Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "This update provides the following changes:

   - The rework of the timer wheel which addresses the shortcomings of
     the current wheel (cascading, slow search for next expiring timer,
     etc).  That's the first major change of the wheel in almost 20
     years since Finn implemted it.

   - A large overhaul of the clocksource drivers init functions to
     consolidate the Device Tree initialization

   - Some more Y2038 updates

   - A capability fix for timerfd

   - Yet another clock chip driver

   - The usual pile of updates, comment improvements all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (130 commits)
  tick/nohz: Optimize nohz idle enter
  clockevents: Make clockevents_subsys static
  clocksource/drivers/time-armada-370-xp: Fix return value check
  timers: Implement optimization for same expiry time in mod_timer()
  timers: Split out index calculation
  timers: Only wake softirq if necessary
  timers: Forward the wheel clock whenever possible
  timers/nohz: Remove pointless tick_nohz_kick_tick() function
  timers: Optimize collect_expired_timers() for NOHZ
  timers: Move __run_timers() function
  timers: Remove set_timer_slack() leftovers
  timers: Switch to a non-cascading wheel
  timers: Reduce the CPU index space to 256k
  timers: Give a few structs and members proper names
  hlist: Add hlist_is_singular_node() helper
  signals: Use hrtimer for sigtimedwait()
  timers: Remove the deprecated mod_timer_pinned() API
  timers, net/ipv4/inet: Initialize connection request timers as pinned
  timers, drivers/tty/mips_ejtag: Initialize the poll timer as pinned
  timers, drivers/tty/metag_da: Initialize the poll timer as pinned
  ...

12 files changed, 741 insertions, 526 deletions

diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index e840ed867a5d..c3aad685bbc0 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -30,7 +30,6 @@
  * struct alarm_base - Alarm timer bases
  * @lock:		Lock for syncrhonized access to the base
  * @timerqueue:		Timerqueue head managing the list of events
- * @timer: 		hrtimer used to schedule events while running
  * @gettime:		Function to read the time correlating to the base
  * @base_clockid:	clockid for the base
  */
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index a9b76a40319e..2c5bc77c0bb0 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -645,7 +645,7 @@ void tick_cleanup_dead_cpu(int cpu)
 #endif
 
 #ifdef CONFIG_SYSFS
-struct bus_type clockevents_subsys = {
+static struct bus_type clockevents_subsys = {
 	.name		= "clockevents",
 	.dev_name       = "clockevent",
 };
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 56ece145a814..6a5a310a1a53 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -669,10 +669,12 @@ static void clocksource_enqueue(struct clocksource *cs)
 	struct list_head *entry = &clocksource_list;
 	struct clocksource *tmp;
 
-	list_for_each_entry(tmp, &clocksource_list, list)
+	list_for_each_entry(tmp, &clocksource_list, list) {
 		/* Keep track of the place, where to insert */
-		if (tmp->rating >= cs->rating)
-			entry = &tmp->list;
+		if (tmp->rating < cs->rating)
+			break;
+		entry = &tmp->list;
+	}
 	list_add(&cs->list, entry);
 }
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index e99df0ff1d42..d13c9aebf7a3 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -177,7 +177,7 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 #endif
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
 static inline
 struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
 					 int pinned)
diff --git a/kernel/time/test_udelay.c b/kernel/time/test_udelay.c
index e622ba365a13..b0928ab3270f 100644
--- a/kernel/time/test_udelay.c
+++ b/kernel/time/test_udelay.c
@@ -43,13 +43,13 @@ static int udelay_test_single(struct seq_file *s, int usecs, uint32_t iters)
 	int allowed_error_ns = usecs * 5;
 
 	for (i = 0; i < iters; ++i) {
-		struct timespec ts1, ts2;
+		s64 kt1, kt2;
 		int time_passed;
 
