hrtimer: Avoid re-evaluation when nothing changed

Most times there is no change between hrtimer_interrupt() deferring the rearm
and the invocation of hrtimer_rearm_deferred(). In those cases it's a pointless
exercise to re-evaluate the next expiring timer.

Cache the required data and use it if nothing changed.

Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260224163431.338569372@kernel.org

diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h
index 2c3bdbd562d22cd19d520a7432b50677afad9c05..b6846efec21079871c6a6b68719528e4486b242f 100644 (file)
--- a/include/linux/hrtimer_defs.h
+++ b/include/linux/hrtimer_defs.h
@@ -47,32 +47,31 @@ enum  hrtimer_base_type {
 
 /**
  * struct hrtimer_cpu_base - the per cpu clock bases
- * @lock:              lock protecting the base and associated clock bases
- *                     and timers
- * @cpu:               cpu number
- * @active_bases:      Bitfield to mark bases with active timers
- * @clock_was_set_seq: Sequence counter of clock was set events
- * @hres_active:       State of high resolution mode
- * @deferred_rearm:    A deferred rearm is pending
- * @hang_detected:     The last hrtimer interrupt detected a hang
- * @softirq_activated: displays, if the softirq is raised - update of softirq
- *                     related settings is not required then.
- * @nr_events:         Total number of hrtimer interrupt events
- * @nr_retries:                Total number of hrtimer interrupt retries
- * @nr_hangs:          Total number of hrtimer interrupt hangs
- * @max_hang_time:     Maximum time spent in hrtimer_interrupt
- * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
- *                      expired
- * @online:            CPU is online from an hrtimers point of view
- * @timer_waiters:     A hrtimer_cancel() invocation waits for the timer
- *                     callback to finish.
- * @expires_next:      absolute time of the next event, is required for remote
- *                     hrtimer enqueue; it is the total first expiry time (hard
- *                     and soft hrtimer are taken into account)
- * @next_timer:                Pointer to the first expiring timer
- * @softirq_expires_next: Time to check, if soft queues needs also to be expired
- * @softirq_next_timer: Pointer to the first expiring softirq based timer
- * @clock_base:                array of clock bases for this cpu
+ * @lock:                      lock protecting the base and associated clock bases and timers
+ * @cpu:                       cpu number
+ * @active_bases:              Bitfield to mark bases with active timers
+ * @clock_was_set_seq:         Sequence counter of clock was set events
+ * @hres_active:               State of high resolution mode
+ * @deferred_rearm:            A deferred rearm is pending
+ * @deferred_needs_update:     The deferred rearm must re-evaluate the first timer
+ * @hang_detected:             The last hrtimer interrupt detected a hang
+ * @softirq_activated:         displays, if the softirq is raised - update of softirq
+ *                             related settings is not required then.
+ * @nr_events:                 Total number of hrtimer interrupt events
+ * @nr_retries:                        Total number of hrtimer interrupt retries
+ * @nr_hangs:                  Total number of hrtimer interrupt hangs
+ * @max_hang_time:             Maximum time spent in hrtimer_interrupt
+ * @softirq_expiry_lock:       Lock which is taken while softirq based hrtimer are expired
+ * @online:                    CPU is online from an hrtimers point of view
+ * @timer_waiters:             A hrtimer_cancel() waiters for the timer callback to finish.
+ * @expires_next:              Absolute time of the next event, is required for remote
+ *                             hrtimer enqueue; it is the total first expiry time (hard
+ *                             and soft hrtimer are taken into account)
+ * @next_timer:                        Pointer to the first expiring timer
+ * @softirq_expires_next:      Time to check, if soft queues needs also to be expired
+ * @softirq_next_timer:                Pointer to the first expiring softirq based timer
+ * @deferred_expires_next:     Cached expires next value for deferred rearm
+ * @clock_base:                        Array of clock bases for this cpu
  *
  * Note: next_timer is just an optimization for __remove_hrtimer().
  *      Do not dereference the pointer because it is not reliable on
@@ -85,6 +84,7 @@ struct hrtimer_cpu_base {
        unsigned int                    clock_was_set_seq;
        bool                            hres_active;
        bool                            deferred_rearm;
+       bool                            deferred_needs_update;
        bool                            hang_detected;
        bool                            softirq_activated;
        bool                            online;
@@ -102,6 +102,7 @@ struct hrtimer_cpu_base {
        struct hrtimer                  *next_timer;
        ktime_t                         softirq_expires_next;
        struct hrtimer                  *softirq_next_timer;
+       ktime_t                         deferred_expires_next;
        struct hrtimer_clock_base       clock_base[HRTIMER_MAX_CLOCK_BASES];
        call_single_data_t              csd;
 } ____cacheline_aligned;

