summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/clock.c1
-rw-r--r--kernel/sched/core.c129
-rw-r--r--kernel/sched/cpufreq.c2
-rw-r--r--kernel/sched/cpufreq_schedutil.c26
-rw-r--r--kernel/sched/cputime.c1
-rw-r--r--kernel/sched/debug.c2
-rw-r--r--kernel/sched/fair.c25
-rw-r--r--kernel/sched/idle.c1
-rw-r--r--kernel/sched/isolation.c19
-rw-r--r--kernel/sched/psi.c617
-rw-r--r--kernel/sched/rt.c5
-rw-r--r--kernel/sched/sched.h18
-rw-r--r--kernel/sched/topology.c31
-rw-r--r--kernel/sched/wait.c1
-rw-r--r--kernel/sched/wait_bit.c1
15 files changed, 677 insertions, 202 deletions
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e3e3b979f9bd..1152259a4ca0 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* sched_clock() for unstable CPU clocks
*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4778c48a7fda..874c427742a9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* kernel/sched/core.c
*
@@ -792,10 +793,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
rq->nr_uninterruptible--;
enqueue_task(rq, p, flags);
+
+ p->on_rq = TASK_ON_RQ_QUEUED;
}
void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
+ p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
if (task_contributes_to_load(p))
rq->nr_uninterruptible++;
@@ -920,7 +925,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
}
/*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
* __set_cpus_allowed_ptr() and select_fallback_rq().
*/
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
@@ -1151,7 +1156,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
/* Need help from migration thread: drop lock and wait. */
task_rq_unlock(rq, p, &rf);
stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
- tlb_migrate_finish(p->mm);
return 0;
} else if (task_on_rq_queued(p)) {
/*
@@ -1237,11 +1241,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
rq_pin_lock(src_rq, &srf);
rq_pin_lock(dst_rq, &drf);
- p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(src_rq, p, 0);
set_task_cpu(p, cpu);
activate_task(dst_rq, p, 0);
- p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(dst_rq, p, 0);
rq_unpin_lock(dst_rq, &drf);
@@ -1681,16 +1683,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
__schedstat_inc(p->se.statistics.nr_wakeups_sync);
}
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
- activate_task(rq, p, en_flags);
- p->on_rq = TASK_ON_RQ_QUEUED;
-
- /* If a worker is waking up, notify the workqueue: */
- if (p->flags & PF_WQ_WORKER)
- wq_worker_waking_up(p, cpu_of(rq));
-}
-
/*
* Mark the task runnable and perform wakeup-preemption.
*/
@@ -1742,7 +1734,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
en_flags |= ENQUEUE_MIGRATED;
#endif
- ttwu_activate(rq, p, en_flags);
+ activate_task(rq, p, en_flags);
ttwu_do_wakeup(rq, p, wake_flags, rf);
}
@@ -2107,56 +2099,6 @@ out:
}
/**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
- struct rq *rq = task_rq(p);
-
- if (WARN_ON_ONCE(rq != this_rq()) ||
- WARN_ON_ONCE(p == current))
- return;
-
- lockdep_assert_held(&rq->lock);
-
- if (!raw_spin_trylock(&p->pi_lock)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we've
- * not yet picked a replacement task.
- */
- rq_unlock(rq, rf);
- raw_spin_lock(&p->pi_lock);
- rq_relock(rq, rf);
- }
-
- if (!(p->state & TASK_NORMAL))
- goto out;
-
- trace_sched_waking(p);
-
- if (!task_on_rq_queued(p)) {
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&rq->nr_iowait);
- }
- ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
- }
-
- ttwu_do_wakeup(rq, p, 0, rf);
- ttwu_stat(p, smp_processor_id(), 0);
-out:
- raw_spin_unlock(&p->pi_lock);
-}
-
-/**
* wake_up_process - Wake up a specific process
* @p: The process to be woken up.
*
@@ -2467,7 +2409,6 @@ void wake_up_new_task(struct task_struct *p)
post_init_entity_util_avg(p);
activate_task(rq, p, ENQUEUE_NOCLOCK);
- p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
@@ -3466,25 +3407,11 @@ static void __sched notrace __schedule(bool preempt)
prev->state = TASK_RUNNING;
} else {
deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
- prev->on_rq = 0;
if (prev->in_iowait) {
atomic_inc(&rq->nr_iowait);
delayacct_blkio_start();
}
-
- /*
- * If a worker went to sleep, notify and ask workqueue
- * whether it wants to wake up a task to maintain
- * concurrency.
- */
- if (prev->flags & PF_WQ_WORKER) {
- struct task_struct *to_wakeup;
-
- to_wakeup = wq_worker_sleeping(prev);
- if (to_wakeup)
- try_to_wake_up_local(to_wakeup, &rf);
- }
}
switch_count = &prev->nvcsw;
}
@@ -3544,6 +3471,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
{
if (!tsk->state || tsk_is_pi_blocked(tsk))
return;
+
+ /*
+ * If a worker went to sleep, notify and ask workqueue whether
+ * it wants to wake up a task to maintain concurrency.
+ * As this function is called inside the schedule() context,
+ * we disable preemption to avoid it calling schedule() again
+ * in the possible wakeup of a kworker.
+ */
+ if (tsk->flags & PF_WQ_WORKER) {
+ preempt_disable();
+ wq_worker_sleeping(tsk);
+ preempt_enable_no_resched();
+ }
+
/*
* If we are going to sleep and we have plugged IO queued,
* make sure to submit it to avoid deadlocks.