-		ktime_get_ts(&ts1);
+		kt1 = ktime_get_ns();
 		udelay(usecs);
-		ktime_get_ts(&ts2);
-		time_passed = timespec_to_ns(&ts2) - timespec_to_ns(&ts1);
+		kt2 = ktime_get_ns();
+		time_passed = kt2 - kt1;
 
 		if (i == 0 || time_passed < min)
 			min = time_passed;
@@ -87,11 +87,11 @@ static int udelay_test_show(struct seq_file *s, void *v)
 	if (usecs > 0 && iters > 0) {
 		return udelay_test_single(s, usecs, iters);
 	} else if (usecs == 0) {
-		struct timespec ts;
+		struct timespec64 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);
+		ktime_get_ts64(&ts);
+		seq_printf(s, "udelay() test (lpj=%ld kt=%lld.%09ld)\n",
+				loops_per_jiffy, (s64)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");
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 53d7184da0be..690b797f522e 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -75,6 +75,7 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 }
 
 static struct clock_event_device ce_broadcast_hrtimer = {
+	.name			= "bc_hrtimer",
 	.set_state_shutdown	= bc_shutdown,
 	.set_next_ktime		= bc_set_next,
 	.features		= CLOCK_EVT_FEAT_ONESHOT |
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 966a5a6fdd0a..f738251000fe 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -164,3 +164,4 @@ static inline void timers_update_migration(bool update_nohz) { }
 DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
 
 extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);
+void timer_clear_idle(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 536ada80f6dd..204fdc86863d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -31,7 +31,7 @@
 #include <trace/events/timer.h>
 
 /*
- * Per cpu nohz control structure
+ * Per-CPU nohz control structure
  */
 static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
@@ -61,7 +61,7 @@ static void tick_do_update_jiffies64(ktime_t now)
 	if (delta.tv64 < tick_period.tv64)
 		return;
 
-	/* Reevalute with jiffies_lock held */
+	/* Reevaluate with jiffies_lock held */
 	write_seqlock(&jiffies_lock);
 
 	delta = ktime_sub(now, last_jiffies_update);
@@ -116,8 +116,8 @@ static void tick_sched_do_timer(ktime_t now)
 #ifdef CONFIG_NO_HZ_COMMON
 	/*
 	 * Check if the do_timer duty was dropped. We don't care about
-	 * concurrency: This happens only when the cpu in charge went
-	 * into a long sleep. If two cpus happen to assign themself to
+	 * concurrency: This happens only when the CPU in charge went
+	 * into a long sleep. If two CPUs happen to assign themselves to
 	 * this duty, then the jiffies update is still serialized by
 	 * jiffies_lock.
 	 */
@@ -349,7 +349,7 @@ void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bi
 /*
  * Re-evaluate the need for the tick as we switch the current task.
  * It might need the tick due to per task/process properties:
- * perf events, posix cpu timers, ...
+ * perf events, posix CPU timers, ...
  */
 void __tick_nohz_task_switch(void)
 {
@@ -509,8 +509,8 @@ int tick_nohz_tick_stopped(void)
  *
  * In case the sched_tick was stopped on this CPU, we have to check if jiffies
  * must be updated. Otherwise an interrupt handler could use a stale jiffy
- * value. We do this unconditionally on any cpu, as we don't know whether the
- * cpu, which has the update task assigned is in a long sleep.
+ * value. We do this unconditionally on any CPU, as we don't know whether the
+ * CPU, which has the update task assigned is in a long sleep.
  */
 static void tick_nohz_update_jiffies(ktime_t now)
 {
@@ -526,7 +526,7 @@ static void tick_nohz_update_jiffies(ktime_t now)
 }
 
 /*
- * Updates the per cpu time idle statistics counters
+ * Updates the per-CPU time idle statistics counters
  */
 static void
 update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
@@ -566,12 +566,12 @@ static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 }
 