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 2e5f0e292efb34f8a3449854adb94b6024835d8e..e9592cb1e39ab6f0965e224dbac032a5ec42a141 100644 (file)
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -919,8 +919,10 @@ static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int act
                return false;
 
        /* If a deferred rearm is pending the remote CPU will take care of it */
-       if (cpu_base->deferred_rearm)
+       if (cpu_base->deferred_rearm) {
+               cpu_base->deferred_needs_update = true;
                return false;
+       }
 
        /*
         * Walk the affected clock bases and check whether the first expiring
@@ -1141,7 +1143,12 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *b
         * a local timer is removed to be immediately restarted. That's handled
         * at the call site.
         */
-       if (reprogram && timer == cpu_base->next_timer && !timer->is_lazy)
+       if (!reprogram || timer != cpu_base->next_timer || timer->is_lazy)
+               return;
+
+       if (cpu_base->deferred_rearm)
+               cpu_base->deferred_needs_update = true;
+       else
                hrtimer_force_reprogram(cpu_base, /* skip_equal */ true);
 }
 
@@ -1328,8 +1335,10 @@ static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 del
        }
 
        /* If a deferred rearm is pending skip reprogramming the device */
-       if (cpu_base->deferred_rearm)
+       if (cpu_base->deferred_rearm) {
+               cpu_base->deferred_needs_update = true;
                return false;
+       }
 
        if (!was_first || cpu_base != this_cpu_base) {
                /*
@@ -1939,8 +1948,7 @@ static __latent_entropy void hrtimer_run_softirq(void)
  * Very similar to hrtimer_force_reprogram(), except it deals with
  * deferred_rearm and hang_detected.
  */
-static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now,
-                         ktime_t expires_next, bool deferred)
+static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t expires_next, bool deferred)
 {
        cpu_base->expires_next = expires_next;
        cpu_base->deferred_rearm = false;
@@ -1950,7 +1958,7 @@ static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now,
                 * Give the system a chance to do something else than looping
                 * on hrtimer interrupts.
                 */
-               expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
+               expires_next = ktime_add_ns(ktime_get(), 100 * NSEC_PER_MSEC);
                cpu_base->hang_detected = false;
        }
        hrtimer_rearm_event(expires_next, deferred);
@@ -1960,27 +1968,36 @@ static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now,
 void __hrtimer_rearm_deferred(void)
 {
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-       ktime_t now, expires_next;
+       ktime_t expires_next;
 
        if (!cpu_base->deferred_rearm)
                return;
 
        guard(raw_spinlock)(&cpu_base->lock);
-       now = hrtimer_update_base(cpu_base);
-       expires_next = hrtimer_update_next_event(cpu_base);
-       hrtimer_rearm(cpu_base, now, expires_next, true);
+       if (cpu_base->deferred_needs_update) {
+               hrtimer_update_base(cpu_base);
+               expires_next = hrtimer_update_next_event(cpu_base);
+       } else {
+               /* No timer added/removed. Use the cached value */
+               expires_next = cpu_base->deferred_expires_next;
+       }
+       hrtimer_rearm(cpu_base, expires_next, true);
 }
 
 static __always_inline void
-hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now, ktime_t expires_next)
+hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t expires_next)
 {
+       /* hrtimer_interrupt() just re-evaluated the first expiring timer */
+       cpu_base->deferred_needs_update = false;
+       /* Cache the expiry time */
+       cpu_base->deferred_expires_next = expires_next;
        set_thread_flag(TIF_HRTIMER_REARM);
 }
 #else  /* CONFIG_HRTIMER_REARM_DEFERRED */
 static __always_inline void
-hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now, ktime_t expires_next)
+hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t expires_next)
 {
-       hrtimer_rearm(cpu_base, now, expires_next, false);
+       hrtimer_rearm(cpu_base, expires_next, false);
 }
 #endif  /* !CONFIG_HRTIMER_REARM_DEFERRED */
 
@@ -2041,7 +2058,7 @@ retry:
                cpu_base->hang_detected = true;
        }
 
-       hrtimer_interrupt_rearm(cpu_base, now, expires_next);
+       hrtimer_interrupt_rearm(cpu_base, expires_next);
        raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 }