summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/Makefile1
-rw-r--r--kernel/sched/autogroup.c3
-rw-r--r--kernel/sched/completion.c30
-rw-r--r--kernel/sched/core.c64
-rw-r--r--kernel/sched/cpudeadline.c27
-rw-r--r--kernel/sched/cpufreq_schedutil.c98
-rw-r--r--kernel/sched/cpupri.c2
-rw-r--r--kernel/sched/deadline.c85
-rw-r--r--kernel/sched/debug.c85
-rw-r--r--kernel/sched/fair.c502
-rw-r--r--kernel/sched/idle.c8
-rw-r--r--kernel/sched/membarrier.c152
-rw-r--r--kernel/sched/rt.c2
-rw-r--r--kernel/sched/sched.h25
-rw-r--r--kernel/sched/swait.c6
-rw-r--r--kernel/sched/topology.c41
16 files changed, 759 insertions, 372 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 53f0164ed362..78f54932ea1d 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -25,3 +25,4 @@ obj-$(CONFIG_SCHED_DEBUG) += debug.o
obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
obj-$(CONFIG_CPU_FREQ) += cpufreq.o
obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
+obj-$(CONFIG_MEMBARRIER) += membarrier.o
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index da39489d2d80..de6d7f4dfcb5 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -71,7 +71,6 @@ static inline struct autogroup *autogroup_create(void)
goto out_fail;
tg = sched_create_group(&root_task_group);
-
if (IS_ERR(tg))
goto out_free;
@@ -101,7 +100,7 @@ out_free:
out_fail:
if (printk_ratelimit()) {
printk(KERN_WARNING "autogroup_create: %s failure.\n",
- ag ? "sched_create_group()" : "kmalloc()");
+ ag ? "sched_create_group()" : "kzalloc()");
}
return autogroup_kref_get(&autogroup_default);
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 13fc5ae9bf2f..cc873075c3bd 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -32,6 +32,12 @@ void complete(struct completion *x)
unsigned long flags;
spin_lock_irqsave(&x->wait.lock, flags);
+
+ /*
+ * Perform commit of crossrelease here.
+ */
+ complete_release_commit(x);
+
if (x->done != UINT_MAX)
x->done++;
__wake_up_locked(&x->wait, TASK_NORMAL, 1);
@@ -47,6 +53,13 @@ EXPORT_SYMBOL(complete);
*
* It may be assumed that this function implies a write memory barrier before
* changing the task state if and only if any tasks are woken up.
+ *
+ * Since complete_all() sets the completion of @x permanently to done
+ * to allow multiple waiters to finish, a call to reinit_completion()
+ * must be used on @x if @x is to be used again. The code must make
+ * sure that all waiters have woken and finished before reinitializing
+ * @x. Also note that the function completion_done() can not be used
+ * to know if there are still waiters after complete_all() has been called.
*/
void complete_all(struct completion *x)
{
@@ -92,9 +105,14 @@ __wait_for_common(struct completion *x,
{
might_sleep();
+ complete_acquire(x);
+
spin_lock_irq(&x->wait.lock);
timeout = do_wait_for_common(x, action, timeout, state);
spin_unlock_irq(&x->wait.lock);
+
+ complete_release(x);
+
return timeout;
}
@@ -297,9 +315,12 @@ EXPORT_SYMBOL(try_wait_for_completion);
* Return: 0 if there are waiters (wait_for_completion() in progress)
* 1 if there are no waiters.
*
+ * Note, this will always return true if complete_all() was called on @X.
*/
bool completion_done(struct completion *x)
{
+ unsigned long flags;
+
if (!READ_ONCE(x->done))
return false;
@@ -307,14 +328,9 @@ bool completion_done(struct completion *x)
* If ->done, we need to wait for complete() to release ->wait.lock
* otherwise we can end up freeing the completion before complete()
* is done referencing it.