 /**
- * get_cpu_idle_time_us - get the total idle time of a cpu
+ * get_cpu_idle_time_us - get the total idle time of a CPU
  * @cpu: CPU number to query
  * @last_update_time: variable to store update time in. Do not update
  * counters if NULL.
  *
- * Return the cummulative idle time (since boot) for a given
+ * Return the cumulative idle time (since boot) for a given
  * CPU, in microseconds.
  *
  * This time is measured via accounting rather than sampling,
@@ -607,12 +607,12 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
 /**
- * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * get_cpu_iowait_time_us - get the total iowait time of a CPU
  * @cpu: CPU number to query
  * @last_update_time: variable to store update time in. Do not update
  * counters if NULL.
  *
- * Return the cummulative iowait time (since boot) for a given
+ * Return the cumulative iowait time (since boot) for a given
  * CPU, in microseconds.
  *
  * This time is measured via accounting rather than sampling,
@@ -700,6 +700,12 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	delta = next_tick - basemono;
 	if (delta <= (u64)TICK_NSEC) {
 		tick.tv64 = 0;
+
+		/*
+		 * Tell the timer code that the base is not idle, i.e. undo
+		 * the effect of get_next_timer_interrupt():
+		 */
+		timer_clear_idle();
 		/*
 		 * We've not stopped the tick yet, and there's a timer in the
 		 * next period, so no point in stopping it either, bail.
@@ -726,14 +732,14 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	}
 
 	/*
-	 * If this cpu is the one which updates jiffies, then give up
-	 * the assignment and let it be taken by the cpu which runs
-	 * the tick timer next, which might be this cpu as well. If we
+	 * If this CPU is the one which updates jiffies, then give up
+	 * the assignment and let it be taken by the CPU which runs
+	 * the tick timer next, which might be this CPU as well. If we
 	 * don't drop this here the jiffies might be stale and
 	 * do_timer() never invoked. Keep track of the fact that it
-	 * was the one which had the do_timer() duty last. If this cpu
+	 * was the one which had the do_timer() duty last. If this CPU
 	 * is the one which had the do_timer() duty last, we limit the
-	 * sleep time to the timekeeping max_deferement value.
+	 * sleep time to the timekeeping max_deferment value.
 	 * Otherwise we can sleep as long as we want.
 	 */
 	delta = timekeeping_max_deferment();
@@ -809,6 +815,12 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	tick_do_update_jiffies64(now);
 	cpu_load_update_nohz_stop();
 
+	/*
+	 * Clear the timer idle flag, so we avoid IPIs on remote queueing and
+	 * the clock forward checks in the enqueue path:
+	 */
+	timer_clear_idle();
+
 	calc_load_exit_idle();
 	touch_softlockup_watchdog_sched();
 	/*
@@ -841,9 +853,9 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 {
 	/*
-	 * If this cpu is offline and it is the one which updates
+	 * If this CPU is offline and it is the one which updates
 	 * jiffies, then give up the assignment and let it be taken by
-	 * the cpu which runs the tick timer next. If we don't drop
+	 * the CPU which runs the tick timer next. If we don't drop
 	 * this here the jiffies might be stale and do_timer() never
 	 * invoked.
 	 */
@@ -896,11 +908,10 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 	ktime_t now, expires;
 	int cpu = smp_processor_id();
 
-	now = tick_nohz_start_idle(ts);
-
 	if (can_stop_idle_tick(cpu, ts)) {
 		int was_stopped = ts->tick_stopped;
 
+		now = tick_nohz_start_idle(ts);
 		ts->idle_calls++;
 
 		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
@@ -933,11 +944,11 @@ void tick_nohz_idle_enter(void)
 	WARN_ON_ONCE(irqs_disabled());
 
 	/*
- 	 * Update the idle state in the scheduler domain hierarchy
- 	 * when tick_nohz_stop_sched_tick() is called from the idle loop.
- 	 * State will be updated to busy during the first busy tick after
- 	 * exiting idle.
- 	 */
+	 * Update the idle state in the scheduler domain hierarchy
+	 * when tick_nohz_stop_sched_tick() is called from the idle loop.
+	 * State will be updated to busy during the first busy tick after
+	 * exiting idle.
+	 */
 	set_cpu_sd_state_idle();
 
 	local_irq_disable();
@@ -1092,35 +1103,6 @@ static void tick_nohz_switch_to_nohz(void)
 	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
 }
 
