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

Pull timer updates from Thomas Gleixner:
 "The timer departement presents:

   - A rather large rework of the hrtimer infrastructure which
     introduces softirq based hrtimers to replace the spread of
     hrtimer/tasklet combos which force the actual callback execution
     into softirq context. The approach is completely different from the
     initial implementation which you cursed at 10 years ago rightfully.

     The softirq based timers have their own queues and there is no
     nasty indirection and list reshuffling in the hard interrupt
     anymore. This comes with conversion of some of the hrtimer/tasklet
     users, the rest and the final removal of that horrible interface
     will come towards the end of the merge window or go through the
     relevant maintainer trees.

     Note: The top commit merged the last minute bugfix for the 10 years
     old CPU hotplug bug as I wanted to make sure that I fatfinger the
     merge conflict resolution myself.

   - The overhaul of the STM32 clocksource/clockevents driver

   - A new driver for the Spreadtrum SC9860 timer

   - A new driver dor the Actions Semi S700 timer

   - The usual set of fixes and updates all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  usb/gadget/NCM: Replace tasklet with softirq hrtimer
  ALSA/dummy: Replace tasklet with softirq hrtimer
  hrtimer: Implement SOFT/HARD clock base selection
  hrtimer: Implement support for softirq based hrtimers
  hrtimer: Prepare handling of hard and softirq based hrtimers
  hrtimer: Add clock bases and hrtimer mode for softirq context
  hrtimer: Use irqsave/irqrestore around __run_hrtimer()
  hrtimer: Factor out __hrtimer_next_event_base()
  hrtimer: Factor out __hrtimer_start_range_ns()
  hrtimer: Remove the 'base' parameter from hrtimer_reprogram()
  hrtimer: Make remote enqueue decision less restrictive
  hrtimer: Unify remote enqueue handling
  hrtimer: Unify hrtimer removal handling
  hrtimer: Make hrtimer_force_reprogramm() unconditionally available
  hrtimer: Make hrtimer_reprogramm() unconditional
  hrtimer: Make hrtimer_cpu_base.next_timer handling unconditional
  hrtimer: Make the remote enqueue check unconditional
  hrtimer: Use accesor functions instead of direct access
  hrtimer: Make the hrtimer_cpu_base::hres_active field unconditional, to simplify the code
  hrtimer: Make room in 'struct hrtimer_cpu_base'
  ...

6 files changed, 482 insertions, 289 deletions

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index aa9d2a2b1210..ae0c8a411fe7 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -60,6 +60,15 @@
 #include "tick-internal.h"
 
 /*
+ * Masks for selecting the soft and hard context timers from
+ * cpu_base->active
+ */
+#define MASK_SHIFT		(HRTIMER_BASE_MONOTONIC_SOFT)
+#define HRTIMER_ACTIVE_HARD	((1U << MASK_SHIFT) - 1)
+#define HRTIMER_ACTIVE_SOFT	(HRTIMER_ACTIVE_HARD << MASK_SHIFT)
+#define HRTIMER_ACTIVE_ALL	(HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
+
+/*
  * The timer bases:
  *
  * There are more clockids than hrtimer bases. Thus, we index
@@ -70,7 +79,6 @@
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
 	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
-	.seq = SEQCNT_ZERO(hrtimer_bases.seq),
 	.clock_base =
 	{
 		{
@@ -93,6 +101,26 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
 		},
+		{
+			.index = HRTIMER_BASE_MONOTONIC_SOFT,
+			.clockid = CLOCK_MONOTONIC,
+			.get_time = &ktime_get,
+		},
+		{
+			.index = HRTIMER_BASE_REALTIME_SOFT,
+			.clockid = CLOCK_REALTIME,
+			.get_time = &ktime_get_real,
+		},
+		{
+			.index = HRTIMER_BASE_BOOTTIME_SOFT,
+			.clockid = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+		},
+		{
+			.index = HRTIMER_BASE_TAI_SOFT,
+			.clockid = CLOCK_TAI,
+			.get_time = &ktime_get_clocktai,
+		},
 	}
 };
 
