summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/futex/core.c5
-rw-r--r--kernel/futex/futex.h11
-rw-r--r--kernel/futex/pi.c2
-rw-r--r--kernel/futex/waitwake.c4
-rw-r--r--kernel/kthread.c4
-rw-r--r--kernel/sched/debug.c2
-rw-r--r--kernel/sched/fair.c19
-rw-r--r--kernel/seccomp.c12
-rw-r--r--kernel/time/clocksource.c9
-rw-r--r--kernel/time/hrtimer.c125
-rw-r--r--kernel/time/timer_migration.c10
-rw-r--r--kernel/trace/trace_functions_graph.c2
12 files changed, 159 insertions, 46 deletions
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index ebdd76b4ecbb..3db8567f5a44 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -532,7 +532,8 @@ void futex_q_unlock(struct futex_hash_bucket *hb)
futex_hb_waiters_dec(hb);
}
-void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
+void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+ struct task_struct *task)
{
int prio;
@@ -548,7 +549,7 @@ void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
plist_node_init(&q->list, prio);
plist_add(&q->list, &hb->chain);
- q->task = current;
+ q->task = task;
}
/**
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 99b32e728c4a..6b2f4c7eb720 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -285,13 +285,15 @@ static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
}
extern void __futex_unqueue(struct futex_q *q);
-extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb);
+extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+ struct task_struct *task);
extern int futex_unqueue(struct futex_q *q);
/**
* futex_queue() - Enqueue the futex_q on the futex_hash_bucket
* @q: The futex_q to enqueue
* @hb: The destination hash bucket
+ * @task: Task queueing this futex
*
* The hb->lock must be held by the caller, and is released here. A call to
* futex_queue() is typically paired with exactly one call to futex_unqueue(). The
@@ -299,11 +301,14 @@ extern int futex_unqueue(struct futex_q *q);
* or nothing if the unqueue is done as part of the wake process and the unqueue
* state is implicit in the state of woken task (see futex_wait_requeue_pi() for
* an example).
+ *
+ * Note that @task may be NULL, for async usage of futexes.
*/
-static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
+static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+ struct task_struct *task)
__releases(&hb->lock)
{
- __futex_queue(q, hb);
+ __futex_queue(q, hb, task);
spin_unlock(&hb->lock);
}
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index daea650b16f5..7a941845f7ee 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -982,7 +982,7 @@ retry_private:
/*
* Only actually queue now that the atomic ops are done:
*/
- __futex_queue(&q, hb);
+ __futex_queue(&q, hb, current);
if (trylock) {
ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index eb86a7ade06a..25877d4f2f8f 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -349,7 +349,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
* access to the hash list and forcing another memory barrier.
*/
set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
- futex_queue(q, hb);
+ futex_queue(q, hb, current);
/* Arm the timer */
if (timeout)
@@ -460,7 +460,7 @@ retry:
* next futex. Queue each futex at this moment so hb can
* be unlocked.
*/
- futex_queue(q, hb);
+ futex_queue(q, hb, current);
continue;
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4005b13ebd7f..5dc5b0d7238e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -859,7 +859,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
struct kthread *kthread = to_kthread(p);
cpumask_var_t affinity;
unsigned long flags;
- int ret;
+ int ret = 0;
if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) {
WARN_ON(1);
@@ -892,7 +892,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
out:
free_cpumask_var(affinity);
- return 0;
+ return ret;
}
/*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fd7e85220715..ef047add7f9e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1262,6 +1262,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
if (task_has_dl_policy(p)) {
P(dl.runtime);
P(dl.deadline);
+ } else if (fair_policy(p->policy)) {
+ P(se.slice);
}
#ifdef CONFIG_SCHED_CLASS_EXT
__PS("ext.enabled", task_on_scx(p));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ce2e94ccad0c..1c0ef435a7aa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5385,6 +5385,15 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
static void set_delayed(struct sched_entity *se)
{
se->sched_delayed = 1;
+
+ /*
+ * Delayed se of cfs_rq have no tasks queued on them.
+ * Do not adjust h_nr_runnable since dequeue_entities()
+ * will account it for blocked tasks.
+ */
+ if (!entity_is_task(se))
+ return;
+
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -5397,6 +5406,16 @@ static void set_delayed(struct sched_entity *se)
static void clear_delayed(struct sched_entity *se)
{
se->sched_delayed = 0;
+
+ /*
+ * Delayed se of cfs_rq have no tasks queued on them.