-/*
- * When NOHZ is enabled and the tick is stopped, we need to kick the
- * tick timer from irq_enter() so that the jiffies update is kept
- * alive during long running softirqs. That's ugly as hell, but
- * correctness is key even if we need to fix the offending softirq in
- * the first place.
- *
- * Note, this is different to tick_nohz_restart. We just kick the
- * timer and do not touch the other magic bits which need to be done
- * when idle is left.
- */
-static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
-{
-#if 0
-	/* Switch back to 2.6.27 behaviour */
-	ktime_t delta;
-
-	/*
-	 * Do not touch the tick device, when the next expiry is either
-	 * already reached or less/equal than the tick period.
-	 */
-	delta =	ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
-	if (delta.tv64 <= tick_period.tv64)
-		return;
-
-	tick_nohz_restart(ts, now);
-#endif
-}
-
 static inline void tick_nohz_irq_enter(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
@@ -1131,10 +1113,8 @@ static inline void tick_nohz_irq_enter(void)
 	now = ktime_get();
 	if (ts->idle_active)
 		tick_nohz_stop_idle(ts, now);
-	if (ts->tick_stopped) {
+	if (ts->tick_stopped)
 		tick_nohz_update_jiffies(now);
-		tick_nohz_kick_tick(ts, now);
-	}
 }
 
 #else
@@ -1211,7 +1191,7 @@ void tick_setup_sched_timer(void)
 	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	ts->sched_timer.function = tick_sched_timer;
 
-	/* Get the next period (per cpu) */
+	/* Get the next period (per-CPU) */
 	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
 
 	/* Offset the tick to avert jiffies_lock contention. */
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
index 86628e755f38..7142580ad94f 100644
--- a/kernel/time/timeconv.c
+++ b/kernel/time/timeconv.c
@@ -67,20 +67,21 @@ static const unsigned short __mon_yday[2][13] = {
 #define SECS_PER_DAY	(SECS_PER_HOUR * 24)
 
 /**
- * time_to_tm - converts the calendar time to local broken-down time
+ * time64_to_tm - converts the calendar time to local broken-down time
  *
  * @totalsecs	the number of seconds elapsed since 00:00:00 on January 1, 1970,
  *		Coordinated Universal Time (UTC).
  * @offset	offset seconds adding to totalsecs.
  * @result	pointer to struct tm variable to receive broken-down time
  */
-void time_to_tm(time_t totalsecs, int offset, struct tm *result)
+void time64_to_tm(time64_t totalsecs, int offset, struct tm *result)
 {
 	long days, rem, y;
+	int remainder;
 	const unsigned short *ip;
 
-	days = totalsecs / SECS_PER_DAY;
-	rem = totalsecs % SECS_PER_DAY;
+	days = div_s64_rem(totalsecs, SECS_PER_DAY, &remainder);
+	rem = remainder;
 	rem += offset;
 	while (rem < 0) {
 		rem += SECS_PER_DAY;
@@ -124,4 +125,4 @@ void time_to_tm(time_t totalsecs, int offset, struct tm *result)
 	result->tm_mon = y;
 	result->tm_mday = days + 1;
 }
-EXPORT_SYMBOL(time_to_tm);
+EXPORT_SYMBOL(time64_to_tm);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 255e225393ac..3b65746c7f15 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -480,10 +480,12 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	* users are removed, this can be killed.
 	*/
 	remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1);
-	tk->tkr_mono.xtime_nsec -= remainder;
-	tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift;
-	tk->ntp_error += remainder << tk->ntp_error_shift;
-	tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift;
+	if (remainder != 0) {
+		tk->tkr_mono.xtime_nsec -= remainder;
+		tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift;
+		tk->ntp_error += remainder << tk->ntp_error_shift;
+		tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift;
+	}
 }
 #else
 #define old_vsyscall_fixup(tk)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3a95f9728778..cb9ab401e2d9 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -59,43 +59,153 @@ __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 EXPORT_SYMBOL(jiffies_64);
 
