summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/core.c59
-rw-r--r--kernel/sched/deadline.c57
-rw-r--r--kernel/sched/debug.c2
-rw-r--r--kernel/sched/fair.c87
-rw-r--r--kernel/sched/features.h3
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/sched/rt.c15
-rw-r--r--kernel/sched/sched.h4
8 files changed, 159 insertions, 70 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b89ca5c83143..85be684687b0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3714,7 +3714,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
-static inline bool ttwu_queue_cond(int cpu, int wake_flags)
+static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
{
/*
* Do not complicate things with the async wake_list while the CPU is
@@ -3723,6 +3723,10 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
if (!cpu_active(cpu))
return false;
+ /* Ensure the task will still be allowed to run on the CPU. */
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+ return false;
+
/*
* If the CPU does not share cache, then queue the task on the
* remote rqs wakelist to avoid accessing remote data.
@@ -3730,13 +3734,21 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
if (!cpus_share_cache(smp_processor_id(), cpu))
return true;
+ if (cpu == smp_processor_id())
+ return false;
+
/*
- * If the task is descheduling and the only running task on the
- * CPU then use the wakelist to offload the task activation to
- * the soon-to-be-idle CPU as the current CPU is likely busy.
- * nr_running is checked to avoid unnecessary task stacking.
+ * If the wakee cpu is idle, or the task is descheduling and the
+ * only running task on the CPU, then use the wakelist to offload
+ * the task activation to the idle (or soon-to-be-idle) CPU as
+ * the current CPU is likely busy. nr_running is checked to
+ * avoid unnecessary task stacking.
+ *
+ * Note that we can only get here with (wakee) p->on_rq=0,
+ * p->on_cpu can be whatever, we've done the dequeue, so
+ * the wakee has been accounted out of ->nr_running.
*/
- if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
+ if (!cpu_rq(cpu)->nr_running)
return true;
return false;
@@ -3744,10 +3756,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
{
- if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
- if (WARN_ON_ONCE(cpu == smp_processor_id()))
- return false;
-
+ if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
sched_clock_cpu(cpu); /* Sync clocks across CPUs */
__ttwu_queue_wakelist(p, cpu, wake_flags);
return true;
@@ -4069,7 +4078,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* scheduling.
*/
if (smp_load_acquire(&p->on_cpu) &&
- ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
+ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
goto unlock;
/*
@@ -4585,7 +4594,8 @@ static inline void prepare_task(struct task_struct *next)
* Claim the task as running, we do this before switching to it
* such that any running task will have this set.
*
- * See the ttwu() WF_ON_CPU case and its ordering comment.
+ * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
+ * its ordering comment.
*/
WRITE_ONCE(next->on_cpu, 1);
#endif
@@ -6379,8 +6389,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
preempt_enable_no_resched();
}
- if (tsk_is_pi_blocked(tsk))
- return;
+ /*
+ * spinlock and rwlock must not flush block requests. This will
+ * deadlock if the callback attempts to acquire a lock which is
+ * already acquired.
+ */
+ SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
/*
* If we are going to sleep and we have plugged IO queued,
@@ -8737,7 +8751,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
}
int task_can_attach(struct task_struct *p,
- const struct cpumask *cs_cpus_allowed)
+ const struct cpumask *cs_effective_cpus)
{
int ret = 0;
@@ -8756,8 +8770,13 @@ int task_can_attach(struct task_struct *p,
}
if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
- cs_cpus_allowed))
- ret = dl_task_can_attach(p, cs_cpus_allowed);
+ cs_effective_cpus)) {
+ int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
+
+ if (unlikely(cpu >= nr_cpu_ids))
+ return -EINVAL;
+ ret = dl_cpu_busy(cpu, p);
+ }
out:
return ret;
@@ -9041,8 +9060,10 @@ static void cpuset_cpu_active(void)
static int cpuset_cpu_inactive(unsigned int cpu)
{
if (!cpuhp_tasks_frozen) {
- if (dl_cpu_busy(cpu))
- return -EBUSY;
+ int ret = dl_cpu_busy(cpu, NULL);
+
+ if (ret)
+ return ret;
cpuset_update_active_cpus();
} else {
num_cpus_frozen++;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fffcb1aa77b7..147b757d162b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1561,7 +1561,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
* the throttle.
*/
p->dl.dl_throttled = 0;
- BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
+ if (!(flags & ENQUEUE_REPLENISH))
+ printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n",
+ task_pid_nr(p));
+
return;
}
@@ -2861,41 +2864,6 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
}
#ifdef CONFIG_SMP
-int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
-{
- unsigned long flags, cap;
- unsigned int dest_cpu;
- struct dl_bw *dl_b;
- bool overflow;
- int ret;
-
- dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
-
- rcu_read_lock_sched();
- dl_b = dl_bw_of(dest_cpu);
- raw_spin_lock_irqsave(&dl_b->lock, flags);
- cap = dl_bw_capacity(dest_cpu);
- overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
- if (overflow) {
- ret = -EBUSY;
- } else {
- /*
- * We reserve space for this task in the destination
- * root_domain, as we can't fail after this point.