@@ -3552,6 +3493,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
blk_schedule_flush_plug(tsk);
}
+static void sched_update_worker(struct task_struct *tsk)
+{
+ if (tsk->flags & PF_WQ_WORKER)
+ wq_worker_running(tsk);
+}
+
asmlinkage __visible void __sched schedule(void)
{
struct task_struct *tsk = current;
@@ -3562,6 +3509,7 @@ asmlinkage __visible void __sched schedule(void)
__schedule(false);
sched_preempt_enable_no_resched();
} while (need_resched());
+ sched_update_worker(tsk);
}
EXPORT_SYMBOL(schedule);
@@ -5918,7 +5866,7 @@ void __init sched_init_smp(void)
static int __init migration_init(void)
{
- sched_rq_cpu_starting(smp_processor_id());
+ sched_cpu_starting(smp_processor_id());
return 0;
}
early_initcall(migration_init);
@@ -6559,6 +6507,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
{
+ if (shareval > scale_load_down(ULONG_MAX))
+ shareval = MAX_SHARES;
return sched_group_set_shares(css_tg(css), scale_load(shareval));
}
@@ -6574,7 +6524,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
static DEFINE_MUTEX(cfs_constraints_mutex);
const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
@@ -6654,20 +6604,22 @@ out_unlock:
return ret;
}
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
u64 quota, period;
period = ktime_to_ns(tg->cfs_bandwidth.period);
if (cfs_quota_us < 0)
quota = RUNTIME_INF;
- else
+ else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+ else
+ return -EINVAL;
return tg_set_cfs_bandwidth(tg, period, quota);
}
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
{
u64 quota_us;
@@ -6680,17 +6632,20 @@ long tg_get_cfs_quota(struct task_group *tg)
return quota_us;
}
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
u64 quota, period;
+ if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+
period = (u64)cfs_period_us * NSEC_PER_USEC;
quota = tg->cfs_bandwidth.quota;
return tg_set_cfs_bandwidth(tg, period, quota);
}
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
{
u64 cfs_period_us;
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 835671f0f917..b5dcd1d83c7f 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -7,7 +7,7 @@
*/
#include "sched.h"
-DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
/**
* cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3638d2377e3c..962cf343f798 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -13,6 +13,8 @@
#include <linux/sched/cpufreq.h>
#include <trace/events/power.h>
+#define IOWAIT_BOOST_MIN (SCHED_CAPACITY_SCALE / 8)
+
struct sugov_tunables {
struct gov_attr_set attr_set;
unsigned int rate_limit_us;
@@ -51,7 +53,6 @@ struct sugov_cpu {
u64 last_update;
unsigned long bw_dl;
- unsigned long min;
unsigned long max;
/* The field below is for single-CPU policies only: */
@@ -291,8 +292,8 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
*
* The IO wait boost of a task is disabled after a tick since the last update
* of a CPU. If a new IO wait boost is requested after more then a tick, then
- * we enable the boost starting from the minimum frequency, which improves
- * energy efficiency by ignoring sporadic wakeups from IO.
+ * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy
+ * efficiency by ignoring sporadic wakeups from IO.
*/
static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
bool set_iowait_boost)
@@ -303,7 +304,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
if (delta_ns <= TICK_NSEC)
return false;
- sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
+ sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
sg_cpu->iowait_boost_pending = set_iowait_boost;
return true;
@@ -317,8 +318,9 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
*
* Each time a task wakes up after an IO operation, the CPU utilization can be
* boosted to a certain utilization which doubles at each "frequent and
- * successive" wakeup from IO, ranging from the utilization of the minimum
- * OPP to the utilization of the maximum OPP.
+ * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization
+ * of the maximum OPP.
+ *
* To keep doubling, an IO boost has to be requested at least once per tick,
* otherwise we restart from the utilization of the minimum OPP.
*/
@@ -349,7 +351,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
}
/* First wakeup after IO: start with minimum boost */
- sg_cpu->iowait_boost = sg_cpu->min;
+ sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
}
/**
@@ -389,7 +391,7 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
* No boost pending; reduce the boost value.
*/
sg_cpu->iowait_boost >>= 1;
- if (sg_cpu->iowait_boost < sg_cpu->min) {
+ if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
sg_cpu->iowait_boost = 0;
return util;
}
@@ -598,13 +600,14 @@ rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf, size_t count
static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us);
-static struct attribute *sugov_attributes[] = {
+static struct attribute *sugov_attrs[] = {
&rate_limit_us.attr,
NULL
};
+ATTRIBUTE_GROUPS(sugov);
static struct kobj_type sugov_tunables_ktype = {
- .default_attrs = sugov_attributes,
+ .default_groups = sugov_groups,
.sysfs_ops = &governor_sysfs_ops,
};
@@ -827,9 +830,6 @@ static int sugov_start(struct cpufreq_policy *policy)
memset(sg_cpu, 0, sizeof(*sg_cpu));
sg_cpu->cpu = cpu;
sg_cpu->sg_policy = sg_policy;
- sg_cpu->min =
- (SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
- policy->cpuinfo.max_freq;
}
for_each_cpu(cpu, policy->cpus) {
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ba4a143bdcf3..2305ce89a26c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Simple CPU accounting cgroup controller
*/
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8039d62ae36e..678bfb9bd87f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -702,7 +702,7 @@ do { \
static const char *sched_tunable_scaling_names[] = {
"none",
- "logaritmic",
+ "logarithmic",
"linear"
};
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 35f3ea375084..f35930f5e528 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2597,7 +2597,7 @@ out:
/*
* Drive the periodic memory faults..
*/
-void task_tick_numa(struct rq *rq, struct task_struct *curr)
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
struct callback_head *work = &curr->numa_work;
u64 period, now;
@@ -3571,7 +3571,7 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
* Synchronize entity load avg of dequeued entity without locking
* the previous rq.