 /*
- * per-CPU timer vector definitions:
+ * The timer wheel has LVL_DEPTH array levels. Each level provides an array of
+ * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
+ * level has a different granularity.
+ *
+ * The level granularity is:		LVL_CLK_DIV ^ lvl
+ * The level clock frequency is:	HZ / (LVL_CLK_DIV ^ level)
+ *
+ * The array level of a newly armed timer depends on the relative expiry
+ * time. The farther the expiry time is away the higher the array level and
+ * therefor the granularity becomes.
+ *
+ * Contrary to the original timer wheel implementation, which aims for 'exact'
+ * expiry of the timers, this implementation removes the need for recascading
+ * the timers into the lower array levels. The previous 'classic' timer wheel
+ * implementation of the kernel already violated the 'exact' expiry by adding
+ * slack to the expiry time to provide batched expiration. The granularity
+ * levels provide implicit batching.
+ *
+ * This is an optimization of the original timer wheel implementation for the
+ * majority of the timer wheel use cases: timeouts. The vast majority of
+ * timeout timers (networking, disk I/O ...) are canceled before expiry. If
+ * the timeout expires it indicates that normal operation is disturbed, so it
+ * does not matter much whether the timeout comes with a slight delay.
+ *
+ * The only exception to this are networking timers with a small expiry
+ * time. They rely on the granularity. Those fit into the first wheel level,
+ * which has HZ granularity.
+ *
+ * We don't have cascading anymore. timers with a expiry time above the
+ * capacity of the last wheel level are force expired at the maximum timeout
+ * value of the last wheel level. From data sampling we know that the maximum
+ * value observed is 5 days (network connection tracking), so this should not
+ * be an issue.
+ *
+ * The currently chosen array constants values are a good compromise between
+ * array size and granularity.
+ *
+ * This results in the following granularity and range levels:
+ *
+ * HZ 1000 steps
+ * Level Offset  Granularity            Range
+ *  0      0         1 ms                0 ms -         63 ms
+ *  1     64         8 ms               64 ms -        511 ms
+ *  2    128        64 ms              512 ms -       4095 ms (512ms - ~4s)
+ *  3    192       512 ms             4096 ms -      32767 ms (~4s - ~32s)
+ *  4    256      4096 ms (~4s)      32768 ms -     262143 ms (~32s - ~4m)
+ *  5    320     32768 ms (~32s)    262144 ms -    2097151 ms (~4m - ~34m)
+ *  6    384    262144 ms (~4m)    2097152 ms -   16777215 ms (~34m - ~4h)
+ *  7    448   2097152 ms (~34m)  16777216 ms -  134217727 ms (~4h - ~1d)
+ *  8    512  16777216 ms (~4h)  134217728 ms - 1073741822 ms (~1d - ~12d)
+ *
+ * HZ  300
+ * Level Offset  Granularity            Range
+ *  0	   0         3 ms                0 ms -        210 ms
+ *  1	  64        26 ms              213 ms -       1703 ms (213ms - ~1s)
+ *  2	 128       213 ms             1706 ms -      13650 ms (~1s - ~13s)
+ *  3	 192      1706 ms (~1s)      13653 ms -     109223 ms (~13s - ~1m)
+ *  4	 256     13653 ms (~13s)    109226 ms -     873810 ms (~1m - ~14m)
+ *  5	 320    109226 ms (~1m)     873813 ms -    6990503 ms (~14m - ~1h)
+ *  6	 384    873813 ms (~14m)   6990506 ms -   55924050 ms (~1h - ~15h)
+ *  7	 448   6990506 ms (~1h)   55924053 ms -  447392423 ms (~15h - ~5d)
+ *  8    512  55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d)
+ *
+ * HZ  250
+ * Level Offset  Granularity            Range
+ *  0	   0         4 ms                0 ms -        255 ms
+ *  1	  64        32 ms              256 ms -       2047 ms (256ms - ~2s)
+ *  2	 128       256 ms             2048 ms -      16383 ms (~2s - ~16s)
+ *  3	 192      2048 ms (~2s)      16384 ms -     131071 ms (~16s - ~2m)
+ *  4	 256     16384 ms (~16s)    131072 ms -    1048575 ms (~2m - ~17m)
+ *  5	 320    131072 ms (~2m)    1048576 ms -    8388607 ms (~17m - ~2h)
+ *  6	 384   1048576 ms (~17m)   8388608 ms -   67108863 ms (~2h - ~18h)
+ *  7	 448   8388608 ms (~2h)   67108864 ms -  536870911 ms (~18h - ~6d)
+ *  8    512  67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d)
+ *
+ * HZ  100
+ * Level Offset  Granularity            Range
+ *  0	   0         10 ms               0 ms -        630 ms
+ *  1	  64         80 ms             640 ms -       5110 ms (640ms - ~5s)
+ *  2	 128        640 ms            5120 ms -      40950 ms (~5s - ~40s)
+ *  3	 192       5120 ms (~5s)     40960 ms -     327670 ms (~40s - ~5m)
+ *  4	 256      40960 ms (~40s)   327680 ms -    2621430 ms (~5m - ~43m)
+ *  5	 320     327680 ms (~5m)   2621440 ms -   20971510 ms (~43m - ~5h)
+ *  6	 384    2621440 ms (~43m) 20971520 ms -  167772150 ms (~5h - ~1d)
+ *  7	 448   20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d)
  */
-#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6)
-#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8)
-#define TVN_SIZE (1 << TVN_BITS)
-#define TVR_SIZE (1 << TVR_BITS)
-#define TVN_MASK (TVN_SIZE - 1)
-#define TVR_MASK (TVR_SIZE - 1)
-#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1))
-
-struct tvec {
-	struct hlist_head vec[TVN_SIZE];
-};
 
