlock_t jiffies_lock;
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
 
 #define TICK_DO_TIMER_NONE	-1

kernel/time/timekeeping.c

@@ -23,8 +23,11 @@
 #include <linux/stop_machine.h>
 #include <linux/pvclock_gtod.h>
 
+#include "tick-internal.h"
 
 static struct timekeeper timekeeper;
+static DEFINE_RAW_SPINLOCK(timekeeper_lock);
+static seqcount_t timekeeper_seq;
 
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
@@ -67,6 +70,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
 	tk->wall_to_monotonic = wtm;
 	set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
 	tk->offs_real = timespec_to_ktime(tmp);
+	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
 }
 
 static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -201,8 +205,6 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 
 /**
  * pvclock_gtod_register_notifier - register a pvclock timedata update listener
- *
- * Must hold write on timekeeper.lock
  */
 int pvclock_gtod_register_notifier(struct notifier_block *nb)
 {
@@ -210,11 +212,10 @@ int pvclock_gtod_register_notifier(struct notifier_block *nb)
 	unsigned long flags;
 	int ret;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
-	/* update timekeeping data */
 	update_pvclock_gtod(tk);
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	return ret;
 }
@@ -223,24 +224,21 @@ EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
 /**
  * pvclock_gtod_unregister_notifier - unregister a pvclock
  * timedata update listener
- *
- * Must hold write on timekeeper.lock
  */
 int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
 {
-	struct timekeeper *tk = &timekeeper;
 	unsigned long flags;
 	int ret;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
 
-/* must hold write on timekeeper.lock */
+/* must hold timekeeper_lock */
 static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 {
 	if (clearntp) {
@@ -294,12 +292,12 @@ int __getnstimeofday(struct timespec *ts)
 	s64 nsecs = 0;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		ts->tv_sec = tk->xtime_sec;
 		nsecs = timekeeping_get_ns(tk);
 
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	ts->tv_nsec = 0;
 	timespec_add_ns(ts, nsecs);
@@ -335,11 +333,11 @@ ktime_t ktime_get(void)
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		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;
 
-	} while (read_seqretry(&tk->lock, seq));
+	} 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.
@@ -366,12 +364,12 @@ void ktime_get_ts(struct timespec *ts)
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 		ts->tv_sec = tk->xtime_sec;
 		nsec = timekeeping_get_ns(tk);
 		tomono = tk->wall_to_monotonic;
 
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	ts->tv_sec += tomono.tv_sec;
 	ts->tv_nsec = 0;
@@ -379,6 +377,50 @@ void ktime_get_ts(struct timespec *ts)
 }
 EXPORT_SYMBOL_GPL(ktime_get_ts);
 
+
+/**
+ * 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.
+ */
+void timekeeping_clocktai(struct timespec *ts)
+{
+	struct timekeeper *tk = &timekeeper;
+	unsigned long seq;
+	u64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&timekeeper_seq);
+
+		ts->tv_sec = tk->xtime_sec + tk->tai_offset;
+		nsecs = timekeeping_get_ns(tk);
+
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
+
+	ts->tv_nsec = 0;
+	timespec_add_ns(ts, nsecs);
+
+}
+EXPORT_SYMBOL(timekeeping_clocktai);
+
+
+/**
+ * ktime_get_clocktai - Returns the TAI time of day in a ktime
+ *
+ * Returns the time of day in a ktime.
+ */
+ktime_t ktime_get_clocktai(void)
+{
+	struct timespec ts;
+
+	timekeeping_clocktai(&ts);
+	return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL(ktime_get_clocktai);
+
 #ifdef CONFIG_NTP_PPS
 
 /**
@@ -399,7 +441,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 	WARN_ON_ONCE(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		*ts_raw = tk->raw_time;
 		ts_real->tv_sec = tk->xtime_sec;
@@ -408,7 +450,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 		nsecs_raw = timekeeping_get_ns_raw(tk);
 		nsecs_real = timekeeping_get_ns(tk);
 
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	timespec_add_ns(ts_raw, nsecs_raw);
 	timespec_add_ns(ts_real, nsecs_real);
@@ -448,7 +490,8 @@ int do_settimeofday(const struct timespec *tv)
 	if (!timespec_valid_strict(tv))
 		return -EINVAL;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 
 	timekeeping_forward_now(tk);
 