- * We will free resources in the source root_domain
- * later on (see set_cpus_allowed_dl()).
- */
- int cpus = dl_bw_cpus(dest_cpu);
-
- __dl_add(dl_b, p->dl.dl_bw, cpus);
- ret = 0;
- }
- raw_spin_unlock_irqrestore(&dl_b->lock, flags);
- rcu_read_unlock_sched();
-
- return ret;
-}
-
int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
const struct cpumask *trial)
{
@@ -2917,7 +2885,7 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
return ret;
}
-bool dl_cpu_busy(unsigned int cpu)
+int dl_cpu_busy(int cpu, struct task_struct *p)
{
unsigned long flags, cap;
struct dl_bw *dl_b;
@@ -2927,11 +2895,22 @@ bool dl_cpu_busy(unsigned int cpu)
dl_b = dl_bw_of(cpu);
raw_spin_lock_irqsave(&dl_b->lock, flags);
cap = dl_bw_capacity(cpu);
- overflow = __dl_overflow(dl_b, cap, 0, 0);
+ overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
+
+ if (!overflow && p) {
+ /*
+ * We reserve space for this task in the destination
+ * root_domain, as we can't fail after this point.
+ * We will free resources in the source root_domain
+ * later on (see set_cpus_allowed_dl()).
+ */
+ __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+ }
+
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
rcu_read_unlock_sched();
- return overflow;
+ return overflow ? -EBUSY : 0;
}
#endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 7a2d32d2025f..34c5ff3a0669 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void)
char buf[32];
snprintf(buf, sizeof(buf), "cpu%d", cpu);
- debugfs_remove(debugfs_lookup(buf, sd_dentry));
+ debugfs_lookup_and_remove(buf, sd_dentry);
d_cpu = debugfs_create_dir(buf, sd_dentry);
i = 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fcbacc35d2b9..a853e4e9e3c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6280,6 +6280,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
{
struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
int i, cpu, idle_cpu = -1, nr = INT_MAX;
+ struct sched_domain_shared *sd_share;
struct rq *this_rq = this_rq();
int this = smp_processor_id();
struct sched_domain *this_sd;
@@ -6319,6 +6320,17 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
time = cpu_clock(this);
}
+ if (sched_feat(SIS_UTIL)) {
+ sd_share = rcu_dereference(per_cpu(sd_llc_shared, target));
+ if (sd_share) {
+ /* because !--nr is the condition to stop scan */
+ nr = READ_ONCE(sd_share->nr_idle_scan) + 1;
+ /* overloaded LLC is unlikely to have idle cpu/core */
+ if (nr == 1)
+ return -1;
+ }
+ }
+
for_each_cpu_wrap(cpu, cpus, target + 1) {
if (has_idle_core) {
i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -9166,6 +9178,77 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
return idlest;
}
+static void update_idle_cpu_scan(struct lb_env *env,
+ unsigned long sum_util)
+{
+ struct sched_domain_shared *sd_share;
+ int llc_weight, pct;
+ u64 x, y, tmp;
+ /*
+ * Update the number of CPUs to scan in LLC domain, which could
+ * be used as a hint in select_idle_cpu(). The update of sd_share
+ * could be expensive because it is within a shared cache line.
+ * So the write of this hint only occurs during periodic load
+ * balancing, rather than CPU_NEWLY_IDLE, because the latter
+ * can fire way more frequently than the former.
+ */
+ if (!sched_feat(SIS_UTIL) || env->idle == CPU_NEWLY_IDLE)
+ return;
+
+ llc_weight = per_cpu(sd_llc_size, env->dst_cpu);
+ if (env->sd->span_weight != llc_weight)
+ return;
+
+ sd_share = rcu_dereference(per_cpu(sd_llc_shared, env->dst_cpu));
+ if (!sd_share)
+ return;
+
+ /*
+ * The number of CPUs to search drops as sum_util increases, when
+ * sum_util hits 85% or above, the scan stops.
+ * The reason to choose 85% as the threshold is because this is the
+ * imbalance_pct(117) when a LLC sched group is overloaded.