+ * Do not adjust h_nr_runnable since a dequeue has
+ * already accounted for it or an enqueue of a task
+ * below it will account for it in enqueue_task_fair().
+ */
+ if (!entity_is_task(se))
+ return;
+
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index f59381c4a2ff..7bbb408431eb 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -749,6 +749,15 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
if (WARN_ON_ONCE(!fprog))
return false;
+ /* Our single exception to filtering. */
+#ifdef __NR_uretprobe
+#ifdef SECCOMP_ARCH_COMPAT
+ if (sd->arch == SECCOMP_ARCH_NATIVE)
+#endif
+ if (sd->nr == __NR_uretprobe)
+ return true;
+#endif
+
for (pc = 0; pc < fprog->len; pc++) {
struct sock_filter *insn = &fprog->filter[pc];
u16 code = insn->code;
@@ -1023,6 +1032,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
*/
static const int mode1_syscalls[] = {
__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
+#ifdef __NR_uretprobe
+ __NR_uretprobe,
+#endif
-1, /* negative terminated */
};
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 7304d7cf47f2..2a7802ec480c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -373,16 +373,18 @@ void clocksource_verify_percpu(struct clocksource *cs)
cpumask_clear(&cpus_ahead);
cpumask_clear(&cpus_behind);
cpus_read_lock();
- preempt_disable();
+ migrate_disable();
clocksource_verify_choose_cpus();
if (cpumask_empty(&cpus_chosen)) {
- preempt_enable();
+ migrate_enable();
cpus_read_unlock();
pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
return;
}
testcpu = smp_processor_id();
- pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+ pr_info("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n",
+ cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+ preempt_disable();
for_each_cpu(cpu, &cpus_chosen) {
if (cpu == testcpu)
continue;
@@ -402,6 +404,7 @@ void clocksource_verify_percpu(struct clocksource *cs)
cs_nsec_min = cs_nsec;
}
preempt_enable();
+ migrate_enable();
cpus_read_unlock();
if (!cpumask_empty(&cpus_ahead))
pr_warn(" CPUs %*pbl ahead of CPU %d for clocksource %s.\n",
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index f6d8df94045c..deb1aa32814e 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -58,6 +58,8 @@
#define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT)
#define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
+static void retrigger_next_event(void *arg);
+
/*
* The timer bases:
*
@@ -111,7 +113,8 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
},
- }
+ },
+ .csd = CSD_INIT(retrigger_next_event, NULL)
};
static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
@@ -124,6 +127,14 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
[CLOCK_TAI] = HRTIMER_BASE_TAI,
};
+static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base)
+{
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ return true;
+ else
+ return likely(base->online);
+}
+
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
@@ -145,11 +156,6 @@ static struct hrtimer_cpu_base migration_cpu_base = {
#define migration_base migration_cpu_base.clock_base[0]
-static inline bool is_migration_base(struct hrtimer_clock_base *base)
-{
- return base == &migration_base;
-}
-
/*
* We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
* means that all timers which are tied to this base via timer->base are
@@ -183,27 +189,54 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
}
/*
- * 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.
+ * Check if the elected target is suitable considering its next
+ * event and the hotplug state of the current CPU.
+ *
+ * If the elected target is remote and its next event is after the timer
+ * to queue, then a remote reprogram is necessary. However there is no
+ * guarantee the IPI handling the operation would arrive in time to meet
+ * the high resolution deadline. In this case the local CPU becomes a
+ * preferred target, unless it is offline.
+ *
+ * High and low resolution modes are handled the same way for simplicity.
*
* Called with cpu_base->lock of target cpu held.
*/
-static int
-hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base,
+ struct hrtimer_cpu_base *new_cpu_base,
+ struct hrtimer_cpu_base *this_cpu_base)
{
ktime_t expires;
+ /*
+ * The local CPU clockevent can be reprogrammed. Also get_target_base()
+ * guarantees it is online.
+ */
+ if (new_cpu_base == this_cpu_base)
+ return true;
+
+ /*
+ * The offline local CPU can't be the default target if the
+ * next remote target event is after this timer. Keep the
+ * elected new base. An IPI will we issued to reprogram
+ * it as a last resort.