@@ -118,7 +146,6 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
  * timer->base->cpu_base
  */
 static struct hrtimer_cpu_base migration_cpu_base = {
-	.seq = SEQCNT_ZERO(migration_cpu_base),
 	.clock_base = { { .cpu_base = &migration_cpu_base, }, },
 };
 
@@ -156,45 +183,33 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 }
 
 /*
- * With HIGHRES=y we do not migrate the timer when it is expiring
- * before the next event on the target cpu because we cannot reprogram
- * the target cpu hardware and we would cause it to fire late.
+ * We do not migrate the timer when it is expiring before the next
+ * event on the target cpu. When high resolution is enabled, we cannot
+ * reprogram the target cpu hardware and we would cause it to fire
+ * late. To keep it simple, we handle the high resolution enabled and
+ * disabled case similar.
  *
  * Called with cpu_base->lock of target cpu held.
  */
 static int
 hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 {
-#ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t expires;
 
-	if (!new_base->cpu_base->hres_active)
-		return 0;
-
 	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
-	return expires <= new_base->cpu_base->expires_next;
-#else
-	return 0;
-#endif
+	return expires < new_base->cpu_base->expires_next;
 }
 
-#ifdef CONFIG_NO_HZ_COMMON
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
-					 int pinned)
-{
-	if (pinned || !base->migration_enabled)
-		return base;
-	return &per_cpu(hrtimer_bases, get_nohz_timer_target());
-}
-#else
 static inline
 struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
 					 int pinned)
 {
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+	if (static_branch_likely(&timers_migration_enabled) && !pinned)
+		return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+#endif
 	return base;
 }
-#endif
 
 /*
  * We switch the timer base to a power-optimized selected CPU target,
@@ -396,7 +411,8 @@ static inline void debug_hrtimer_init(struct hrtimer *timer)
 	debug_object_init(timer, &hrtimer_debug_descr);
 }
 
-static inline void debug_hrtimer_activate(struct hrtimer *timer)
+static inline void debug_hrtimer_activate(struct hrtimer *timer,
+					  enum hrtimer_mode mode)
 {
 	debug_object_activate(timer, &hrtimer_debug_descr);
 }
@@ -429,8 +445,10 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer)
 EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
 
 #else
+
 static inline void debug_hrtimer_init(struct hrtimer *timer) { }
-static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
+static inline void debug_hrtimer_activate(struct hrtimer *timer,
+					  enum hrtimer_mode mode) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
@@ -442,10 +460,11 @@ debug_init(struct hrtimer *timer, clockid_t clockid,
 	trace_hrtimer_init(timer, clockid, mode);
 }
 
-static inline void debug_activate(struct hrtimer *timer)
+static inline void debug_activate(struct hrtimer *timer,
+				  enum hrtimer_mode mode)
 {
-	debug_hrtimer_activate(timer);
-	trace_hrtimer_start(timer);
+	debug_hrtimer_activate(timer, mode);
+	trace_hrtimer_start(timer, mode);
 }
 
 static inline void debug_deactivate(struct hrtimer *timer)
@@ -454,35 +473,43 @@ static inline void debug_deactivate(struct hrtimer *timer)
 	trace_hrtimer_cancel(timer);
 }
 
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
-static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
-					     struct hrtimer *timer)
+static struct hrtimer_clock_base *
+__next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active)
 {
-#ifdef CONFIG_HIGH_RES_TIMERS
-	cpu_base->next_timer = timer;
-#endif
+	unsigned int idx;
+
+	if (!*active)
+		return NULL;
+
+	idx = __ffs(*active);
+	*active &= ~(1U << idx);
+
+	return &cpu_base->clock_base[idx];
 }
 