*/
-void sync_entity_load_avg(struct sched_entity *se)
+static void sync_entity_load_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 last_update_time;
@@ -3584,7 +3584,7 @@ void sync_entity_load_avg(struct sched_entity *se)
* Task first catches up with cfs_rq, and then subtract
* itself from the cfs_rq (task must be off the queue now).
*/
-void remove_entity_load_avg(struct sched_entity *se)
+static void remove_entity_load_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
unsigned long flags;
@@ -5145,7 +5145,6 @@ static inline void hrtick_update(struct rq *rq)
#ifdef CONFIG_SMP
static inline unsigned long cpu_util(int cpu);
-static unsigned long capacity_of(int cpu);
static inline bool cpu_overutilized(int cpu)
{
@@ -7521,7 +7520,6 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
{
lockdep_assert_held(&env->src_rq->lock);
- p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
set_task_cpu(p, env->dst_cpu);
}
@@ -7657,7 +7655,6 @@ static void attach_task(struct rq *rq, struct task_struct *p)
BUG_ON(task_rq(p) != rq);
activate_task(rq, p, ENQUEUE_NOCLOCK);
- p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(rq, p, 0);
}
@@ -9551,22 +9548,26 @@ static inline int on_null_domain(struct rq *rq)
* - When one of the busy CPUs notice that there may be an idle rebalancing
* needed, they will kick the idle load balancer, which then does idle
* load balancing for all the idle CPUs.
+ * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ * anywhere yet.
*/
static inline int find_new_ilb(void)
{
- int ilb = cpumask_first(nohz.idle_cpus_mask);
+ int ilb;
- if (ilb < nr_cpu_ids && idle_cpu(ilb))
- return ilb;
+ for_each_cpu_and(ilb, nohz.idle_cpus_mask,
+ housekeeping_cpumask(HK_FLAG_MISC)) {
+ if (idle_cpu(ilb))
+ return ilb;
+ }
return nr_cpu_ids;
}
/*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick the
- * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
- * CPU (if there is one).
+ * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
+ * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
*/
static void kick_ilb(unsigned int flags)
{
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f5516bae0c1b..80940939b733 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic entry points for the idle threads and
* implementation of the idle task scheduling class.
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index b02d148e7672..123ea07a3f3b 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Housekeeping management. Manage the targets for routine code that can run on
* any CPU: unbound workqueues, timers, kthreads and any offloadable work.
@@ -65,6 +66,7 @@ void __init housekeeping_init(void)
static int __init housekeeping_setup(char *str, enum hk_flags flags)
{
cpumask_var_t non_housekeeping_mask;
+ cpumask_var_t tmp;
int err;
alloc_bootmem_cpumask_var(&non_housekeeping_mask);
@@ -75,16 +77,23 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
return 0;
}
+ alloc_bootmem_cpumask_var(&tmp);
if (!housekeeping_flags) {
alloc_bootmem_cpumask_var(&housekeeping_mask);
cpumask_andnot(housekeeping_mask,
cpu_possible_mask, non_housekeeping_mask);
- if (cpumask_empty(housekeeping_mask))
+
+ cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+ if (cpumask_empty(tmp)) {
+ pr_warn("Housekeeping: must include one present CPU, "
+ "using boot CPU:%d\n", smp_processor_id());
__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
+ __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+ }
} else {
- cpumask_var_t tmp;
-
- alloc_bootmem_cpumask_var(&tmp);
+ cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+ if (cpumask_empty(tmp))
+ __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
if (!cpumask_equal(tmp, housekeeping_mask)) {
pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
@@ -92,8 +101,8 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
free_bootmem_cpumask_var(non_housekeeping_mask);
return 0;
}
- free_bootmem_cpumask_var(tmp);
}
+ free_bootmem_cpumask_var(tmp);
if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 0e97ca9306ef..7acc632c3b82 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -4,6 +4,9 @@
* Copyright (c) 2018 Facebook, Inc.
* Author: Johannes Weiner <hannes@cmpxchg.org>
*
+ * Polling support by Suren Baghdasaryan <surenb@google.com>
+ * Copyright (c) 2018 Google, Inc.