+ */
+ if (!hrtimer_base_is_online(this_cpu_base))
+ return true;
+
expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
- return expires < new_base->cpu_base->expires_next;
+
+ return expires >= new_base->cpu_base->expires_next;
}
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
- int pinned)
+static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned)
{
+ if (!hrtimer_base_is_online(base)) {
+ int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER));
+
+ return &per_cpu(hrtimer_bases, cpu);
+ }
+
#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());
@@ -254,8 +287,8 @@ again:
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
- if (new_cpu_base != this_cpu_base &&
- hrtimer_check_target(timer, new_base)) {
+ if (!hrtimer_suitable_target(timer, new_base, new_cpu_base,
+ this_cpu_base)) {
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
new_cpu_base = this_cpu_base;
@@ -264,8 +297,7 @@ again:
}
WRITE_ONCE(timer->base, new_base);
} else {
- if (new_cpu_base != this_cpu_base &&
- hrtimer_check_target(timer, new_base)) {
+ if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) {
new_cpu_base = this_cpu_base;
goto again;
}
@@ -275,11 +307,6 @@ again:
#else /* CONFIG_SMP */
-static inline bool is_migration_base(struct hrtimer_clock_base *base)
-{
- return false;
-}
-
static inline struct hrtimer_clock_base *
lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
__acquires(&timer->base->cpu_base->lock)
@@ -716,8 +743,6 @@ static inline int hrtimer_is_hres_enabled(void)
return hrtimer_hres_enabled;
}
-static void retrigger_next_event(void *arg);
-
/*
* Switch to high resolution mode
*/
@@ -1205,6 +1230,7 @@ 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_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases);
struct hrtimer_clock_base *new_base;
bool force_local, first;
@@ -1216,10 +1242,16 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
* and enforce reprogramming after it is queued no matter whether
* it is the new first expiring timer again or not.
*/
- force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
+ force_local = base->cpu_base == this_cpu_base;
force_local &= base->cpu_base->next_timer == timer;
/*
+ * Don't force local queuing if this enqueue happens on a unplugged
+ * CPU after hrtimer_cpu_dying() has been invoked.
+ */
+ force_local &= this_cpu_base->online;
+
+ /*
* Remove an active timer from the queue. In case it is not queued
* on the current CPU, make sure that remove_hrtimer() updates the
* remote data correctly.
@@ -1248,8 +1280,27 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
}
first = enqueue_hrtimer(timer, new_base, mode);
- if (!force_local)
- return first;
+ if (!force_local) {
+ /*
+ * If the current CPU base is online, then the timer is
+ * never queued on a remote CPU if it would be the first
+ * expiring timer there.
+ */
+ if (hrtimer_base_is_online(this_cpu_base))
+ return first;
+
+ /*
+ * Timer was enqueued remote because the current base is
+ * already offline. If the timer is the first to expire,
+ * kick the remote CPU to reprogram the clock event.
+ */
+ if (first) {
+ struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base;
+
+ smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd);
+ }
+ return 0;
+ }
/*
* Timer was forced to stay on the current CPU to avoid
@@ -1370,6 +1421,18 @@ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base,
}
}
+#ifdef CONFIG_SMP
+static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
+{
+ return base == &migration_base;
+}
+#else
+static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
+{
+ return false;
+}
+#endif
+
/*
* This function is called on PREEMPT_RT kernels when the fast path
* deletion of a timer failed because the timer callback function was
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 9cb9b6584ea1..2f6330831f08 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -1675,6 +1675,9 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
} while (i < tmigr_hierarchy_levels);
+ /* Assert single root */
+ WARN_ON_ONCE(!err && !group->parent && !list_is_singular(&tmigr_level_list[top]));
+
while (i > 0) {
group = stack[--i];
@@ -1716,7 +1719,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
WARN_ON_ONCE(top == 0);
lvllist = &tmigr_level_list[top];
- if (group->num_children == 1 && list_is_singular(lvllist)) {
+
+ /*
+ * Newly created root level should have accounted the upcoming
+ * CPU's child group and pre-accounted the old root.
+ */
+ if (group->num_children == 2 && list_is_singular(lvllist)) {
/*
* The target CPU must never do the prepare work, except
* on early boot when the boot CPU is the target. Otherwise
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 54d850997c0a..136c750b0b4d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -198,7 +198,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
* returning from the function.
*/
if (ftrace_graph_notrace_addr(trace->func)) {
- *task_var |= TRACE_GRAPH_NOTRACE_BIT;
+ *task_var |= TRACE_GRAPH_NOTRACE;
/*
* Need to return 1 to have the return called
* that will clear the NOTRACE bit.
generated by cgit v1.2.3 (git 2.46.0) at 2025-12-10 02:10:08 +0000