-static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
+#define for_each_active_base(base, cpu_base, active)	\
+	while ((base = __next_base((cpu_base), &(active))))
+
+static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
+					 unsigned int active,
+					 ktime_t expires_next)
 {
-	struct hrtimer_clock_base *base = cpu_base->clock_base;
-	unsigned int active = cpu_base->active_bases;
-	ktime_t expires, expires_next = KTIME_MAX;
+	struct hrtimer_clock_base *base;
+	ktime_t expires;
 
-	hrtimer_update_next_timer(cpu_base, NULL);
-	for (; active; base++, active >>= 1) {
+	for_each_active_base(base, cpu_base, active) {
 		struct timerqueue_node *next;
 		struct hrtimer *timer;
 
-		if (!(active & 0x01))
-			continue;
-
 		next = timerqueue_getnext(&base->active);
 		timer = container_of(next, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
 		if (expires < expires_next) {
 			expires_next = expires;
-			hrtimer_update_next_timer(cpu_base, timer);
+			if (timer->is_soft)
+				cpu_base->softirq_next_timer = timer;
+			else
+				cpu_base->next_timer = timer;
 		}
 	}
 	/*
@@ -494,7 +521,47 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 		expires_next = 0;
 	return expires_next;
 }
-#endif
+
+/*
+ * Recomputes cpu_base::*next_timer and returns the earliest expires_next but
+ * does not set cpu_base::*expires_next, that is done by hrtimer_reprogram.
+ *
+ * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases,
+ * those timers will get run whenever the softirq gets handled, at the end of
+ * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases.
+ *
+ * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases.
+ * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual
+ * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD.
+ *
+ * @active_mask must be one of:
+ *  - HRTIMER_ACTIVE_ALL,
+ *  - HRTIMER_ACTIVE_SOFT, or
+ *  - HRTIMER_ACTIVE_HARD.
+ */
+static ktime_t
+__hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask)
+{
+	unsigned int active;
+	struct hrtimer *next_timer = NULL;
+	ktime_t expires_next = KTIME_MAX;
+
+	if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) {
+		active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
+		cpu_base->softirq_next_timer = NULL;
+		expires_next = __hrtimer_next_event_base(cpu_base, active, KTIME_MAX);
+
+		next_timer = cpu_base->softirq_next_timer;
+	}
+
+	if (active_mask & HRTIMER_ACTIVE_HARD) {
+		active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD;
+		cpu_base->next_timer = next_timer;
+		expires_next = __hrtimer_next_event_base(cpu_base, active, expires_next);
+	}
+
+	return expires_next;
+}
 
 static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 {
@@ -502,36 +569,14 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 	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_now(&base->clock_was_set_seq,
+	ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
 					    offs_real, offs_boot, offs_tai);
-}
-
-/* High resolution timer related functions */
-#ifdef CONFIG_HIGH_RES_TIMERS
 
-/*
- * High resolution timer enabled ?
- */
-static bool hrtimer_hres_enabled __read_mostly  = true;
-unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
-EXPORT_SYMBOL_GPL(hrtimer_resolution);
+	base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
+	base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
+	base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
 
-/*
- * Enable / Disable high resolution mode
- */
-static int __init setup_hrtimer_hres(char *str)
-{
-	return (kstrtobool(str, &hrtimer_hres_enabled) == 0);
-}
-
-__setup("highres=", setup_hrtimer_hres);
-
-/*
- * hrtimer_high_res_enabled - query, if the highres mode is enabled
- */
-static inline int hrtimer_is_hres_enabled(void)
-{
-	return hrtimer_hres_enabled;
+	return now;
 }
 
 /*
@@ -539,7 +584,8 @@ static inline int hrtimer_is_hres_enabled(void)
  */
 static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
 {
-	return cpu_base->hres_active;
+	return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+		cpu_base->hres_active : 0;
 }
 
 static inline int hrtimer_hres_active(void)
@@ -557,10 +603,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
 	ktime_t expires_next;
 