+ *
* When CPU, memory and IO are contended, tasks experience delays that
* reduce throughput and introduce latencies into the workload. Memory
* and IO contention, in addition, can cause a full loss of forward
@@ -129,9 +132,13 @@
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/seqlock.h>
+#include <linux/uaccess.h>
#include <linux/cgroup.h>
#include <linux/module.h>
#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/file.h>
+#include <linux/poll.h>
#include <linux/psi.h>
#include "sched.h"
@@ -140,9 +147,9 @@ static int psi_bug __read_mostly;
DEFINE_STATIC_KEY_FALSE(psi_disabled);
#ifdef CONFIG_PSI_DEFAULT_DISABLED
-bool psi_enable;
+static bool psi_enable;
#else
-bool psi_enable = true;
+static bool psi_enable = true;
#endif
static int __init setup_psi(char *str)
{
@@ -156,16 +163,21 @@ __setup("psi=", setup_psi);
#define EXP_60s 1981 /* 1/exp(2s/60s) */
#define EXP_300s 2034 /* 1/exp(2s/300s) */
+/* PSI trigger definitions */
+#define WINDOW_MIN_US 500000 /* Min window size is 500ms */
+#define WINDOW_MAX_US 10000000 /* Max window size is 10s */
+#define UPDATES_PER_WINDOW 10 /* 10 updates per window */
+
/* Sampling frequency in nanoseconds */
static u64 psi_period __read_mostly;
/* System-level pressure and stall tracking */
static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu);
-static struct psi_group psi_system = {
+struct psi_group psi_system = {
.pcpu = &system_group_pcpu,
};
-static void psi_update_work(struct work_struct *work);
+static void psi_avgs_work(struct work_struct *work);
static void group_init(struct psi_group *group)
{
@@ -173,9 +185,20 @@ static void group_init(struct psi_group *group)
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
- group->next_update = sched_clock() + psi_period;
- INIT_DELAYED_WORK(&group->clock_work, psi_update_work);
- mutex_init(&group->stat_lock);
+ group->avg_next_update = sched_clock() + psi_period;
+ INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
+ mutex_init(&group->avgs_lock);
+ /* Init trigger-related members */
+ atomic_set(&group->poll_scheduled, 0);
+ mutex_init(&group->trigger_lock);
+ INIT_LIST_HEAD(&group->triggers);
+ memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
+ group->poll_states = 0;
+ group->poll_min_period = U32_MAX;
+ memset(group->polling_total, 0, sizeof(group->polling_total));
+ group->polling_next_update = ULLONG_MAX;
+ group->polling_until = 0;
+ rcu_assign_pointer(group->poll_kworker, NULL);
}
void __init psi_init(void)
@@ -210,20 +233,24 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
}
}
-static void get_recent_times(struct psi_group *group, int cpu, u32 *times)
+static void get_recent_times(struct psi_group *group, int cpu,
+ enum psi_aggregators aggregator, u32 *times,
+ u32 *pchanged_states)
{
struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
- unsigned int tasks[NR_PSI_TASK_COUNTS];
u64 now, state_start;
+ enum psi_states s;
unsigned int seq;
- int s;
+ u32 state_mask;
+
+ *pchanged_states = 0;
/* Snapshot a coherent view of the CPU state */
do {
seq = read_seqcount_begin(&groupc->seq);
now = cpu_clock(cpu);
memcpy(times, groupc->times, sizeof(groupc->times));
- memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
+ state_mask = groupc->state_mask;
state_start = groupc->state_start;
} while (read_seqcount_retry(&groupc->seq, seq));
@@ -239,13 +266,15 @@ static void get_recent_times(struct psi_group *group, int cpu, u32 *times)
* (u32) and our reported pressure close to what's
* actually happening.
*/
- if (test_state(tasks, s))
+ if (state_mask & (1 << s))
times[s] += now - state_start;
- delta = times[s] - groupc->times_prev[s];
- groupc->times_prev[s] = times[s];
+ delta = times[s] - groupc->times_prev[aggregator][s];
+ groupc->times_prev[aggregator][s] = times[s];
times[s] = delta;
+ if (delta)
+ *pchanged_states |= (1 << s);
}
}
@@ -269,17 +298,16 @@ static void calc_avgs(unsigned long avg[3], int missed_periods,
avg[2] = calc_load(avg[2], EXP_300s, pct);
}
-static bool update_stats(struct psi_group *group)
+static void collect_percpu_times(struct psi_group *group,
+ enum psi_aggregators aggregator,
+ u32 *pchanged_states)
{
u64 deltas[NR_PSI_STATES - 1] = { 0, };
- unsigned long missed_periods = 0;
unsigned long nonidle_total = 0;
- u64 now, expires, period;
+ u32 changed_states = 0;
int cpu;
int s;
- mutex_lock(&group->stat_lock);
-
/*
* Collect the per-cpu time buckets and average them into a
* single time sample that is normalized to wallclock time.
@@ -291,8 +319,11 @@ static bool update_stats(struct psi_group *group)
for_each_possible_cpu(cpu) {
u32 times[NR_PSI_STATES];
u32 nonidle;
+ u32 cpu_changed_states;
- get_recent_times(group, cpu, times);
+ get_recent_times(group, cpu, aggregator, times,
+ &cpu_changed_states);
+ changed_states |= cpu_changed_states;
nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]);
nonidle_total += nonidle;
@@ -315,13 +346,22 @@ static bool update_stats(struct psi_group *group)
/* total= */
for (s = 0; s < NR_PSI_STATES - 1; s++)
- group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));
+ group->total[aggregator][s] +=
+ div_u64(deltas[s], max(nonidle_total, 1UL));
+
+ if (pchanged_states)
+ *pchanged_states = changed_states;
+}
+
+static u64 update_averages(struct psi_group *group, u64 now)
+{
+ unsigned long missed_periods = 0;
+ u64 expires, period;
+ u64 avg_next_update;
+ int s;
/* avgX= */
- now = sched_clock();
- expires = group->next_update;
- if (now < expires)
- goto out;
+ expires = group->avg_next_update;
if (now - expires >= psi_period)
missed_periods = div_u64(now - expires, psi_period);
@@ -332,14 +372,14 @@ static bool update_stats(struct psi_group *group)
* But the deltas we sample out of the per-cpu buckets above
* are based on the actual time elapsing between clock ticks.
*/
- group->next_update = expires + ((1 + missed_periods) * psi_period);
- period = now - (group->last_update + (missed_periods * psi_period));
- group->last_update = now;
+ avg_next_update = expires + ((1 + missed_periods) * psi_period);
+ period = now - (group->avg_last_update + (missed_periods * psi_period));
+ group->avg_last_update = now;
for (s = 0; s < NR_PSI_STATES - 1; s++) {
u32 sample;
- sample = group->total[s] - group->total_prev[s];
+ sample = group->total[PSI_AVGS][s] - group->avg_total[s];
/*
* Due to the lockless sampling of the time buckets,
* recorded time deltas can slip into the next period,
@@ -359,23 +399,30 @@ static bool update_stats(struct psi_group *group)
*/
if (sample > period)
sample = period;
- group->total_prev[s] += sample;
+ group->avg_total[s] += sample;
calc_avgs(group->avg[s], missed_periods, sample, period);
}
-out:
- mutex_unlock(&group->stat_lock);
- return nonidle_total;
+
+ return avg_next_update;
}
-static void psi_update_work(struct work_struct *work)
+static void psi_avgs_work(struct work_struct *work)
{
struct delayed_work *dwork;
struct psi_group *group;
+ u32 changed_states;
bool nonidle;
+ u64 now;
dwork = to_delayed_work(work);
- group = container_of(dwork, struct psi_group, clock_work);
+ group = container_of(dwork, struct psi_group, avgs_work);
+
+ mutex_lock(&group->avgs_lock);
+ now = sched_clock();
+
+ collect_percpu_times(group, PSI_AVGS, &changed_states);
+ nonidle = changed_states & (1 << PSI_NONIDLE);
/*
* If there is task activity, periodically fold the per-cpu
* times and feed samples into the running averages. If things
@@ -383,18 +430,196 @@ static void psi_update_work(struct work_struct *work)
* Once restarted, we'll catch up the running averages in one
* go - see calc_avgs() and missed_periods.