- *
- * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders
- * the loads of ->done and ->wait.lock such that we cannot observe
- * the lock before complete() acquires it while observing the ->done
- * after it's acquired the lock.
*/
- smp_rmb();
- spin_unlock_wait(&x->wait.lock);
+ spin_lock_irqsave(&x->wait.lock, flags);
+ spin_unlock_irqrestore(&x->wait.lock, flags);
return true;
}
EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0869b20fba81..6d2c7ff9ba98 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -951,8 +951,13 @@ struct migration_arg {
static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
struct task_struct *p, int dest_cpu)
{
- if (unlikely(!cpu_active(dest_cpu)))
- return rq;
+ if (p->flags & PF_KTHREAD) {
+ if (unlikely(!cpu_online(dest_cpu)))
+ return rq;
+ } else {
+ if (unlikely(!cpu_active(dest_cpu)))
+ return rq;
+ }
/* Affinity changed (again). */
if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
@@ -1967,8 +1972,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* reordered with p->state check below. This pairs with mb() in
* set_current_state() the waiting thread does.
*/
- smp_mb__before_spinlock();
raw_spin_lock_irqsave(&p->pi_lock, flags);
+ smp_mb__after_spinlock();
if (!(p->state & state))
goto out;
@@ -2635,6 +2640,16 @@ static struct rq *finish_task_switch(struct task_struct *prev)
prev_state = prev->state;
vtime_task_switch(prev);
perf_event_task_sched_in(prev, current);
+ /*
+ * The membarrier system call requires a full memory barrier
+ * after storing to rq->curr, before going back to user-space.
+ *
+ * TODO: This smp_mb__after_unlock_lock can go away if PPC end
+ * up adding a full barrier to switch_mm(), or we should figure
+ * out if a smp_mb__after_unlock_lock is really the proper API
+ * to use.
+ */
+ smp_mb__after_unlock_lock();
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
@@ -3281,8 +3296,8 @@ static void __sched notrace __schedule(bool preempt)
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up().
*/
- smp_mb__before_spinlock();
rq_lock(rq, &rf);
+ smp_mb__after_spinlock();
/* Promote REQ to ACT */
rq->clock_update_flags <<= 1;
@@ -3324,6 +3339,21 @@ static void __sched notrace __schedule(bool preempt)
if (likely(prev != next)) {
rq->nr_switches++;
rq->curr = next;
+ /*
+ * The membarrier system call requires each architecture
+ * to have a full memory barrier after updating
+ * rq->curr, before returning to user-space. For TSO
+ * (e.g. x86), the architecture must provide its own
+ * barrier in switch_mm(). For weakly ordered machines
+ * for which spin_unlock() acts as a full memory
+ * barrier, finish_lock_switch() in common code takes
+ * care of this barrier. For weakly ordered machines for
+ * which spin_unlock() acts as a RELEASE barrier (only
+ * arm64 and PowerPC), arm64 has a full barrier in
+ * switch_to(), and PowerPC has
+ * smp_mb__after_unlock_lock() before
+ * finish_lock_switch().