-struct tvec_root {
-	struct hlist_head vec[TVR_SIZE];
-};
+/* Clock divisor for the next level */
+#define LVL_CLK_SHIFT	3
+#define LVL_CLK_DIV	(1UL << LVL_CLK_SHIFT)
+#define LVL_CLK_MASK	(LVL_CLK_DIV - 1)
+#define LVL_SHIFT(n)	((n) * LVL_CLK_SHIFT)
+#define LVL_GRAN(n)	(1UL << LVL_SHIFT(n))
 
-struct tvec_base {
-	spinlock_t lock;
-	struct timer_list *running_timer;
-	unsigned long timer_jiffies;
-	unsigned long next_timer;
-	unsigned long active_timers;
-	unsigned long all_timers;
-	int cpu;
-	bool migration_enabled;
-	bool nohz_active;
-	struct tvec_root tv1;
-	struct tvec tv2;
-	struct tvec tv3;
-	struct tvec tv4;
-	struct tvec tv5;
-} ____cacheline_aligned;
+/*
+ * The time start value for each level to select the bucket at enqueue
+ * time.
+ */
+#define LVL_START(n)	((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT))
+
+/* Size of each clock level */
+#define LVL_BITS	6
+#define LVL_SIZE	(1UL << LVL_BITS)
+#define LVL_MASK	(LVL_SIZE - 1)
+#define LVL_OFFS(n)	((n) * LVL_SIZE)
+
+/* Level depth */
+#if HZ > 100
+# define LVL_DEPTH	9
+# else
+# define LVL_DEPTH	8
+#endif
+
+/* The cutoff (max. capacity of the wheel) */
+#define WHEEL_TIMEOUT_CUTOFF	(LVL_START(LVL_DEPTH))
+#define WHEEL_TIMEOUT_MAX	(WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1))
+
+/*
+ * The resulting wheel size. If NOHZ is configured we allocate two
+ * wheels so we have a separate storage for the deferrable timers.
+ */
+#define WHEEL_SIZE	(LVL_SIZE * LVL_DEPTH)
+
+#ifdef CONFIG_NO_HZ_COMMON
+# define NR_BASES	2
+# define BASE_STD	0
+# define BASE_DEF	1
+#else
+# define NR_BASES	1
+# define BASE_STD	0
+# define BASE_DEF	0
+#endif
 
+struct timer_base {
+	spinlock_t		lock;
+	struct timer_list	*running_timer;
+	unsigned long		clk;
+	unsigned long		next_expiry;
+	unsigned int		cpu;
+	bool			migration_enabled;
+	bool			nohz_active;
+	bool			is_idle;
+	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
+	struct hlist_head	vectors[WHEEL_SIZE];
+} ____cacheline_aligned;
 
-static DEFINE_PER_CPU(struct tvec_base, tvec_bases);
+static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 unsigned int sysctl_timer_migration = 1;
@@ -106,15 +216,17 @@ void timers_update_migration(bool update_nohz)
 	unsigned int cpu;
 