-	if (!cpu_base->hres_active)
-		return;
+	/*
+	 * Find the current next expiration time.
+	 */
+	expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 
-	expires_next = __hrtimer_get_next_event(cpu_base);
+	if (cpu_base->next_timer && cpu_base->next_timer->is_soft) {
+		/*
+		 * When the softirq is activated, hrtimer has to be
+		 * programmed with the first hard hrtimer because soft
+		 * timer interrupt could occur too late.
+		 */
+		if (cpu_base->softirq_activated)
+			expires_next = __hrtimer_get_next_event(cpu_base,
+								HRTIMER_ACTIVE_HARD);
+		else
+			cpu_base->softirq_expires_next = expires_next;
+	}
 
 	if (skip_equal && expires_next == cpu_base->expires_next)
 		return;
@@ -568,6 +627,9 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	cpu_base->expires_next = expires_next;
 
 	/*
+	 * If hres is not active, hardware does not have to be
+	 * reprogrammed yet.
+	 *
 	 * If a hang was detected in the last timer interrupt then we
 	 * leave the hang delay active in the hardware. We want the
 	 * system to make progress. That also prevents the following
@@ -581,83 +643,38 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	 * set. So we'd effectivly block all timers until the T2 event
 	 * fires.
 	 */
-	if (cpu_base->hang_detected)
+	if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
 		return;
 
 	tick_program_event(cpu_base->expires_next, 1);
 }
 
+/* High resolution timer related functions */
+#ifdef CONFIG_HIGH_RES_TIMERS
+
 /*
- * When a timer is enqueued and expires earlier than the already enqueued
- * timers, we have to check, whether it expires earlier than the timer for
- * which the clock event device was armed.
- *
- * Called with interrupts disabled and base->cpu_base.lock held
+ * High resolution timer enabled ?
  */
-static void hrtimer_reprogram(struct hrtimer *timer,
-			      struct hrtimer_clock_base *base)
-{
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-
-	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
-
-	/*
-	 * If the timer is not on the current cpu, we cannot reprogram
-	 * the other cpus clock event device.
-	 */
-	if (base->cpu_base != cpu_base)
-		return;
-
-	/*
-	 * If the hrtimer interrupt is running, then it will
-	 * reevaluate the clock bases and reprogram the clock event
-	 * device. The callbacks are always executed in hard interrupt
-	 * context so we don't need an extra check for a running
-	 * callback.
-	 */
-	if (cpu_base->in_hrtirq)
-		return;
-
-	/*
-	 * CLOCK_REALTIME timer might be requested with an absolute
-	 * expiry time which is less than base->offset. Set it to 0.
-	 */
-	if (expires < 0)
-		expires = 0;
-
-	if (expires >= cpu_base->expires_next)
-		return;
-
-	/* Update the pointer to the next expiring timer */
-	cpu_base->next_timer = timer;
-
-	/*
-	 * If a hang was detected in the last timer interrupt then we
-	 * do not schedule a timer which is earlier than the expiry
-	 * which we enforced in the hang detection. We want the system
-	 * to make progress.
-	 */
-	if (cpu_base->hang_detected)
-		return;
+static bool hrtimer_hres_enabled __read_mostly  = true;
+unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+EXPORT_SYMBOL_GPL(hrtimer_resolution);
 
-	/*
-	 * Program the timer hardware. We enforce the expiry for
-	 * events which are already in the past.
-	 */
-	cpu_base->expires_next = expires;
-	tick_program_event(expires, 1);
+/*
+ * Enable / Disable high resolution mode
+ */
+static int __init setup_hrtimer_hres(char *str)
+{
+	return (kstrtobool(str, &hrtimer_hres_enabled) == 0);
 }
 