+ */
++*switch_count;
trace_sched_switch(preempt, prev, next);
@@ -3352,8 +3382,8 @@ void __noreturn do_task_dead(void)
* To avoid it, we have to wait for releasing tsk->pi_lock which
* is held by try_to_wake_up()
*/
- smp_mb();
- raw_spin_unlock_wait(&current->pi_lock);
+ raw_spin_lock_irq(&current->pi_lock);
+ raw_spin_unlock_irq(&current->pi_lock);
/* Causes final put_task_struct in finish_task_switch(): */
__set_current_state(TASK_DEAD);
@@ -5103,24 +5133,17 @@ out_unlock:
return retval;
}
-static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
-
void sched_show_task(struct task_struct *p)
{
unsigned long free = 0;
int ppid;
- unsigned long state = p->state;
-
- /* Make sure the string lines up properly with the number of task states: */
- BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1);
if (!try_get_task_stack(p))
return;
- if (state)
- state = __ffs(state) + 1;
- printk(KERN_INFO "%-15.15s %c", p->comm,
- state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
- if (state == TASK_RUNNING)
+
+ printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p));
+
+ if (p->state == TASK_RUNNING)
printk(KERN_CONT " running task ");
#ifdef CONFIG_DEBUG_STACK_USAGE
free = stack_not_used(p);
@@ -5177,11 +5200,6 @@ void show_state_filter(unsigned long state_filter)
debug_show_all_locks();
}
-void init_idle_bootup_task(struct task_struct *idle)
-{
- idle->sched_class = &idle_sched_class;
-}
-
/**
* init_idle - set up an idle thread for a given CPU
* @idle: task in question
@@ -5438,7 +5456,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
*/
next = pick_next_task(rq, &fake_task, rf);
BUG_ON(!next);
- next->sched_class->put_prev_task(rq, next);
+ put_prev_task(rq, next);
/*
* Rules for changing task_struct::cpus_allowed are holding
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index fba235c7d026..8d9562d890d3 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -119,29 +119,29 @@ static inline int cpudl_maximum(struct cpudl *cp)
* @p: the task
* @later_mask: a mask to fill in with the selected CPUs (or NULL)
*
- * Returns: int - best CPU (heap maximum if suitable)
+ * Returns: int - CPUs were found
*/
int cpudl_find(struct cpudl *cp, struct task_struct *p,
struct cpumask *later_mask)
{
- int best_cpu = -1;
const struct sched_dl_entity *dl_se = &p->dl;
if (later_mask &&
cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
- best_cpu = cpumask_any(later_mask);
- goto out;
- } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
- dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
- best_cpu = cpudl_maximum(cp);
- if (later_mask)
- cpumask_set_cpu(best_cpu, later_mask);
- }
+ return 1;
+ } else {
+ int best_cpu = cpudl_maximum(cp);
+ WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
-out:
- WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
+ if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) &&
+ dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+ if (later_mask)
+ cpumask_set_cpu(best_cpu, later_mask);
- return best_cpu;
+ return 1;
+ }
+ }
+ return 0;
}
/*
@@ -246,7 +246,6 @@ int cpudl_init(struct cpudl *cp)
{
int i;
- memset(cp, 0, sizeof(*cp));
raw_spin_lock_init(&cp->lock);
cp->size = 0;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 29a397067ffa..9209d83ecdcf 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -52,9 +52,11 @@ struct sugov_policy {
struct sugov_cpu {
struct update_util_data update_util;
struct sugov_policy *sg_policy;
+ unsigned int cpu;
- unsigned long iowait_boost;
- unsigned long iowait_boost_max;
+ bool iowait_boost_pending;
+ unsigned int iowait_boost;
+ unsigned int iowait_boost_max;
u64 last_update;
/* The fields below are only needed when sharing a policy. */
@@ -76,6 +78,26 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
{
s64 delta_ns;
+ /*
+ * Since cpufreq_update_util() is called with rq->lock held for
+ * the @target_cpu, our per-cpu data is fully serialized.
+ *
+ * However, drivers cannot in general deal with cross-cpu
+ * requests, so while get_next_freq() will work, our
+ * sugov_update_commit() call may not for the fast switching platforms.
+ *
+ * Hence stop here for remote requests if they aren't supported
+ * by the hardware, as calculating the frequency is pointless if
+ * we cannot in fact act on it.
+ *
+ * For the slow switching platforms, the kthread is always scheduled on
+ * the right set of CPUs and any CPU can find the next frequency and
+ * schedule the kthread.