 	/* Avoid the loop, if nothing to update */
-	if (this_cpu_read(tvec_bases.migration_enabled) == on)
+	if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on)
 		return;
 
 	for_each_possible_cpu(cpu) {
-		per_cpu(tvec_bases.migration_enabled, cpu) = on;
+		per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on;
+		per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on;
 		per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
 		if (!update_nohz)
 			continue;
-		per_cpu(tvec_bases.nohz_active, cpu) = true;
+		per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true;
+		per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true;
 		per_cpu(hrtimer_bases.nohz_active, cpu) = true;
 	}
 }
@@ -133,20 +245,6 @@ int timer_migration_handler(struct ctl_table *table, int write,
 	mutex_unlock(&mutex);
 	return ret;
 }
-
-static inline struct tvec_base *get_target_base(struct tvec_base *base,
-						int pinned)
-{
-	if (pinned || !base->migration_enabled)
-		return this_cpu_ptr(&tvec_bases);
-	return per_cpu_ptr(&tvec_bases, get_nohz_timer_target());
-}
-#else
-static inline struct tvec_base *get_target_base(struct tvec_base *base,
-						int pinned)
-{
-	return this_cpu_ptr(&tvec_bases);
-}
 #endif
 
 static unsigned long round_jiffies_common(unsigned long j, int cpu,
@@ -351,101 +449,126 @@ unsigned long round_jiffies_up_relative(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
 
-/**
- * set_timer_slack - set the allowed slack for a timer
- * @timer: the timer to be modified
- * @slack_hz: the amount of time (in jiffies) allowed for rounding
- *
- * Set the amount of time, in jiffies, that a certain timer has
- * in terms of slack. By setting this value, the timer subsystem
- * will schedule the actual timer somewhere between
- * the time mod_timer() asks for, and that time plus the slack.
- *
- * By setting the slack to -1, a percentage of the delay is used
- * instead.
- */
-void set_timer_slack(struct timer_list *timer, int slack_hz)
+
+static inline unsigned int timer_get_idx(struct timer_list *timer)
 {
-	timer->slack = slack_hz;
+	return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT;
 }
-EXPORT_SYMBOL_GPL(set_timer_slack);
 
-static void
-__internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+static inline void timer_set_idx(struct timer_list *timer, unsigned int idx)
 {
-	unsigned long expires = timer->expires;
-	unsigned long idx = expires - base->timer_jiffies;
-	struct hlist_head *vec;
+	timer->flags = (timer->flags & ~TIMER_ARRAYMASK) |
+			idx << TIMER_ARRAYSHIFT;
+}
 
-	if (idx < TVR_SIZE) {
-		int i = expires & TVR_MASK;
-		vec = base->tv1.vec + i;
-	} else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
-		int i = (expires >> TVR_BITS) & TVN_MASK;
-		vec = base->tv2.vec + i;
-	} else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
-		int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
-		vec = base->tv3.vec + i;
-	} else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
-		int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
-		vec = base->tv4.vec + i;
-	} else if ((signed long) idx < 0) {
-		/*
-		 * Can happen if you add a timer with expires == jiffies,
-		 * or you set a timer to go off in the past
-		 */
-		vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
+/*
+ * Helper function to calculate the array index for a given expiry
+ * time.
+ */
+static inline unsigned calc_index(unsigned expires, unsigned lvl)
+{
+	expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl);
+	return LVL_OFFS(lvl) + (expires & LVL_MASK);
+}
+
+static int calc_wheel_index(unsigned long expires, unsigned long clk)
+{
+	unsigned long delta = expires - clk;
+	unsigned int idx;
+
+	if (delta < LVL_START(1)) {
+		idx = calc_index(expires, 0);
+	} else if (delta < LVL_START(2)) {
+		idx = calc_index(expires, 1);
+	} else if (delta < LVL_START(3)) {
+		idx = calc_index(expires, 2);
+	} else if (delta < LVL_START(4)) {
+		idx = calc_index(expires, 3);
+	} else if (delta < LVL_START(5)) {
+		idx = calc_index(expires, 4);
+	} else if (delta < LVL_START(6)) {
+		idx = calc_index(expires, 5);
+	} else if (delta < LVL_START(7)) {
+		idx = calc_index(expires, 6);
+	} else if (LVL_DEPTH > 8 && delta < LVL_START(8)) {
+		idx = calc_index(expires, 7);
+	} else if ((long) delta < 0) {
+		idx = clk & LVL_MASK;
 	} else {
-		int i;
-		/* If the timeout is larger than MAX_TVAL (on 64-bit
-		 * architectures or with CONFIG_BASE_SMALL=1) then we
-		 * use the maximum timeout.
+		/*
+		 * Force expire obscene large timeouts to expire at the
+		 * capacity limit of the wheel.
 		 */
-		if (idx > MAX_TVAL) {
-			idx = MAX_TVAL;
-			expires = idx + base->timer_jiffies;
-		}
-		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
-		vec = base->tv5.vec + i;
+		if (expires >= WHEEL_TIMEOUT_CUTOFF)
+			expires = WHEEL_TIMEOUT_MAX;
+
+		idx = calc_index(expires, LVL_DEPTH - 1);
 	}
+	return idx;
+}
 