+__setup("highres=", setup_hrtimer_hres);
+
 /*
- * Initialize the high resolution related parts of cpu_base
+ * hrtimer_high_res_enabled - query, if the highres mode is enabled
  */
-static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
+static inline int hrtimer_is_hres_enabled(void)
 {
-	base->expires_next = KTIME_MAX;
-	base->hang_detected = 0;
-	base->hres_active = 0;
-	base->next_timer = NULL;
+	return hrtimer_hres_enabled;
 }
 
 /*
@@ -669,7 +686,7 @@ static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-	if (!base->hres_active)
+	if (!__hrtimer_hres_active(base))
 		return;
 
 	raw_spin_lock(&base->lock);
@@ -716,23 +733,102 @@ void clock_was_set_delayed(void)
 
 #else
 
-static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
-static inline int hrtimer_hres_active(void) { return 0; }
 static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline void hrtimer_switch_to_hres(void) { }
-static inline void
-hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
-static inline int hrtimer_reprogram(struct hrtimer *timer,
-				    struct hrtimer_clock_base *base)
-{
-	return 0;
-}
-static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
 static inline void retrigger_next_event(void *arg) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
 /*
+ * When a timer is enqueued and expires earlier than the already enqueued
+ * timers, we have to check, whether it expires earlier than the timer for
+ * which the clock event device was armed.
+ *
+ * Called with interrupts disabled and base->cpu_base.lock held
+ */
+static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	struct hrtimer_clock_base *base = timer->base;
+	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+
+	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
+
+	/*
+	 * CLOCK_REALTIME timer might be requested with an absolute
+	 * expiry time which is less than base->offset. Set it to 0.
+	 */
+	if (expires < 0)
+		expires = 0;
+
+	if (timer->is_soft) {
+		/*
+		 * soft hrtimer could be started on a remote CPU. In this
+		 * case softirq_expires_next needs to be updated on the
+		 * remote CPU. The soft hrtimer will not expire before the
+		 * first hard hrtimer on the remote CPU -
+		 * hrtimer_check_target() prevents this case.
+		 */
+		struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base;
+
+		if (timer_cpu_base->softirq_activated)
+			return;
+
+		if (!ktime_before(expires, timer_cpu_base->softirq_expires_next))
+			return;
+
+		timer_cpu_base->softirq_next_timer = timer;
+		timer_cpu_base->softirq_expires_next = expires;
+
+		if (!ktime_before(expires, timer_cpu_base->expires_next) ||
+		    !reprogram)
+			return;
+	}
+
+	/*
+	 * If the timer is not on the current cpu, we cannot reprogram
+	 * the other cpus clock event device.
+	 */
+	if (base->cpu_base != cpu_base)
+		return;
+
+	/*
+	 * If the hrtimer interrupt is running, then it will
+	 * reevaluate the clock bases and reprogram the clock event
+	 * device. The callbacks are always executed in hard interrupt
+	 * context so we don't need an extra check for a running
+	 * callback.
+	 */
+	if (cpu_base->in_hrtirq)
+		return;
+
+	if (expires >= cpu_base->expires_next)
+		return;
+
+	/* Update the pointer to the next expiring timer */
+	cpu_base->next_timer = timer;
+	cpu_base->expires_next = expires;
+
+	/*
+	 * If hres is not active, hardware does not have to be
+	 * programmed yet.
+	 *
+	 * If a hang was detected in the last timer interrupt then we
+	 * do not schedule a timer which is earlier than the expiry
+	 * which we enforced in the hang detection. We want the system
+	 * to make progress.
+	 */
+	if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
+		return;
+
+	/*
+	 * Program the timer hardware. We enforce the expiry for
+	 * events which are already in the past.
+	 */
+	tick_program_event(expires, 1);
+}
+
+/*
  * Clock realtime was set
  *
  * Change the offset of the realtime clock vs. the monotonic
@@ -837,9 +933,10 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
  * Returns 1 when the new timer is the leftmost timer in the tree.
  */
 static int enqueue_hrtimer(struct hrtimer *timer,
-			   struct hrtimer_clock_base *base)
+			   struct hrtimer_clock_base *base,
+			   enum hrtimer_mode mode)
 {
-	debug_activate(timer);
+	debug_activate(timer, mode);
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
@@ -872,7 +969,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
 	if (!timerqueue_del(&base->active, &timer->node))
 		cpu_base->active_bases &= ~(1 << base->index);
 