+ */
+ if (sg_policy->policy->fast_switch_enabled &&
+ !cpufreq_can_do_remote_dvfs(sg_policy->policy))
+ return false;
+
if (sg_policy->work_in_progress)
return false;
@@ -106,7 +128,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
if (policy->fast_switch_enabled) {
next_freq = cpufreq_driver_fast_switch(policy, next_freq);
- if (next_freq == CPUFREQ_ENTRY_INVALID)
+ if (!next_freq)
return;
policy->cur = next_freq;
@@ -154,12 +176,12 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
return cpufreq_driver_resolve_freq(policy, freq);
}
-static void sugov_get_util(unsigned long *util, unsigned long *max)
+static void sugov_get_util(unsigned long *util, unsigned long *max, int cpu)
{
- struct rq *rq = this_rq();
+ struct rq *rq = cpu_rq(cpu);
unsigned long cfs_max;
- cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
+ cfs_max = arch_scale_cpu_capacity(NULL, cpu);
*util = min(rq->cfs.avg.util_avg, cfs_max);
*max = cfs_max;
@@ -169,30 +191,54 @@ static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
unsigned int flags)
{
if (flags & SCHED_CPUFREQ_IOWAIT) {
- sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+ if (sg_cpu->iowait_boost_pending)
+ return;
+
+ sg_cpu->iowait_boost_pending = true;
+
+ if (sg_cpu->iowait_boost) {
+ sg_cpu->iowait_boost <<= 1;
+ if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
+ sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+ } else {
+ sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+ }
} else if (sg_cpu->iowait_boost) {
s64 delta_ns = time - sg_cpu->last_update;
/* Clear iowait_boost if the CPU apprears to have been idle. */
- if (delta_ns > TICK_NSEC)
+ if (delta_ns > TICK_NSEC) {
sg_cpu->iowait_boost = 0;
+ sg_cpu->iowait_boost_pending = false;
+ }
}
}
static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
unsigned long *max)
{
- unsigned long boost_util = sg_cpu->iowait_boost;
- unsigned long boost_max = sg_cpu->iowait_boost_max;
+ unsigned int boost_util, boost_max;
- if (!boost_util)
+ if (!sg_cpu->iowait_boost)
return;
+ if (sg_cpu->iowait_boost_pending) {
+ sg_cpu->iowait_boost_pending = false;
+ } else {
+ sg_cpu->iowait_boost >>= 1;
+ if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
+ sg_cpu->iowait_boost = 0;
+ return;
+ }
+ }
+
+ boost_util = sg_cpu->iowait_boost;
+ boost_max = sg_cpu->iowait_boost_max;
+
if (*util * boost_max < *max * boost_util) {
*util = boost_util;
*max = boost_max;
}
- sg_cpu->iowait_boost >>= 1;
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -229,7 +275,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (flags & SCHED_CPUFREQ_RT_DL) {
next_f = policy->cpuinfo.max_freq;
} else {
- sugov_get_util(&util, &max);
+ sugov_get_util(&util, &max, sg_cpu->cpu);
sugov_iowait_boost(sg_cpu, &util, &max);
next_f = get_next_freq(sg_policy, util, max);
/*
@@ -264,6 +310,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
delta_ns = time - j_sg_cpu->last_update;
if (delta_ns > TICK_NSEC) {
j_sg_cpu->iowait_boost = 0;
+ j_sg_cpu->iowait_boost_pending = false;
continue;
}
if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
@@ -290,7 +337,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
unsigned long util, max;
unsigned int next_f;
- sugov_get_util(&util, &max);
+ sugov_get_util(&util, &max, sg_cpu->cpu);
raw_spin_lock(&sg_policy->update_lock);
@@ -445,7 +492,11 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
}
sg_policy->thread = thread;
- kthread_bind_mask(thread, policy->related_cpus);
+
+ /* Kthread is bound to all CPUs by default */
+ if (!policy->dvfs_possible_from_any_cpu)
+ kthread_bind_mask(thread, policy->related_cpus);
+
init_irq_work(&sg_policy->irq_work, sugov_irq_work);
mutex_init(&sg_policy->work_lock);
@@ -528,16 +579,7 @@ static int sugov_init(struct cpufreq_policy *policy)
goto stop_kthread;
