[tip: sched/hrtick] hrtimer: Push reprogramming timers into the interrupt return path
From: tip-bot2 for Peter Zijlstra
Date: Sat Feb 28 2026 - 10:41:21 EST
The following commit has been merged into the sched/hrtick branch of tip:
Commit-ID: 15dd3a9488557d3e6ebcecacab79f4e56b69ab54
Gitweb: https://git.kernel.org/tip/15dd3a9488557d3e6ebcecacab79f4e56b69ab54
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Tue, 24 Feb 2026 17:38:18 +01:00
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Fri, 27 Feb 2026 16:40:14 +01:00
hrtimer: Push reprogramming timers into the interrupt return path
Currently hrtimer_interrupt() runs expired timers, which can re-arm
themselves, after which it computes the next expiration time and
re-programs the hardware.
However, things like HRTICK, a highres timer driving preemption, cannot
re-arm itself at the point of running, since the next task has not been
determined yet. The schedule() in the interrupt return path will switch to
the next task, which then causes a new hrtimer to be programmed.
This then results in reprogramming the hardware at least twice, once after
running the timers, and once upon selecting the new task.
Notably, *both* events happen in the interrupt.
By pushing the hrtimer reprogram all the way into the interrupt return
path, it runs after schedule() picks the new task and the double reprogram
can be avoided.
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://patch.msgid.link/20260224163431.273488269@xxxxxxxxxx
---
include/asm-generic/thread_info_tif.h | 5 +-
include/linux/hrtimer_rearm.h | 72 ++++++++++++++++++++++++--
kernel/time/Kconfig | 4 +-
kernel/time/hrtimer.c | 38 ++++++++++++--
4 files changed, 107 insertions(+), 12 deletions(-)
diff --git a/include/asm-generic/thread_info_tif.h b/include/asm-generic/thread_info_tif.h
index da1610a..528e6fc 100644
--- a/include/asm-generic/thread_info_tif.h
+++ b/include/asm-generic/thread_info_tif.h
@@ -41,11 +41,14 @@
#define _TIF_PATCH_PENDING BIT(TIF_PATCH_PENDING)
#ifdef HAVE_TIF_RESTORE_SIGMASK
-# define TIF_RESTORE_SIGMASK 10 // Restore signal mask in do_signal() */
+# define TIF_RESTORE_SIGMASK 10 // Restore signal mask in do_signal()
# define _TIF_RESTORE_SIGMASK BIT(TIF_RESTORE_SIGMASK)
#endif
#define TIF_RSEQ 11 // Run RSEQ fast path
#define _TIF_RSEQ BIT(TIF_RSEQ)
+#define TIF_HRTIMER_REARM 12 // re-arm the timer
+#define _TIF_HRTIMER_REARM BIT(TIF_HRTIMER_REARM)
+
#endif /* _ASM_GENERIC_THREAD_INFO_TIF_H_ */
diff --git a/include/linux/hrtimer_rearm.h b/include/linux/hrtimer_rearm.h
index 6293076..a6f2e5d 100644
--- a/include/linux/hrtimer_rearm.h
+++ b/include/linux/hrtimer_rearm.h
@@ -3,12 +3,74 @@
#define _LINUX_HRTIMER_REARM_H
#ifdef CONFIG_HRTIMER_REARM_DEFERRED
-static __always_inline void __hrtimer_rearm_deferred(void) { }
-static __always_inline void hrtimer_rearm_deferred(void) { }
-static __always_inline void hrtimer_rearm_deferred_tif(unsigned long tif_work) { }
+#include <linux/thread_info.h>
+
+void __hrtimer_rearm_deferred(void);
+
+/*
+ * This is purely CPU local, so check the TIF bit first to avoid the overhead of
+ * the atomic test_and_clear_bit() operation for the common case where the bit
+ * is not set.