@@ -462,7 +505,8 @@ int do_settimeofday(const struct timespec *tv)
 
 	timekeeping_update(tk, true);
 
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
@@ -487,7 +531,8 @@ int timekeeping_inject_offset(struct timespec *ts)
 	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 
 	timekeeping_forward_now(tk);
 
@@ -504,7 +549,8 @@ int timekeeping_inject_offset(struct timespec *ts)
 error: /* even if we error out, we forwarded the time, so call update */
 	timekeeping_update(tk, true);
 
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
@@ -513,6 +559,51 @@ error: /* even if we error out, we forwarded the time, so call update */
 }
 EXPORT_SYMBOL(timekeeping_inject_offset);
 
+
+/**
+ * timekeeping_get_tai_offset - Returns current TAI offset from UTC
+ *
+ */
+s32 timekeeping_get_tai_offset(void)
+{
+	struct timekeeper *tk = &timekeeper;
+	unsigned int seq;
+	s32 ret;
+
+	do {
+		seq = read_seqcount_begin(&timekeeper_seq);
+		ret = tk->tai_offset;
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
+
+	return ret;
+}
+
+/**
+ * __timekeeping_set_tai_offset - Lock free worker function
+ *
+ */
+static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
+{
+	tk->tai_offset = tai_offset;
+	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+}
+
+/**
+ * timekeeping_set_tai_offset - Sets the current TAI offset from UTC
+ *
+ */
+void timekeeping_set_tai_offset(s32 tai_offset)
+{
+	struct timekeeper *tk = &timekeeper;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
+	__timekeeping_set_tai_offset(tk, tai_offset);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+}
+
 /**
  * change_clocksource - Swaps clocksources if a new one is available
  *
@@ -526,7 +617,8 @@ static int change_clocksource(void *data)
 
 	new = (struct clocksource *) data;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 
 	timekeeping_forward_now(tk);
 	if (!new->enable || new->enable(new) == 0) {
@@ -537,7 +629,8 @@ static int change_clocksource(void *data)
 	}
 	timekeeping_update(tk, true);
 
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	return 0;
 }
@@ -587,11 +680,11 @@ void getrawmonotonic(struct timespec *ts)
 	s64 nsecs;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 		nsecs = timekeeping_get_ns_raw(tk);
 		*ts = tk->raw_time;
 
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	timespec_add_ns(ts, nsecs);
 }
@@ -607,11 +700,11 @@ int timekeeping_valid_for_hres(void)
 	int ret;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	return ret;
 }
@@ -626,11 +719,11 @@ u64 timekeeping_max_deferment(void)
 	u64 ret;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		ret = tk->clock->max_idle_ns;
 
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	return ret;
 }
@@ -693,11 +786,10 @@ void __init timekeeping_init(void)
 		boot.tv_nsec = 0;
 	}
 
-	seqlock_init(&tk->lock);
-
 	ntp_init();
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 	clock = clocksource_default_clock();
 	if (clock->enable)
 		clock->enable(clock);
@@ -716,7 +808,8 @@ void __init timekeeping_init(void)
 	tmp.tv_nsec = 0;
 	tk_set_sleep_time(tk, tmp);
 
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 }
 
 /* time in seconds when suspend began */
@@ -764,7 +857,8 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 	if (has_persistent_clock())
 		return;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 
 	timekeeping_forward_now(tk);
 
@@ -772,7 +866,8 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 
 	timekeeping_update(tk, true);
 
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
@@ -788,26 +883,72 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 static void timekeeping_resume(void)
 {
 	struct timekeeper *tk = &timekeeper;
+	struct clocksource *clock = tk->clock;
 	unsigned long flags;
-	struct timespec ts;
+	struct timespec ts_new, ts_delta;
+	cycle_t cycle_now, cycle_delta;
+	bool suspendtime_found = false;
 