}
- if (policy->transition_delay_us) {
- tunables->rate_limit_us = policy->transition_delay_us;
- } else {
- unsigned int lat;
-
- tunables->rate_limit_us = LATENCY_MULTIPLIER;
- lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
- if (lat)
- tunables->rate_limit_us *= lat;
- }
+ tunables->rate_limit_us = cpufreq_policy_transition_delay_us(policy);
policy->governor_data = sg_policy;
sg_policy->tunables = tunables;
@@ -655,6 +697,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
static struct cpufreq_governor schedutil_gov = {
.name = "schedutil",
.owner = THIS_MODULE,
+ .dynamic_switching = true,
.init = sugov_init,
.exit = sugov_exit,
.start = sugov_start,
@@ -671,6 +714,11 @@ struct cpufreq_governor *cpufreq_default_governor(void)
static int __init sugov_register(void)
{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(sugov_cpu, cpu).cpu = cpu;
+
return cpufreq_register_governor(&schedutil_gov);
}
fs_initcall(sugov_register);
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 981fcd7dc394..2511aba36b89 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -209,8 +209,6 @@ int cpupri_init(struct cpupri *cp)
{
int i;
- memset(cp, 0, sizeof(*cp));
-
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 755bd3f1a1a9..0191ec7667c3 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -296,7 +296,7 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
{
struct sched_dl_entity *dl_se = &p->dl;
- return dl_rq->rb_leftmost == &dl_se->rb_node;
+ return dl_rq->root.rb_leftmost == &dl_se->rb_node;
}
void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
@@ -320,7 +320,7 @@ void init_dl_bw(struct dl_bw *dl_b)
void init_dl_rq(struct dl_rq *dl_rq)
{
- dl_rq->rb_root = RB_ROOT;
+ dl_rq->root = RB_ROOT_CACHED;
#ifdef CONFIG_SMP
/* zero means no -deadline tasks */
@@ -328,7 +328,7 @@ void init_dl_rq(struct dl_rq *dl_rq)
dl_rq->dl_nr_migratory = 0;
dl_rq->overloaded = 0;
- dl_rq->pushable_dl_tasks_root = RB_ROOT;
+ dl_rq->pushable_dl_tasks_root = RB_ROOT_CACHED;
#else
init_dl_bw(&dl_rq->dl_bw);
#endif
@@ -410,10 +410,10 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
{
struct dl_rq *dl_rq = &rq->dl;
- struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+ struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_root.rb_node;
struct rb_node *parent = NULL;
struct task_struct *entry;
- int leftmost = 1;
+ bool leftmost = true;
BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
@@ -425,17 +425,16 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
link = &parent->rb_left;
else {
link = &parent->rb_right;
- leftmost = 0;
+ leftmost = false;
}
}
- if (leftmost) {
- dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+ if (leftmost)
dl_rq->earliest_dl.next = p->dl.deadline;
- }
rb_link_node(&p->pushable_dl_tasks, parent, link);
- rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+ rb_insert_color_cached(&p->pushable_dl_tasks,
+ &dl_rq->pushable_dl_tasks_root, leftmost);
}
static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
@@ -445,24 +444,23 @@ static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
return;
- if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+ if (dl_rq->pushable_dl_tasks_root.rb_leftmost == &p->pushable_dl_tasks) {
struct rb_node *next_node;
next_node = rb_next(&p->pushable_dl_tasks);
- dl_rq->pushable_dl_tasks_leftmost = next_node;
if (next_node) {
dl_rq->earliest_dl.next = rb_entry(next_node,
struct task_struct, pushable_dl_tasks)->dl.deadline;
}
}
- rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+ rb_erase_cached(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
}
static inline int has_pushable_dl_tasks(struct rq *rq)
{
- return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+ return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root.rb_root);