+ */
+static __always_inline bool hrtimer_test_and_clear_rearm_deferred_tif(unsigned long tif_work)
+{
+ lockdep_assert_irqs_disabled();
+
+ if (unlikely(tif_work & _TIF_HRTIMER_REARM)) {
+ clear_thread_flag(TIF_HRTIMER_REARM);
+ return true;
+ }
+ return false;
+}
+
+#define TIF_REARM_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_HRTIMER_REARM)
+
+/* Invoked from the exit to user before invoking exit_to_user_mode_loop() */
static __always_inline bool
-hrtimer_rearm_deferred_user_irq(unsigned long *tif_work, const unsigned long tif_mask) { return false; }
-static __always_inline bool hrtimer_test_and_clear_rearm_deferred(void) { return false; }
+hrtimer_rearm_deferred_user_irq(unsigned long *tif_work, const unsigned long tif_mask)
+{
+ /* Help the compiler to optimize the function out for syscall returns */
+ if (!(tif_mask & _TIF_HRTIMER_REARM))
+ return false;
+ /*
+ * Rearm the timer if none of the resched flags is set before going into
+ * the loop which re-enables interrupts.
+ */
+ if (unlikely((*tif_work & TIF_REARM_MASK) == _TIF_HRTIMER_REARM)) {
+ clear_thread_flag(TIF_HRTIMER_REARM);
+ __hrtimer_rearm_deferred();
+ /* Don't go into the loop if HRTIMER_REARM was the only flag */
+ *tif_work &= ~TIF_HRTIMER_REARM;
+ return !*tif_work;
+ }
+ return false;
+}
+
+/* Invoked from the time slice extension decision function */
+static __always_inline void hrtimer_rearm_deferred_tif(unsigned long tif_work)
+{
+ if (hrtimer_test_and_clear_rearm_deferred_tif(tif_work))
+ __hrtimer_rearm_deferred();
+}
+
+/*
+ * This is to be called on all irqentry_exit() paths that will enable
+ * interrupts.
+ */
+static __always_inline void hrtimer_rearm_deferred(void)
+{
+ hrtimer_rearm_deferred_tif(read_thread_flags());
+}
+
+/*
+ * Invoked from the scheduler on entry to __schedule() so it can defer
+ * rearming after the load balancing callbacks which might change hrtick.
+ */
+static __always_inline bool hrtimer_test_and_clear_rearm_deferred(void)
+{
+ return hrtimer_test_and_clear_rearm_deferred_tif(read_thread_flags());
+}
+
#else /* CONFIG_HRTIMER_REARM_DEFERRED */
static __always_inline void __hrtimer_rearm_deferred(void) { }
static __always_inline void hrtimer_rearm_deferred(void) { }
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index b95bfee..6d6aace 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -60,7 +60,9 @@ config GENERIC_CMOS_UPDATE
# Deferred rearming of the hrtimer interrupt
config HRTIMER_REARM_DEFERRED
- def_bool n
+ def_bool y
+ depends on GENERIC_ENTRY && HAVE_GENERIC_TIF_BITS
+ depends on HIGH_RES_TIMERS && SCHED_HRTICK
# Select to handle posix CPU timers from task_work
# and not from the timer interrupt context
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 6f05d25..2e5f0e2 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1939,10 +1939,9 @@ 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)
+static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now,
+ ktime_t expires_next, bool deferred)
{
- ktime_t expires_next = hrtimer_update_next_event(cpu_base);
-
cpu_base->expires_next = expires_next;
cpu_base->deferred_rearm = false;
@@ -1954,9 +1953,37 @@ static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now)
expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
cpu_base->hang_detected = false;
}
- hrtimer_rearm_event(expires_next, false);
+ hrtimer_rearm_event(expires_next, deferred);
+}
+
+#ifdef CONFIG_HRTIMER_REARM_DEFERRED
+void __hrtimer_rearm_deferred(void)
+{
+ struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+ ktime_t now, 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);
}
+static __always_inline void
+hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t now, ktime_t 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_rearm(cpu_base, now, expires_next, false);
+}
+#endif /* !CONFIG_HRTIMER_REARM_DEFERRED */
+
/*
* High resolution timer interrupt
* Called with interrupts disabled
@@ -2014,9 +2041,10 @@ retry:
cpu_base->hang_detected = true;
}
- hrtimer_rearm(cpu_base, now);
+ hrtimer_interrupt_rearm(cpu_base, now, expires_next);
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
}
+
#endif /* !CONFIG_HIGH_RES_TIMERS */
/*