-#ifdef CONFIG_HIGH_RES_TIMERS
 	/*
 	 * Note: If reprogram is false we do not update
 	 * cpu_base->next_timer. This happens when we remove the first
@@ -883,7 +979,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
 	 */
 	if (reprogram && timer == cpu_base->next_timer)
 		hrtimer_force_reprogram(cpu_base, 1);
-#endif
 }
 
 /*
@@ -932,22 +1027,36 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
 	return tim;
 }
 
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- */
-void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-			    u64 delta_ns, const enum hrtimer_mode mode)
+static void
+hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram)
 {
-	struct hrtimer_clock_base *base, *new_base;
-	unsigned long flags;
-	int leftmost;
+	ktime_t expires;
 
-	base = lock_hrtimer_base(timer, &flags);
+	/*
+	 * Find the next SOFT expiration.
+	 */
+	expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT);
+
+	/*
+	 * reprogramming needs to be triggered, even if the next soft
+	 * hrtimer expires at the same time than the next hard
+	 * hrtimer. cpu_base->softirq_expires_next needs to be updated!
+	 */
+	if (expires == KTIME_MAX)
+		return;
+
+	/*
+	 * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event()
+	 * cpu_base->*expires_next is only set by hrtimer_reprogram()
+	 */
+	hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram);
+}
+
+static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+				    u64 delta_ns, const enum hrtimer_mode mode,
+				    struct hrtimer_clock_base *base)
+{
+	struct hrtimer_clock_base *new_base;
 
 	/* Remove an active timer from the queue: */
 	remove_hrtimer(timer, base, true);
@@ -962,21 +1071,35 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Switch the timer base, if necessary: */
 	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
 
-	leftmost = enqueue_hrtimer(timer, new_base);
-	if (!leftmost)
-		goto unlock;
+	return enqueue_hrtimer(timer, new_base, mode);
+}
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	timer mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
+ *		softirq based mode is considered for debug purpose only!
+ */
+void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			    u64 delta_ns, const enum hrtimer_mode mode)
+{
+	struct hrtimer_clock_base *base;
+	unsigned long flags;
+
+	/*
+	 * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft
+	 * match.
+	 */
+	WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft);
+
+	base = lock_hrtimer_base(timer, &flags);
+
+	if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base))
+		hrtimer_reprogram(timer, true);
 
-	if (!hrtimer_is_hres_active(timer)) {
-		/*
-		 * Kick to reschedule the next tick to handle the new timer
-		 * on dynticks target.
-		 */
-		if (new_base->cpu_base->nohz_active)
-			wake_up_nohz_cpu(new_base->cpu_base->cpu);
-	} else {
-		hrtimer_reprogram(timer, new_base);
-	}
-unlock:
 	unlock_hrtimer_base(timer, &flags);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
@@ -1074,7 +1197,7 @@ u64 hrtimer_get_next_event(void)
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
 	if (!__hrtimer_hres_active(cpu_base))
-		expires = __hrtimer_get_next_event(cpu_base);
+		expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
@@ -1097,17 +1220,24 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
+	bool softtimer = !!(mode & HRTIMER_MODE_SOFT);
+	int base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
 	struct hrtimer_cpu_base *cpu_base;
-	int base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
 	cpu_base = raw_cpu_ptr(&hrtimer_bases);
 
-	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
+	/*
+	 * POSIX magic: Relative CLOCK_REALTIME timers are not affected by
+	 * clock modifications, so they needs to become CLOCK_MONOTONIC to
+	 * ensure POSIX compliance.
+	 */
+	if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL)
 		clock_id = CLOCK_MONOTONIC;
 