*/
-
- nonidle = update_stats(group);
+ if (now >= group->avg_next_update)
+ group->avg_next_update = update_averages(group, now);
if (nonidle) {
- unsigned long delay = 0;
- u64 now;
+ schedule_delayed_work(dwork, nsecs_to_jiffies(
+ group->avg_next_update - now) + 1);
+ }
+
+ mutex_unlock(&group->avgs_lock);
+}
+
+/* Trigger tracking window manupulations */
+static void window_reset(struct psi_window *win, u64 now, u64 value,
+ u64 prev_growth)
+{
+ win->start_time = now;
+ win->start_value = value;
+ win->prev_growth = prev_growth;
+}
+
+/*
+ * PSI growth tracking window update and growth calculation routine.
+ *
+ * This approximates a sliding tracking window by interpolating
+ * partially elapsed windows using historical growth data from the
+ * previous intervals. This minimizes memory requirements (by not storing
+ * all the intermediate values in the previous window) and simplifies
+ * the calculations. It works well because PSI signal changes only in
+ * positive direction and over relatively small window sizes the growth
+ * is close to linear.
+ */
+static u64 window_update(struct psi_window *win, u64 now, u64 value)
+{
+ u64 elapsed;
+ u64 growth;
+
+ elapsed = now - win->start_time;
+ growth = value - win->start_value;
+ /*
+ * After each tracking window passes win->start_value and
+ * win->start_time get reset and win->prev_growth stores
+ * the average per-window growth of the previous window.
+ * win->prev_growth is then used to interpolate additional
+ * growth from the previous window assuming it was linear.
+ */
+ if (elapsed > win->size)
+ window_reset(win, now, value, growth);
+ else {
+ u32 remaining;
+
+ remaining = win->size - elapsed;
+ growth += div_u64(win->prev_growth * remaining, win->size);
+ }
+
+ return growth;
+}
+
+static void init_triggers(struct psi_group *group, u64 now)
+{
+ struct psi_trigger *t;
+
+ list_for_each_entry(t, &group->triggers, node)
+ window_reset(&t->win, now,
+ group->total[PSI_POLL][t->state], 0);
+ memcpy(group->polling_total, group->total[PSI_POLL],
+ sizeof(group->polling_total));
+ group->polling_next_update = now + group->poll_min_period;
+}
+
+static u64 update_triggers(struct psi_group *group, u64 now)
+{
+ struct psi_trigger *t;
+ bool new_stall = false;
+ u64 *total = group->total[PSI_POLL];
+
+ /*
+ * On subsequent updates, calculate growth deltas and let
+ * watchers know when their specified thresholds are exceeded.
+ */
+ list_for_each_entry(t, &group->triggers, node) {
+ u64 growth;
+
+ /* Check for stall activity */
+ if (group->polling_total[t->state] == total[t->state])
+ continue;
+
+ /*
+ * Multiple triggers might be looking at the same state,
+ * remember to update group->polling_total[] once we've
+ * been through all of them. Also remember to extend the
+ * polling time if we see new stall activity.
+ */
+ new_stall = true;
+
+ /* Calculate growth since last update */
+ growth = window_update(&t->win, now, total[t->state]);
+ if (growth < t->threshold)
+ continue;
+
+ /* Limit event signaling to once per window */
+ if (now < t->last_event_time + t->win.size)
+ continue;
+
+ /* Generate an event */
+ if (cmpxchg(&t->event, 0, 1) == 0)
+ wake_up_interruptible(&t->event_wait);
+ t->last_event_time = now;
+ }
+
+ if (new_stall)
+ memcpy(group->polling_total, total,
+ sizeof(group->polling_total));
+
+ return now + group->poll_min_period;
+}
+
+/*
+ * Schedule polling if it's not already scheduled. It's safe to call even from
+ * hotpath because even though kthread_queue_delayed_work takes worker->lock
+ * spinlock that spinlock is never contended due to poll_scheduled atomic
+ * preventing such competition.
+ */
+static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
+{
+ struct kthread_worker *kworker;
+
+ /* Do not reschedule if already scheduled */
+ if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+ return;
+
+ rcu_read_lock();
- now = sched_clock();
- if (group->next_update > now)
- delay = nsecs_to_jiffies(group->next_update - now) + 1;
- schedule_delayed_work(dwork, delay);
+ kworker = rcu_dereference(group->poll_kworker);
+ /*
+ * kworker might be NULL in case psi_trigger_destroy races with
+ * psi_task_change (hotpath) which can't use locks
+ */
+ if (likely(kworker))
+ kthread_queue_delayed_work(kworker, &group->poll_work, delay);
+ else
+ atomic_set(&group->poll_scheduled, 0);
+
+ rcu_read_unlock();
+}
+
+static void psi_poll_work(struct kthread_work *work)
+{
+ struct kthread_delayed_work *dwork;
+ struct psi_group *group;
+ u32 changed_states;
+ u64 now;
+
+ dwork = container_of(work, struct kthread_delayed_work, work);
+ group = container_of(dwork, struct psi_group, poll_work);
+
+ atomic_set(&group->poll_scheduled, 0);
+
+ mutex_lock(&group->trigger_lock);
+
+ now = sched_clock();
+
+ collect_percpu_times(group, PSI_POLL, &changed_states);
+
+ if (changed_states & group->poll_states) {
+ /* Initialize trigger windows when entering polling mode */
+ if (now > group->polling_until)
+ init_triggers(group, now);
+
+ /*
+ * Keep the monitor active for at least the duration of the
+ * minimum tracking window as long as monitor states are
+ * changing.