}
static int push_dl_task(struct rq *rq);
@@ -1136,7 +1134,7 @@ static void update_curr_dl(struct rq *rq)
}
/* kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
+ cpufreq_update_util(rq, SCHED_CPUFREQ_DL);
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
@@ -1266,7 +1264,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
dl_rq->earliest_dl.next = 0;
cpudl_clear(&rq->rd->cpudl, rq->cpu);
} else {
- struct rb_node *leftmost = dl_rq->rb_leftmost;
+ struct rb_node *leftmost = dl_rq->root.rb_leftmost;
struct sched_dl_entity *entry;
entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
@@ -1313,7 +1311,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
- struct rb_node **link = &dl_rq->rb_root.rb_node;
+ struct rb_node **link = &dl_rq->root.rb_root.rb_node;
struct rb_node *parent = NULL;
struct sched_dl_entity *entry;
int leftmost = 1;
@@ -1331,11 +1329,8 @@ static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
}
}
- if (leftmost)
- dl_rq->rb_leftmost = &dl_se->rb_node;
-
rb_link_node(&dl_se->rb_node, parent, link);
- rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
+ rb_insert_color_cached(&dl_se->rb_node, &dl_rq->root, leftmost);
inc_dl_tasks(dl_se, dl_rq);
}
@@ -1347,14 +1342,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
if (RB_EMPTY_NODE(&dl_se->rb_node))
return;
- if (dl_rq->rb_leftmost == &dl_se->rb_node) {
- struct rb_node *next_node;
-
- next_node = rb_next(&dl_se->rb_node);
- dl_rq->rb_leftmost = next_node;
- }
-
- rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
+ rb_erase_cached(&dl_se->rb_node, &dl_rq->root);
RB_CLEAR_NODE(&dl_se->rb_node);
dec_dl_tasks(dl_se, dl_rq);
@@ -1594,7 +1582,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
* let's hope p can move out.
*/
if (rq->curr->nr_cpus_allowed == 1 ||
- cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
+ !cpudl_find(&rq->rd->cpudl, rq->curr, NULL))
return;
/*
@@ -1602,7 +1590,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
* see if it is pushed or pulled somewhere else.
*/
if (p->nr_cpus_allowed != 1 &&
- cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
+ cpudl_find(&rq->rd->cpudl, p, NULL))
return;
resched_curr(rq);
@@ -1647,7 +1635,7 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
struct dl_rq *dl_rq)
{
- struct rb_node *left = dl_rq->rb_leftmost;
+ struct rb_node *left = rb_first_cached(&dl_rq->root);
if (!left)
return NULL;
@@ -1655,7 +1643,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
return rb_entry(left, struct sched_dl_entity, rb_node);
}
-struct task_struct *
+static struct task_struct *
pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_dl_entity *dl_se;
@@ -1771,7 +1759,7 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
*/
static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
{
- struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost;
+ struct rb_node *next_node = rq->dl.pushable_dl_tasks_root.rb_leftmost;
struct task_struct *p = NULL;
if (!has_pushable_dl_tasks(rq))
@@ -1798,7 +1786,7 @@ static int find_later_rq(struct task_struct *task)
struct sched_domain *sd;
struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
int this_cpu = smp_processor_id();
- int best_cpu, cpu = task_cpu(task);
+ int cpu = task_cpu(task);
/* Make sure the mask is initialized first */
if (unlikely(!later_mask))
@@ -1811,17 +1799,14 @@ static int find_later_rq(struct task_struct *task)
* We have to consider system topology and task affinity
* first, then we can look for a suitable cpu.
*/
- best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
- task, later_mask);
- if (best_cpu == -1)
+ if (!cpudl_find(&task_rq(task)->rd->cpudl, task, later_mask))
return -1;
/*
- * If we are here, some target has been found,
- * the most suitable of which is cached in best_cpu.