-	base = hrtimer_clockid_to_base(clock_id);
+	base += hrtimer_clockid_to_base(clock_id);
+	timer->is_soft = softtimer;
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
 }
@@ -1116,7 +1246,13 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
  * hrtimer_init - initialize a timer to the given clock
  * @timer:	the timer to be initialized
  * @clock_id:	the clock to be used
- * @mode:	timer mode abs/rel
+ * @mode:       The modes which are relevant for intitialization:
+ *              HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT,
+ *              HRTIMER_MODE_REL_SOFT
+ *
+ *              The PINNED variants of the above can be handed in,
+ *              but the PINNED bit is ignored as pinning happens
+ *              when the hrtimer is started
  */
 void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 		  enum hrtimer_mode mode)
@@ -1135,19 +1271,19 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
  */
 bool hrtimer_active(const struct hrtimer *timer)
 {
-	struct hrtimer_cpu_base *cpu_base;
+	struct hrtimer_clock_base *base;
 	unsigned int seq;
 
 	do {
-		cpu_base = READ_ONCE(timer->base->cpu_base);
-		seq = raw_read_seqcount_begin(&cpu_base->seq);
+		base = READ_ONCE(timer->base);
+		seq = raw_read_seqcount_begin(&base->seq);
 
 		if (timer->state != HRTIMER_STATE_INACTIVE ||
-		    cpu_base->running == timer)
+		    base->running == timer)
 			return true;
 
-	} while (read_seqcount_retry(&cpu_base->seq, seq) ||
-		 cpu_base != READ_ONCE(timer->base->cpu_base));
+	} while (read_seqcount_retry(&base->seq, seq) ||
+		 base != READ_ONCE(timer->base));
 
 	return false;
 }
@@ -1173,7 +1309,8 @@ EXPORT_SYMBOL_GPL(hrtimer_active);
 
 static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 			  struct hrtimer_clock_base *base,
-			  struct hrtimer *timer, ktime_t *now)
+			  struct hrtimer *timer, ktime_t *now,
+			  unsigned long flags)
 {
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
@@ -1181,16 +1318,16 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	lockdep_assert_held(&cpu_base->lock);
 
 	debug_deactivate(timer);
-	cpu_base->running = timer;
+	base->running = timer;
 
 	/*
 	 * Separate the ->running assignment from the ->state assignment.
 	 *
 	 * As with a regular write barrier, this ensures the read side in
-	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * hrtimer_active() cannot observe base->running == NULL &&
 	 * timer->state == INACTIVE.
 	 */
-	raw_write_seqcount_barrier(&cpu_base->seq);
+	raw_write_seqcount_barrier(&base->seq);
 
 	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
 	fn = timer->function;
@@ -1204,15 +1341,15 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 		timer->is_rel = false;
 
 	/*
-	 * Because we run timers from hardirq context, there is no chance
-	 * they get migrated to another cpu, therefore its safe to unlock
-	 * the timer base.
+	 * The timer is marked as running in the CPU base, so it is
+	 * protected against migration to a different CPU even if the lock
+	 * is dropped.
 	 */
-	raw_spin_unlock(&cpu_base->lock);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 	trace_hrtimer_expire_entry(timer, now);
 	restart = fn(timer);
 	trace_hrtimer_expire_exit(timer);
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irq(&cpu_base->lock);
 
 	/*
 	 * Note: We clear the running state after enqueue_hrtimer and
@@ -1225,33 +1362,31 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	 */
 	if (restart != HRTIMER_NORESTART &&
 	    !(timer->state & HRTIMER_STATE_ENQUEUED))
-		enqueue_hrtimer(timer, base);
+		enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS);
 