+ */
+ group->polling_until = now +
+ group->poll_min_period * UPDATES_PER_WINDOW;
+ }
+
+ if (now > group->polling_until) {
+ group->polling_next_update = ULLONG_MAX;
+ goto out;
}
+
+ if (now >= group->polling_next_update)
+ group->polling_next_update = update_triggers(group, now);
+
+ psi_schedule_poll_work(group,
+ nsecs_to_jiffies(group->polling_next_update - now) + 1);
+
+out:
+ mutex_unlock(&group->trigger_lock);
}
static void record_times(struct psi_group_cpu *groupc, int cpu,
@@ -407,15 +632,15 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
delta = now - groupc->state_start;
groupc->state_start = now;
- if (test_state(groupc->tasks, PSI_IO_SOME)) {
+ if (groupc->state_mask & (1 << PSI_IO_SOME)) {
groupc->times[PSI_IO_SOME] += delta;
- if (test_state(groupc->tasks, PSI_IO_FULL))
+ if (groupc->state_mask & (1 << PSI_IO_FULL))
groupc->times[PSI_IO_FULL] += delta;
}
- if (test_state(groupc->tasks, PSI_MEM_SOME)) {
+ if (groupc->state_mask & (1 << PSI_MEM_SOME)) {
groupc->times[PSI_MEM_SOME] += delta;
- if (test_state(groupc->tasks, PSI_MEM_FULL))
+ if (groupc->state_mask & (1 << PSI_MEM_FULL))
groupc->times[PSI_MEM_FULL] += delta;
else if (memstall_tick) {
u32 sample;
@@ -436,18 +661,20 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
}
}
- if (test_state(groupc->tasks, PSI_CPU_SOME))
+ if (groupc->state_mask & (1 << PSI_CPU_SOME))
groupc->times[PSI_CPU_SOME] += delta;
- if (test_state(groupc->tasks, PSI_NONIDLE))
+ if (groupc->state_mask & (1 << PSI_NONIDLE))
groupc->times[PSI_NONIDLE] += delta;
}
-static void psi_group_change(struct psi_group *group, int cpu,
- unsigned int clear, unsigned int set)
+static u32 psi_group_change(struct psi_group *group, int cpu,
+ unsigned int clear, unsigned int set)
{
struct psi_group_cpu *groupc;
unsigned int t, m;
+ enum psi_states s;
+ u32 state_mask = 0;
groupc = per_cpu_ptr(group->pcpu, cpu);
@@ -480,7 +707,16 @@ static void psi_group_change(struct psi_group *group, int cpu,
if (set & (1 << t))
groupc->tasks[t]++;
+ /* Calculate state mask representing active states */
+ for (s = 0; s < NR_PSI_STATES; s++) {
+ if (test_state(groupc->tasks, s))
+ state_mask |= (1 << s);
+ }
+ groupc->state_mask = state_mask;
+
write_seqcount_end(&groupc->seq);
+
+ return state_mask;
}
static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -537,13 +773,17 @@ void psi_task_change(struct task_struct *task, int clear, int set)
*/
if (unlikely((clear & TSK_RUNNING) &&
(task->flags & PF_WQ_WORKER) &&
- wq_worker_last_func(task) == psi_update_work))
+ wq_worker_last_func(task) == psi_avgs_work))
wake_clock = false;
while ((group = iterate_groups(task, &iter))) {
- psi_group_change(group, cpu, clear, set);
- if (wake_clock && !delayed_work_pending(&group->clock_work))
- schedule_delayed_work(&group->clock_work, PSI_FREQ);
+ u32 state_mask = psi_group_change(group, cpu, clear, set);
+
+ if (state_mask & group->poll_states)
+ psi_schedule_poll_work(group, 1);
+
+ if (wake_clock && !delayed_work_pending(&group->avgs_work))
+ schedule_delayed_work(&group->avgs_work, PSI_FREQ);
}
}
@@ -640,8 +880,10 @@ void psi_cgroup_free(struct cgroup *cgroup)
if (static_branch_likely(&psi_disabled))
return;
- cancel_delayed_work_sync(&cgroup->psi.clock_work);
+ cancel_delayed_work_sync(&cgroup->psi.avgs_work);
free_percpu(cgroup->psi.pcpu);
+ /* All triggers must be removed by now */
+ WARN_ONCE(cgroup->psi.poll_states, "psi: trigger leak\n");
}
/**
@@ -697,11 +939,18 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
{
int full;
+ u64 now;
if (static_branch_likely(&psi_disabled))
return -EOPNOTSUPP;
- update_stats(group);
+ /* Update averages before reporting them */
+ mutex_lock(&group->avgs_lock);
+ now = sched_clock();
+ collect_percpu_times(group, PSI_AVGS, NULL);
+ if (now >= group->avg_next_update)
+ group->avg_next_update = update_averages(group, now);
+ mutex_unlock(&group->avgs_lock);
for (full = 0; full < 2 - (res == PSI_CPU); full++) {
unsigned long avg[3];
@@ -710,7 +959,8 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
for (w = 0; w < 3; w++)
avg[w] = group->avg[res * 2 + full][w];
- total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC);
+ total = div_u64(group->total[PSI_AVGS][res * 2 + full],
+ NSEC_PER_USEC);
seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
full ? "full" : "some",
@@ -753,25 +1003,270 @@ static int psi_cpu_open(struct inode *inode, struct file *file)
return single_open(file, psi_cpu_show, NULL);
}
+struct psi_trigger *psi_trigger_create(struct psi_group *group,
+ char *buf, size_t nbytes, enum psi_res res)
+{
+ struct psi_trigger *t;
+ enum psi_states state;
+ u32 threshold_us;
+ u32 window_us;
+
+ if (static_branch_likely(&psi_disabled))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2)
+ state = PSI_IO_SOME + res * 2;
+ else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2)
+ state = PSI_IO_FULL + res * 2;
+ else
+ return ERR_PTR(-EINVAL);
+
+ if (state >= PSI_NONIDLE)
+ return ERR_PTR(-EINVAL);
+
+ if (window_us < WINDOW_MIN_US ||
+ window_us > WINDOW_MAX_US)
+ return ERR_PTR(-EINVAL);