- * This is, among the runqueues where the current tasks
- * have later deadlines than the task's one, the rq
- * with the latest possible one.
+ * If we are here, some targets have been found, including
+ * the most suitable which is, among the runqueues where the
+ * current tasks have later deadlines than the task's one, the
+ * rq with the latest possible one.
*
* Now we check how well this matches with task's
* affinity and system topology.
@@ -1841,6 +1826,7 @@ static int find_later_rq(struct task_struct *task)
rcu_read_lock();
for_each_domain(cpu, sd) {
if (sd->flags & SD_WAKE_AFFINE) {
+ int best_cpu;
/*
* If possible, preempting this_cpu is
@@ -1852,12 +1838,15 @@ static int find_later_rq(struct task_struct *task)
return this_cpu;
}
+ best_cpu = cpumask_first_and(later_mask,
+ sched_domain_span(sd));
/*
- * Last chance: if best_cpu is valid and is
- * in the mask, that becomes our choice.
+ * Last chance: if a cpu being in both later_mask
+ * and current sd span is valid, that becomes our
+ * choice. Of course, the latest possible cpu is
+ * already under consideration through later_mask.
*/
- if (best_cpu < nr_cpu_ids &&
- cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+ if (best_cpu < nr_cpu_ids) {
rcu_read_unlock();
return best_cpu;
}
@@ -1944,7 +1933,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
if (!has_pushable_dl_tasks(rq))
return NULL;
- p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+ p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost,
struct task_struct, pushable_dl_tasks);
BUG_ON(rq->cpu != task_cpu(p));
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4fa66de52bd6..8e536d963652 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -327,38 +327,78 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
return table;
}
+static cpumask_var_t sd_sysctl_cpus;
static struct ctl_table_header *sd_sysctl_header;
+
void register_sched_domain_sysctl(void)
{
- int i, cpu_num = num_possible_cpus();
- struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+ static struct ctl_table *cpu_entries;
+ static struct ctl_table **cpu_idx;
char buf[32];
+ int i;
- WARN_ON(sd_ctl_dir[0].child);
- sd_ctl_dir[0].child = entry;
+ if (!cpu_entries) {
+ cpu_entries = sd_alloc_ctl_entry(num_possible_cpus() + 1);
+ if (!cpu_entries)
+ return;
- if (entry == NULL)
- return;
+ WARN_ON(sd_ctl_dir[0].child);
+ sd_ctl_dir[0].child = cpu_entries;
+ }
- for_each_possible_cpu(i) {
- snprintf(buf, 32, "cpu%d", i);
- entry->procname = kstrdup(buf, GFP_KERNEL);
- entry->mode = 0555;
- entry->child = sd_alloc_ctl_cpu_table(i);
- entry++;
+ if (!cpu_idx) {
+ struct ctl_table *e = cpu_entries;
+
+ cpu_idx = kcalloc(nr_cpu_ids, sizeof(struct ctl_table*), GFP_KERNEL);
+ if (!cpu_idx)
+ return;
+
+ /* deal with sparse possible map */
+ for_each_possible_cpu(i) {
+ cpu_idx[i] = e;
+ e++;
+ }
+ }
+
+ if (!cpumask_available(sd_sysctl_cpus)) {
+ if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
+ return;
+
+ /* init to possible to not have holes in @cpu_entries */
+ cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
+ }
+
+ for_each_cpu(i, sd_sysctl_cpus) {
+ struct ctl_table *e = cpu_idx[i];
+
+ if (e->child)
+ sd_free_ctl_entry(&e->child);
+
+ if (!e->procname) {
+ snprintf(buf, 32, "cpu%d", i);
+ e->procname = kstrdup(buf, GFP_KERNEL);
+ }
+ e->mode = 0555;
+ e->child = sd_alloc_ctl_cpu_table(i);
+
+ __cpumask_clear_cpu(i, sd_sysctl_cpus);
}
WARN_ON(sd_sysctl_header);
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
}
+void dirty_sched_domain_sysctl(int cpu)
+{
+ if (cpumask_available(sd_sysctl_cpus))
+ __cpumask_set_cpu(cpu, sd_sysctl_cpus);
+}
+
/* may be called multiple times per register */
void unregister_sched_domain_sysctl(void)
{
unregister_sysctl_table(sd_sysctl_header);
