hrtimer: Provide LAZY_REARM mode

The hrtick timer is frequently rearmed before expiry and most of the time
the new expiry is past the armed one. As this happens on every context
switch it becomes expensive with scheduling heavy work loads especially in
virtual machines as the "hardware" reprogamming implies a VM exit.

Add a lazy rearm mode flag which skips the reprogamming if:

    1) The timer was the first expiring timer before the rearm

    2) The new expiry time is farther out than the armed time

This avoids a massive amount of reprogramming operations of the hrtick
timer for the price of eventually taking the alredy armed interrupt for
nothing.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260224163429.408524456@kernel.org

3 files changed, 27 insertions, 1 deletions

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index b5003856fd60..c924bb2498db 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -31,6 +31,13 @@
  *				  soft irq context
  * HRTIMER_MODE_HARD		- Timer callback function will be executed in
  *				  hard irq context even on PREEMPT_RT.
+ * HRTIMER_MODE_LAZY_REARM	- Avoid reprogramming if the timer was the
+ *				  first expiring timer and is moved into the
+ *				  future. Special mode for the HRTICK timer to
+ *				  avoid extensive reprogramming of the hardware,
+ *				  which is expensive in virtual machines. Risks
+ *				  a pointless expiry, but that's better than
+ *				  reprogramming on every context switch,
  */
 enum hrtimer_mode {
 	HRTIMER_MODE_ABS	= 0x00,
@@ -38,6 +45,7 @@ enum hrtimer_mode {
 	HRTIMER_MODE_PINNED	= 0x02,
 	HRTIMER_MODE_SOFT	= 0x04,
 	HRTIMER_MODE_HARD	= 0x08,
+	HRTIMER_MODE_LAZY_REARM	= 0x10,
 
 	HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
 	HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h
index 8fbbb6bdf7a1..64381c64cdbd 100644
--- a/include/linux/hrtimer_types.h
+++ b/include/linux/hrtimer_types.h
@@ -33,6 +33,8 @@ enum hrtimer_restart {
  * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
  * @is_hard:	Set if hrtimer will be expired in hard interrupt context
  *		even on RT.
+ * @is_lazy:	Set if the timer is frequently rearmed to avoid updates
+ *		of the clock event device
  *
  * The hrtimer structure must be initialized by hrtimer_setup()
  */
@@ -45,6 +47,7 @@ struct hrtimer {
 	u8				is_rel;
 	u8				is_soft;
 	u8				is_hard;
+	u8				is_lazy;
 };
 
 #endif /* _LINUX_HRTIMER_TYPES_H */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 67917ce696d4..e54f8b59f6b4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1152,7 +1152,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
 	 * an superfluous call to hrtimer_force_reprogram() on the
 	 * remote cpu later on if the same timer gets enqueued again.
 	 */
-	if (reprogram && timer == cpu_base->next_timer)
+	if (reprogram && timer == cpu_base->next_timer && !timer->is_lazy)
 		hrtimer_force_reprogram(cpu_base, 1);
 }
 
@@ -1322,6 +1322,20 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	}
 
 	/*
+	 * Special case for the HRTICK timer. It is frequently rearmed and most
+	 * of the time moves the expiry into the future. That's expensive in
+	 * virtual machines and it's better to take the pointless already armed
+	 * interrupt than reprogramming the hardware on every context switch.
+	 *
+	 * If the new expiry is before the armed time, then reprogramming is
+	 * required.
+	 */
+	if (timer->is_lazy) {
+		if (new_base->cpu_base->expires_next <= hrtimer_get_expires(timer))
+			return 0;
+	}
+
+	/*
 	 * Timer was forced to stay on the current CPU to avoid
 	 * reprogramming on removal and enqueue. Force reprogram the
 	 * hardware by evaluating the new first expiring timer.
@@ -1675,6 +1689,7 @@ static void __hrtimer_setup(struct hrtimer *timer,
 	base += hrtimer_clockid_to_base(clock_id);
 	timer->is_soft = softtimer;
 	timer->is_hard = !!(mode & HRTIMER_MODE_HARD);
+	timer->is_lazy = !!(mode & HRTIMER_MODE_LAZY_REARM);
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);