-	read_persistent_clock(&ts);
+	read_persistent_clock(&ts_new);
 
 	clockevents_resume();
 	clocksource_resume();
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 
-	if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
-		ts = timespec_sub(ts, timekeeping_suspend_time);
-		__timekeeping_inject_sleeptime(tk, &ts);
+	/*
+	 * After system resumes, we need to calculate the suspended time and
+	 * compensate it for the OS time. There are 3 sources that could be
+	 * used: Nonstop clocksource during suspend, persistent clock and rtc
+	 * device.
+	 *
+	 * One specific platform may have 1 or 2 or all of them, and the
+	 * preference will be:
+	 *	suspend-nonstop clocksource -> persistent clock -> rtc
+	 * 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);
+	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
+		cycle_now > clock->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 * mutl" may cause 64 bits overflow, if the
+		 * suspended time is too long. In that case we need do the
+		 * 64 bits math carefully
+		 */
+		do_div(max, mult);
+		if (cycle_delta > max) {
+			num = div64_u64(cycle_delta, max);
+			nsec = (((u64) max * mult) >> shift) * num;
+			cycle_delta -= num * max;
+		}
+		nsec += ((u64) cycle_delta * mult) >> shift;
+
+		ts_delta = ns_to_timespec(nsec);
+		suspendtime_found = true;
+	} else if (timespec_compare(&ts_new, &timekeeping_suspend_time) > 0) {
+		ts_delta = timespec_sub(ts_new, timekeeping_suspend_time);
+		suspendtime_found = true;
 	}
-	/* re-base the last cycle value */
-	tk->clock->cycle_last = tk->clock->read(tk->clock);
+
+	if (suspendtime_found)
+		__timekeeping_inject_sleeptime(tk, &ts_delta);
+
+	/* Re-base the last cycle value */
+	clock->cycle_last = cycle_now;
 	tk->ntp_error = 0;
 	timekeeping_suspended = 0;
 	timekeeping_update(tk, false);
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	touch_softlockup_watchdog();
 
@@ -826,7 +967,8 @@ static int timekeeping_suspend(void)
 
 	read_persistent_clock(&timekeeping_suspend_time);
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
@@ -849,7 +991,8 @@ static int timekeeping_suspend(void)
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
 	clocksource_suspend();
@@ -1099,6 +1242,8 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
 			tk_set_wall_to_mono(tk,
 				timespec_sub(tk->wall_to_monotonic, ts));
 
+			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
+
 			clock_was_set_delayed();
 		}
 	}
@@ -1116,15 +1261,16 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 						u32 shift)
 {
+	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
 
 	/* If the offset is smaller then a shifted interval, do nothing */
-	if (offset < tk->cycle_interval<<shift)
+	if (offset < interval)
 		return offset;
 
 	/* Accumulate one shifted interval */
-	offset -= tk->cycle_interval << shift;
-	tk->clock->cycle_last += tk->cycle_interval << shift;
+	offset -= interval;
+	tk->clock->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
 	accumulate_nsecs_to_secs(tk);
@@ -1186,7 +1332,8 @@ static void update_wall_time(void)
 	int shift = 0, maxshift;
 	unsigned long flags;
 
-	write_seqlock_irqsave(&tk->lock, flags);
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	write_seqcount_begin(&timekeeper_seq);
 
 	/* Make sure we're fully resumed: */
 	if (unlikely(timekeeping_suspended))
@@ -1241,7 +1388,8 @@ static void update_wall_time(void)
 	timekeeping_update(tk, false);
 
 out:
-	write_sequnlock_irqrestore(&tk->lock, flags);
+	write_seqcount_end(&timekeeper_seq);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
 }
 
@@ -1289,13 +1437,13 @@ void get_monotonic_boottime(struct timespec *ts)
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		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_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	ts->tv_sec += tomono.tv_sec + sleep.tv_sec;
 	ts->tv_nsec = 0;
@@ -1354,10 +1502,10 @@ struct timespec current_kernel_time(void)
 	unsigned long seq;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		now = tk_xtime(tk);
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	return now;
 }
@@ -1370,11 +1518,11 @@ struct timespec get_monotonic_coarse(void)
 	unsigned long seq;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		now = tk_xtime(tk);
 		mono = tk->wall_to_monotonic;
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
 				now.tv_nsec + mono.tv_nsec);
@@ -1405,11 +1553,11 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
 	unsigned long seq;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 		*xtim = tk_xtime(tk);
 		*wtom = tk->wall_to_monotonic;
 		*sleep = tk->total_sleep_time;
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 }
 