-	hlist_add_head(&timer->entry, vec);
+/*
+ * Enqueue the timer into the hash bucket, mark it pending in
+ * the bitmap and store the index in the timer flags.
+ */
+static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
+			  unsigned int idx)
+{
+	hlist_add_head(&timer->entry, base->vectors + idx);
+	__set_bit(idx, base->pending_map);
+	timer_set_idx(timer, idx);
 }
 
-static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+static void
+__internal_add_timer(struct timer_base *base, struct timer_list *timer)
 {
-	/* Advance base->jiffies, if the base is empty */
-	if (!base->all_timers++)
-		base->timer_jiffies = jiffies;
+	unsigned int idx;
+
+	idx = calc_wheel_index(timer->expires, base->clk);
+	enqueue_timer(base, timer, idx);
+}
+
+static void
+trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
+{
+	if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+		return;
 
-	__internal_add_timer(base, timer);
 	/*
-	 * Update base->active_timers and base->next_timer
+	 * TODO: This wants some optimizing similar to the code below, but we
+	 * will do that when we switch from push to pull for deferrable timers.
 	 */
-	if (!(timer->flags & TIMER_DEFERRABLE)) {
-		if (!base->active_timers++ ||
-		    time_before(timer->expires, base->next_timer))
-			base->next_timer = timer->expires;
+	if (timer->flags & TIMER_DEFERRABLE) {
+		if (tick_nohz_full_cpu(base->cpu))
+			wake_up_nohz_cpu(base->cpu);
+		return;
 	}
 
 	/*
-	 * 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.
+	 * We might have to IPI the remote CPU if the base is idle and the
+	 * timer is not deferrable. If the other CPU is on the way to idle
+	 * then it can't set base->is_idle as we hold the base lock:
 	 */
-	if (base->nohz_active) {
-		if (!(timer->flags & TIMER_DEFERRABLE) ||
-		    tick_nohz_full_cpu(base->cpu))
-			wake_up_nohz_cpu(base->cpu);
-	}
+	if (!base->is_idle)
+		return;
+
+	/* Check whether this is the new first expiring timer: */
+	if (time_after_eq(timer->expires, base->next_expiry))
+		return;
+
+	/*
+	 * Set the next expiry time and kick the CPU so it can reevaluate the
+	 * wheel:
+	 */
+	base->next_expiry = timer->expires;
+		wake_up_nohz_cpu(base->cpu);
+}
+
+static void
+internal_add_timer(struct timer_base *base, struct timer_list *timer)
+{
+	__internal_add_timer(base, timer);
+	trigger_dyntick_cpu(base, timer);
 }
 
 #ifdef CONFIG_TIMER_STATS
@@ -666,7 +789,6 @@ static void do_init_timer(struct timer_list *timer, unsigned int flags,
 {
 	timer->entry.pprev = NULL;
 	timer->flags = flags | raw_smp_processor_id();
-	timer->slack = -1;
 #ifdef CONFIG_TIMER_STATS
 	timer->start_site = NULL;
 	timer->start_pid = -1;
@@ -706,54 +828,125 @@ static inline void detach_timer(struct timer_list *timer, bool clear_pending)
 	entry->next = LIST_POISON2;
 }
 
-static inline void
-detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
-{
-	detach_timer(timer, true);
-	if (!(timer->flags & TIMER_DEFERRABLE))
-		base->active_timers--;
-	base->all_timers--;