+ *
+ * let y = SCHED_CAPACITY_SCALE - p * x^2 [1]
+ * and y'= y / SCHED_CAPACITY_SCALE
+ *
+ * x is the ratio of sum_util compared to the CPU capacity:
+ * x = sum_util / (llc_weight * SCHED_CAPACITY_SCALE)
+ * y' is the ratio of CPUs to be scanned in the LLC domain,
+ * and the number of CPUs to scan is calculated by:
+ *
+ * nr_scan = llc_weight * y' [2]
+ *
+ * When x hits the threshold of overloaded, AKA, when
+ * x = 100 / pct, y drops to 0. According to [1],
+ * p should be SCHED_CAPACITY_SCALE * pct^2 / 10000
+ *
+ * Scale x by SCHED_CAPACITY_SCALE:
+ * x' = sum_util / llc_weight; [3]
+ *
+ * and finally [1] becomes:
+ * y = SCHED_CAPACITY_SCALE -
+ * x'^2 * pct^2 / (10000 * SCHED_CAPACITY_SCALE) [4]
+ *
+ */
+ /* equation [3] */
+ x = sum_util;
+ do_div(x, llc_weight);
+
+ /* equation [4] */
+ pct = env->sd->imbalance_pct;
+ tmp = x * x * pct * pct;
+ do_div(tmp, 10000 * SCHED_CAPACITY_SCALE);
+ tmp = min_t(long, tmp, SCHED_CAPACITY_SCALE);
+ y = SCHED_CAPACITY_SCALE - tmp;
+
+ /* equation [2] */
+ y *= llc_weight;
+ do_div(y, SCHED_CAPACITY_SCALE);
+ if ((int)y != sd_share->nr_idle_scan)
+ WRITE_ONCE(sd_share->nr_idle_scan, (int)y);
+}
+
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
@@ -9178,6 +9261,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
+ unsigned long sum_util = 0;
int sg_status = 0;
do {
@@ -9210,6 +9294,7 @@ next_group:
sds->total_load += sgs->group_load;
sds->total_capacity += sgs->group_capacity;
+ sum_util += sgs->group_util;
sg = sg->next;
} while (sg != env->sd->groups);
@@ -9235,6 +9320,8 @@ next_group:
WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED);
trace_sched_overutilized_tp(rd, SG_OVERUTILIZED);
}
+
+ update_idle_cpu_scan(env, sum_util);
}
#define NUMA_IMBALANCE_MIN 2
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 7f8dace0964c..c4947c1b5edb 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -55,7 +55,8 @@ SCHED_FEAT(TTWU_QUEUE, true)
/*
* When doing wakeups, attempt to limit superfluous scans of the LLC domain.
*/
-SCHED_FEAT(SIS_PROP, true)
+SCHED_FEAT(SIS_PROP, false)
+SCHED_FEAT(SIS_UTIL, true)
/*
* Issue a WARN when we do multiple update_rq_clock() calls
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index d17b0a5ce6ac..499a3e286cd0 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -105,7 +105,7 @@ void __cpuidle default_idle_call(void)
* last -- this is very similar to the entry code.
*/
trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(_THIS_IP_);
+ lockdep_hardirqs_on_prepare();
rcu_idle_enter();
lockdep_hardirqs_on(_THIS_IP_);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8007d087a57f..f75dcd3537b8 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -444,7 +444,7 @@ static inline void rt_queue_push_tasks(struct rq *rq)
#endif /* CONFIG_SMP */
static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
-static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
+static void dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count);
static inline int on_rt_rq(struct sched_rt_entity *rt_se)
{
@@ -565,7 +565,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
rt_se = rt_rq->tg->rt_se[cpu];
if (!rt_se) {
- dequeue_top_rt_rq(rt_rq);
+ dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
}
@@ -651,7 +651,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
- dequeue_top_rt_rq(rt_rq);
+ dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
}
static inline int rt_rq_throttled(struct rt_rq *rt_rq)
@@ -1051,7 +1051,7 @@ static void update_curr_rt(struct rq *rq)
}
static void
-dequeue_top_rt_rq(struct rt_rq *rt_rq)
+dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count)
{
struct rq *rq = rq_of_rt_rq(rt_rq);
@@ -1062,7 +1062,7 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
BUG_ON(!rq->nr_running);
- sub_nr_running(rq, rt_rq->rt_nr_running);
+ sub_nr_running(rq, count);
rt_rq->rt_queued = 0;
}
@@ -1342,18 +1342,21 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag
static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
{
struct sched_rt_entity *back = NULL;
+ unsigned int rt_nr_running;
for_each_sched_rt_entity(rt_se) {
rt_se->back = back;
back = rt_se;
}
- dequeue_top_rt_rq(rt_rq_of_se(back));
+ rt_nr_running = rt_rq_of_se(back)->rt_nr_running;
for (rt_se = back; rt_se; rt_se = rt_se->back) {
if (on_rt_rq(rt_se))
__dequeue_rt_entity(rt_se, flags);
}
+
+ dequeue_top_rt_rq(rt_rq_of_se(back), rt_nr_running);
}
static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fe8be2f8a47d..e49902898253 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -348,9 +348,8 @@ extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
extern bool __checkparam_dl(const struct sched_attr *attr);
extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
-extern int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern bool dl_cpu_busy(unsigned int cpu);
+extern int dl_cpu_busy(int cpu, struct task_struct *p);
#ifdef CONFIG_CGROUP_SCHED
@@ -2053,7 +2052,6 @@ static inline int task_on_rq_migrating(struct task_struct *p)
#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
-#define WF_ON_CPU 0x40 /* Wakee is on_cpu */
#ifdef CONFIG_SMP
static_assert(WF_EXEC == SD_BALANCE_EXEC);
generated by cgit v1.2.3 (git 2.0.4) at 2024-09-11 14:31:53 +0000