+
+ /* Check threshold */
+ if (threshold_us == 0 || threshold_us > window_us)
+ return ERR_PTR(-EINVAL);
+
+ t = kmalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return ERR_PTR(-ENOMEM);
+
+ t->group = group;
+ t->state = state;
+ t->threshold = threshold_us * NSEC_PER_USEC;
+ t->win.size = window_us * NSEC_PER_USEC;
+ window_reset(&t->win, 0, 0, 0);
+
+ t->event = 0;
+ t->last_event_time = 0;
+ init_waitqueue_head(&t->event_wait);
+ kref_init(&t->refcount);
+
+ mutex_lock(&group->trigger_lock);
+
+ if (!rcu_access_pointer(group->poll_kworker)) {
+ struct sched_param param = {
+ .sched_priority = MAX_RT_PRIO - 1,
+ };
+ struct kthread_worker *kworker;
+
+ kworker = kthread_create_worker(0, "psimon");
+ if (IS_ERR(kworker)) {
+ kfree(t);
+ mutex_unlock(&group->trigger_lock);
+ return ERR_CAST(kworker);
+ }
+ sched_setscheduler(kworker->task, SCHED_FIFO, &param);
+ kthread_init_delayed_work(&group->poll_work,
+ psi_poll_work);
+ rcu_assign_pointer(group->poll_kworker, kworker);
+ }
+
+ list_add(&t->node, &group->triggers);
+ group->poll_min_period = min(group->poll_min_period,
+ div_u64(t->win.size, UPDATES_PER_WINDOW));
+ group->nr_triggers[t->state]++;
+ group->poll_states |= (1 << t->state);
+
+ mutex_unlock(&group->trigger_lock);
+
+ return t;
+}
+
+static void psi_trigger_destroy(struct kref *ref)
+{
+ struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
+ struct psi_group *group = t->group;
+ struct kthread_worker *kworker_to_destroy = NULL;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ /*
+ * Wakeup waiters to stop polling. Can happen if cgroup is deleted
+ * from under a polling process.
+ */
+ wake_up_interruptible(&t->event_wait);
+
+ mutex_lock(&group->trigger_lock);
+
+ if (!list_empty(&t->node)) {
+ struct psi_trigger *tmp;
+ u64 period = ULLONG_MAX;
+
+ list_del(&t->node);
+ group->nr_triggers[t->state]--;
+ if (!group->nr_triggers[t->state])
+ group->poll_states &= ~(1 << t->state);
+ /* reset min update period for the remaining triggers */
+ list_for_each_entry(tmp, &group->triggers, node)
+ period = min(period, div_u64(tmp->win.size,
+ UPDATES_PER_WINDOW));
+ group->poll_min_period = period;
+ /* Destroy poll_kworker when the last trigger is destroyed */
+ if (group->poll_states == 0) {
+ group->polling_until = 0;
+ kworker_to_destroy = rcu_dereference_protected(
+ group->poll_kworker,
+ lockdep_is_held(&group->trigger_lock));
+ rcu_assign_pointer(group->poll_kworker, NULL);
+ }
+ }
+
+ mutex_unlock(&group->trigger_lock);
+
+ /*
+ * Wait for both *trigger_ptr from psi_trigger_replace and
+ * poll_kworker RCUs to complete their read-side critical sections
+ * before destroying the trigger and optionally the poll_kworker
+ */
+ synchronize_rcu();
+ /*
+ * Destroy the kworker after releasing trigger_lock to prevent a
+ * deadlock while waiting for psi_poll_work to acquire trigger_lock
+ */
+ if (kworker_to_destroy) {
+ kthread_cancel_delayed_work_sync(&group->poll_work);
+ kthread_destroy_worker(kworker_to_destroy);
+ }
+ kfree(t);
+}
+
+void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new)
+{
+ struct psi_trigger *old = *trigger_ptr;
+
+ if (static_branch_likely(&psi_disabled))
+ return;
+
+ rcu_assign_pointer(*trigger_ptr, new);
+ if (old)
+ kref_put(&old->refcount, psi_trigger_destroy);
+}
+
+__poll_t psi_trigger_poll(void **trigger_ptr,
+ struct file *file, poll_table *wait)
+{
+ __poll_t ret = DEFAULT_POLLMASK;
+ struct psi_trigger *t;
+
+ if (static_branch_likely(&psi_disabled))
+ return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
+
+ rcu_read_lock();
+
+ t = rcu_dereference(*(void __rcu __force **)trigger_ptr);
+ if (!t) {
+ rcu_read_unlock();
+ return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
+ }
+ kref_get(&t->refcount);
+
+ rcu_read_unlock();
+
+ poll_wait(file, &t->event_wait, wait);
+
+ if (cmpxchg(&t->event, 1, 0) == 1)
+ ret |= EPOLLPRI;
+
+ kref_put(&t->refcount, psi_trigger_destroy);
+
+ return ret;
+}
+
+static ssize_t psi_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, enum psi_res res)
+{
+ char buf[32];
+ size_t buf_size;
+ struct seq_file *seq;
+ struct psi_trigger *new;
+
+ if (static_branch_likely(&psi_disabled))
+ return -EOPNOTSUPP;
+
+ buf_size = min(nbytes, (sizeof(buf) - 1));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+
+ buf[buf_size - 1] = '\0';
+
+ new = psi_trigger_create(&psi_system, buf, nbytes, res);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ seq = file->private_data;
+ /* Take seq->lock to protect seq->private from concurrent writes */
+ mutex_lock(&seq->lock);
+ psi_trigger_replace(&seq->private, new);
+ mutex_unlock(&seq->lock);
+
+ return nbytes;
+}
+
+static ssize_t psi_io_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_IO);
+}
+
+static ssize_t psi_memory_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_MEM);
+}
+
+static ssize_t psi_cpu_write(struct file *file, const char __user *user_buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return psi_write(file, user_buf, nbytes, PSI_CPU);
+}
+
+static __poll_t psi_fop_poll(struct file *file, poll_table *wait)
