[GIT pull] timers/urgent for v7.0
From: Thomas Gleixner
Date: Sun Apr 12 2026 - 09:42:35 EST
Linus,
please pull the latest timers/urgent branch from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2026-04-12
up to: d6e152d905bd: clockevents: Prevent timer interrupt starvation
Two fixes for the time/timers subsystem:
- Invert the inverted fastpath decision in check_tick_dependency(), which
prevents NOHZ full to stop the tick. That's a regression introduced in
the 7.0 merge window.
- Prevent a unpriviledged DoS in the clockevents code, where user space
can starve the timer interrupt by arming a timerfd or posix interval
timer in a tight loop with an absolute expiry time in the past. The
fix turned out to be incomplete and was was amended yesterday to make
it work on some 20 years old AMD machines as well. All issues with it
have been confirmed to be resolved by various reporters.
Thanks,
tglx
------------------>
Josh Snyder (1):
tick/nohz: Fix inverted return value in check_tick_dependency() fast path
Thomas Gleixner (1):
clockevents: Prevent timer interrupt starvation
include/linux/clockchips.h | 2 ++
kernel/time/clockevents.c | 27 +++++++++++++++++++--------
kernel/time/hrtimer.c | 1 +
kernel/time/tick-broadcast.c | 8 +++++++-
kernel/time/tick-common.c | 1 +
kernel/time/tick-sched.c | 3 ++-
6 files changed, 32 insertions(+), 10 deletions(-)
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index b0df28ddd394..50cdc9da8d32 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -80,6 +80,7 @@ enum clock_event_state {
* @shift: nanoseconds to cycles divisor (power of two)
* @state_use_accessors:current state of the device, assigned by the core code
* @features: features
+ * @next_event_forced: True if the last programming was a forced event
* @retries: number of forced programming retries
* @set_state_periodic: switch state to periodic
* @set_state_oneshot: switch state to oneshot
@@ -108,6 +109,7 @@ struct clock_event_device {
u32 shift;
enum clock_event_state state_use_accessors;
unsigned int features;
+ unsigned int next_event_forced;
unsigned long retries;
int (*set_state_periodic)(struct clock_event_device *);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index eaae1ce9f060..38570998a19b 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -172,6 +172,7 @@ void clockevents_shutdown(struct clock_event_device *dev)
{
clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
dev->next_event = KTIME_MAX;
+ dev->next_event_forced = 0;
}
/**
@@ -305,7 +306,6 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
{
unsigned long long clc;
int64_t delta;
- int rc;
if (WARN_ON_ONCE(expires < 0))
return -ETIME;
@@ -324,16 +324,27 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
return dev->set_next_ktime(expires, dev);
delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
- if (delta <= 0)
- return force ? clockevents_program_min_delta(dev) : -ETIME;
- delta = min(delta, (int64_t) dev->max_delta_ns);
- delta = max(delta, (int64_t) dev->min_delta_ns);
+ /* Required for tick_periodic() during early boot */
+ if (delta <= 0 && !force)
+ return -ETIME;
+
+ if (delta > (int64_t)dev->min_delta_ns) {
+ delta = min(delta, (int64_t) dev->max_delta_ns);
+ clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+ if (!dev->set_next_event((unsigned long) clc, dev))
+ return 0;
+ }
- clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
- rc = dev->set_next_event((unsigned long) clc, dev);
+ if (dev->next_event_forced)
+ return 0;
- return (rc && force) ? clockevents_program_min_delta(dev) : rc;
+ if (dev->set_next_event(dev->min_delta_ticks, dev)) {
+ if (!force || clockevents_program_min_delta(dev))
+ return -ETIME;
+ }
+ dev->next_event_forced = 1;
+ return 0;
}
/*
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 860af7a58428..1e37142fe52f 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1888,6 +1888,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event = KTIME_MAX;
+ dev->next_event_forced = 0;
raw_spin_lock_irqsave(&cpu_base->lock, flags);
entry_time = now = hrtimer_update_base(cpu_base);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f63c65881364..7e57fa31ee26 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -76,8 +76,10 @@ const struct clock_event_device *tick_get_wakeup_device(int cpu)
*/
static void tick_broadcast_start_periodic(struct clock_event_device *bc)
{
- if (bc)
+ if (bc) {
+ bc->next_event_forced = 0;
tick_setup_periodic(bc, 1);
+ }
}
/*
@@ -403,6 +405,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
bool bc_local;
raw_spin_lock(&tick_broadcast_lock);
+ tick_broadcast_device.evtdev->next_event_forced = 0;
/* Handle spurious interrupts gracefully */
if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) {
@@ -696,6 +699,7 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
raw_spin_lock(&tick_broadcast_lock);
dev->next_event = KTIME_MAX;
+ tick_broadcast_device.evtdev->next_event_forced = 0;
next_event = KTIME_MAX;
cpumask_clear(tmpmask);
now = ktime_get();
@@ -1063,6 +1067,7 @@ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc,
bc->event_handler = tick_handle_oneshot_broadcast;
+ bc->next_event_forced = 0;
bc->next_event = KTIME_MAX;
/*
@@ -1175,6 +1180,7 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
}
/* This moves the broadcast assignment to this CPU: */
+ bc->next_event_forced = 0;
clockevents_program_event(bc, bc->next_event, 1);
}
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index d305d8521896..6a9198a4279b 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -110,6 +110,7 @@ void tick_handle_periodic(struct clock_event_device *dev)
int cpu = smp_processor_id();
ktime_t next = dev->next_event;
+ dev->next_event_forced = 0;
tick_periodic(cpu);
/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f7907fadd63f..d1f27df1e60e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -345,7 +345,7 @@ static bool check_tick_dependency(atomic_t *dep)
int val = atomic_read(dep);
if (likely(!tracepoint_enabled(tick_stop)))
- return !val;
+ return !!val;
if (val & TICK_DEP_MASK_POSIX_TIMER) {
trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
@@ -1513,6 +1513,7 @@ static void tick_nohz_lowres_handler(struct clock_event_device *dev)
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
dev->next_event = KTIME_MAX;
+ dev->next_event_forced = 0;
if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART))
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);