 	/*
 	 * Separate the ->running assignment from the ->state assignment.
 	 *
 	 * As with a regular write barrier, this ensures the read side in
-	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * hrtimer_active() cannot observe base->running.timer == NULL &&
 	 * timer->state == INACTIVE.
 	 */
-	raw_write_seqcount_barrier(&cpu_base->seq);
+	raw_write_seqcount_barrier(&base->seq);
 
-	WARN_ON_ONCE(cpu_base->running != timer);
-	cpu_base->running = NULL;
+	WARN_ON_ONCE(base->running != timer);
+	base->running = NULL;
 }
 
-static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now,
+				 unsigned long flags, unsigned int active_mask)
 {
-	struct hrtimer_clock_base *base = cpu_base->clock_base;
-	unsigned int active = cpu_base->active_bases;
+	struct hrtimer_clock_base *base;
+	unsigned int active = cpu_base->active_bases & active_mask;
 
-	for (; active; base++, active >>= 1) {
+	for_each_active_base(base, cpu_base, active) {
 		struct timerqueue_node *node;
 		ktime_t basenow;
 
-		if (!(active & 0x01))
-			continue;
-
 		basenow = ktime_add(now, base->offset);
 
 		while ((node = timerqueue_getnext(&base->active))) {
@@ -1274,11 +1409,28 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
 			if (basenow < hrtimer_get_softexpires_tv64(timer))
 				break;
 
-			__run_hrtimer(cpu_base, base, timer, &basenow);
+			__run_hrtimer(cpu_base, base, timer, &basenow, flags);
 		}
 	}
 }
 
+static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	unsigned long flags;
+	ktime_t now;
+
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
+
+	now = hrtimer_update_base(cpu_base);
+	__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT);
+
+	cpu_base->softirq_activated = 0;
+	hrtimer_update_softirq_timer(cpu_base, true);
+
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+}
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 
 /*
@@ -1289,13 +1441,14 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires_next, now, entry_time, delta;
+	unsigned long flags;
 	int retries = 0;
 
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
 	dev->next_event = KTIME_MAX;
 
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
 	cpu_base->in_hrtirq = 1;
@@ -1308,17 +1461,23 @@ retry:
 	 */
 	cpu_base->expires_next = KTIME_MAX;
 
-	__hrtimer_run_queues(cpu_base, now);
+	if (!ktime_before(now, cpu_base->softirq_expires_next)) {
+		cpu_base->softirq_expires_next = KTIME_MAX;
+		cpu_base->softirq_activated = 1;
+		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+	}
+
+	__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
 
 	/* Reevaluate the clock bases for the next expiry */
-	expires_next = __hrtimer_get_next_event(cpu_base);
+	expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 	/*
 	 * Store the new expiry value so the migration code can verify
 	 * against it.
 	 */
 	cpu_base->expires_next = expires_next;
 	cpu_base->in_hrtirq = 0;
-	raw_spin_unlock(&cpu_base->lock);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
 	/* Reprogramming necessary ? */
 	if (!tick_program_event(expires_next, 0)) {
@@ -1339,7 +1498,7 @@ retry:
 	 * Acquire base lock for updating the offsets and retrieving
 	 * the current time.
 	 */
-	raw_spin_lock(&cpu_base->lock);
+	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	now = hrtimer_update_base(cpu_base);
 	cpu_base->nr_retries++;
 	if (++retries < 3)
@@ -1352,7 +1511,8 @@ retry:
 	 */
 	cpu_base->nr_hangs++;
 	cpu_base->hang_detected = 1;
-	raw_spin_unlock(&cpu_base->lock);
+	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+
 	delta = ktime_sub(now, entry_time);
 	if ((unsigned int)delta > cpu_base->max_hang_time)
 		cpu_base->max_hang_time = (unsigned int) delta;
@@ -1394,6 +1554,7 @@ static inline void __hrtimer_peek_ahead_timers(void) { }
 void hrtimer_run_queues(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	unsigned long flags;
 	ktime_t now;