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -1421,7 +1569,8 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
  * Returns current monotonic time and updates the offsets
  * Called from hrtimer_interupt() or retrigger_next_event()
  */
-ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
+ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot,
+							ktime_t *offs_tai)
 {
 	struct timekeeper *tk = &timekeeper;
 	ktime_t now;
@@ -1429,14 +1578,15 @@ ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
 	u64 secs, nsecs;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 
 		secs = tk->xtime_sec;
 		nsecs = timekeeping_get_ns(tk);
 
 		*offs_real = tk->offs_real;
 		*offs_boot = tk->offs_boot;
-	} while (read_seqretry(&tk->lock, seq));
+		*offs_tai = tk->offs_tai;
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
 	now = ktime_sub(now, *offs_real);
@@ -1454,9 +1604,9 @@ ktime_t ktime_get_monotonic_offset(void)
 	struct timespec wtom;
 
 	do {
-		seq = read_seqbegin(&tk->lock);
+		seq = read_seqcount_begin(&timekeeper_seq);
 		wtom = tk->wall_to_monotonic;
-	} while (read_seqretry(&tk->lock, seq));
+	} while (read_seqcount_retry(&timekeeper_seq, seq));
 
 	return timespec_to_ktime(wtom);
 }

kernel/trace/Kconfig

@@ -414,24 +414,28 @@ config PROBE_EVENTS
 	def_bool n
 
 config DYNAMIC_FTRACE
-	bool "enable/disable ftrace tracepoints dynamically"
+	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
 	default y
 	help
-          This option will modify all the calls to ftrace dynamically
-	  (will patch them out of the binary image and replace them
-	  with a No-Op instruction) as they are called. A table is
-	  created to dynamically enable them again.
+	  This option will modify all the calls to function tracing
+	  dynamically (will patch them out of the binary image and
+	  replace them with a No-Op instruction) on boot up. During
+	  compile time, a table is made of all the locations that ftrace
+	  can function trace, and this table is linked into the kernel
+	  image. When this is enabled, functions can be individually
+	  enabled, and the functions not enabled will not affect
+	  performance of the system.
+
+	  See the files in /sys/kernel/debug/tracing:
+	    available_filter_functions
+	    set_ftrace_filter
+	    set_ftrace_notrace
 
 	  This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
 	  otherwise has native performance as long as no tracing is active.
 
-	  The changes to the code are done by a kernel thread that
-	  wakes up once a second and checks to see if any ftrace calls
-	  were made. If so, it runs stop_machine (stops all CPUS)
-	  and modifies the code to jump over the call to ftrace.
-
 config DYNAMIC_FTRACE_WITH_REGS
 	def_bool y
 	depends on DYNAMIC_FTRACE

kernel/trace/trace.c

@@ -2400,6 +2400,27 @@ static void test_ftrace_alive(struct seq_file *m)
 	seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
 }
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
+{
+	if (iter->trace->allocated_snapshot)
+		seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
+	else
+		seq_printf(m, "#\n# * Snapshot is freed *\n#\n");
+
+	seq_printf(m, "# Snapshot commands:\n");
+	seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
+	seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
+	seq_printf(m, "#                      Takes a snapshot of the main buffer.\n");
+	seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
+	seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
+	seq_printf(m, "#                       is not a '0' or '1')\n");
+}
+#else
+/* Should never be called */
+static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { }
+#endif
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2411,7 +2432,9 @@ static int s_show(struct seq_file *m, void *v)
 			seq_puts(m, "#\n");
 			test_ftrace_alive(m);
 		}
-		if (iter->trace && iter->trace->print_header)
+		if (iter->snapshot && trace_empty(iter))
+			print_snapshot_help(m, iter);
+		else if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
 		else
 			trace_default_header(m);
@@ -4144,8 +4167,6 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	default:
 		if (current_trace->allocated_snapshot)
 			tracing_reset_online_cpus(&max_tr);
-		else
-			ret = -EINVAL;
 		break;
 	}