+{
+ struct seq_file *seq = file->private_data;
+
+ return psi_trigger_poll(&seq->private, file, wait);
+}
+
+static int psi_fop_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+
+ psi_trigger_replace(&seq->private, NULL);
+ return single_release(inode, file);
+}
+
static const struct file_operations psi_io_fops = {
.open = psi_io_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .write = psi_io_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
};
static const struct file_operations psi_memory_fops = {
.open = psi_memory_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .write = psi_memory_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
};
static const struct file_operations psi_cpu_fops = {
.open = psi_cpu_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .write = psi_cpu_write,
+ .poll = psi_fop_poll,
+ .release = psi_fop_release,
};
static int __init psi_proc_init(void)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 90fa23d36565..1e6b909dca36 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2555,6 +2555,8 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
if (rt_runtime_us < 0)
rt_runtime = RUNTIME_INF;
+ else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}
@@ -2575,6 +2577,9 @@ int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
{
u64 rt_runtime, rt_period;
+ if (rt_period_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+
rt_period = rt_period_us * NSEC_PER_USEC;
rt_runtime = tg->rt_bandwidth.rt_runtime;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efa686eeff26..b52ed1ada0be 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -780,7 +780,7 @@ struct root_domain {
* NULL-terminated list of performance domains intersecting with the
* CPUs of the rd. Protected by RCU.
*/
- struct perf_domain *pd;
+ struct perf_domain __rcu *pd;
};
extern struct root_domain def_root_domain;
@@ -869,8 +869,8 @@ struct rq {
atomic_t nr_iowait;
#ifdef CONFIG_SMP
- struct root_domain *rd;
- struct sched_domain *sd;
+ struct root_domain *rd;
+ struct sched_domain __rcu *sd;
unsigned long cpu_capacity;
unsigned long cpu_capacity_orig;
@@ -1324,13 +1324,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
return sd;
}
-DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
-DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
struct sched_group_capacity {
@@ -2185,7 +2185,7 @@ static inline u64 irq_time_read(int cpu)
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
#ifdef CONFIG_CPU_FREQ
-DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
/**
* cpufreq_update_util - Take a note about CPU utilization changes.
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ab7f371a3a17..f53f89df837d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -615,13 +615,13 @@ static void destroy_sched_domains(struct sched_domain *sd)
* the cpumask of the domain), this allows us to quickly tell if
* two CPUs are in the same cache domain, see cpus_share_cache().
*/
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
static void update_top_cache_domain(int cpu)
@@ -1059,6 +1059,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
struct sched_domain *child = sd->child;
struct sched_group *sg;
+ bool already_visited;
if (child)
cpu = cpumask_first(sched_domain_span(child));
@@ -1066,9 +1067,14 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
sg = *per_cpu_ptr(sdd->sg, cpu);
sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
- /* For claim_allocations: */
- atomic_inc(&sg->ref);
- atomic_inc(&sg->sgc->ref);
+ /* Increase refcounts for claim_allocations: */
+ already_visited = atomic_inc_return(&sg->ref) > 1;
+ /* sgc visits should follow a similar trend as sg */
+ WARN_ON(already_visited != (atomic_inc_return(&sg->sgc->ref) > 1));
+
+ /* If we have already visited that group, it's already initialized. */
+ if (already_visited)
+ return sg;
if (child) {
cpumask_copy(sched_group_span(sg), sched_domain_span(child));
@@ -1087,8 +1093,8 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
/*
* build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
+ * covered by the given span, will set each group's ->cpumask correctly,
+ * and will initialize their ->sgc.
*
* Assumes the sched_domain tree is fully constructed
*/
@@ -2075,9 +2081,8 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
}
/*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated CPUs, but could be used to
- * exclude other special cases in the future.
+ * Set up scheduler domains and groups. For now this just excludes isolated
+ * CPUs, but could be used to exclude other special cases in the future.
*/
int sched_init_domains(const struct cpumask *cpu_map)
{
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 6eb1f8efd221..fa0f9adfb752 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic waiting primitives.
*
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index c67c6d24adc2..45eba18a2898 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* The implementation of the wait_bit*() and related waiting APIs:
*/
OpenPOWER on IntegriCloud