sd_sysctl_header = NULL;
- if (sd_ctl_dir[0].child)
- sd_free_ctl_entry(&sd_ctl_dir[0].child);
}
#endif /* CONFIG_SYSCTL */
#endif /* CONFIG_SMP */
@@ -421,13 +461,15 @@ static char *task_group_path(struct task_group *tg)
}
#endif
+static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
+
static void
print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
if (rq->curr == p)
- SEQ_printf(m, "R");
+ SEQ_printf(m, ">R");
else
- SEQ_printf(m, " ");
+ SEQ_printf(m, " %c", task_state_to_char(p));
SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
p->comm, task_pid_nr(p),
@@ -456,9 +498,9 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
SEQ_printf(m,
"\nrunnable tasks:\n"
- " task PID tree-key switches prio"
+ " S task PID tree-key switches prio"
" wait-time sum-exec sum-sleep\n"
- "------------------------------------------------------"
+ "-------------------------------------------------------"
"----------------------------------------------------\n");
rcu_read_lock();
@@ -488,7 +530,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
SPLIT_NS(cfs_rq->exec_clock));
raw_spin_lock_irqsave(&rq->lock, flags);
- if (cfs_rq->rb_leftmost)
+ if (rb_first_cached(&cfs_rq->tasks_timeline))
MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
last = __pick_last_entity(cfs_rq);
if (last)
@@ -872,11 +914,12 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
#endif
}
-void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
+ struct seq_file *m)
{
unsigned long nr_switches;
- SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
+ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
get_nr_threads(p));
SEQ_printf(m,
"---------------------------------------------------------"
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c95880e216f6..a5d83ed8dd82 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -513,6 +513,7 @@ static inline int entity_before(struct sched_entity *a,
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
+ struct rb_node *leftmost = rb_first_cached(&cfs_rq->tasks_timeline);
u64 vruntime = cfs_rq->min_vruntime;
@@ -523,10 +524,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
curr = NULL;
}
- if (cfs_rq->rb_leftmost) {
- struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
- struct sched_entity,
- run_node);
+ if (leftmost) { /* non-empty tree */
+ struct sched_entity *se;
+ se = rb_entry(leftmost, struct sched_entity, run_node);
if (!curr)
vruntime = se->vruntime;
@@ -547,10 +547,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
*/
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
+ struct rb_node **link = &cfs_rq->tasks_timeline.rb_root.rb_node;
struct rb_node *parent = NULL;
struct sched_entity *entry;
- int leftmost = 1;
+ bool leftmost = true;
/*
* Find the right place in the rbtree:
@@ -566,36 +566,23 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
link = &parent->rb_left;
} else {
link = &parent->rb_right;
- leftmost = 0;
+ leftmost = false;
}
}
- /*
- * Maintain a cache of leftmost tree entries (it is frequently
- * used):
- */
- if (leftmost)
- cfs_rq->rb_leftmost = &se->run_node;
-
rb_link_node(&se->run_node, parent, link);
- rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
+ rb_insert_color_cached(&se->run_node,
+ &cfs_rq->tasks_timeline, leftmost);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (cfs_rq->rb_leftmost == &se->run_node) {
- struct rb_node *next_node;
-
- next_node = rb_next(&se->run_node);
- cfs_rq->rb_leftmost = next_node;
- }
-
- rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
+ rb_erase_cached(&se->run_node, &cfs_rq->tasks_timeline);
}
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
- struct rb_node *left = cfs_rq->rb_leftmost;
+ struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
if (!left)
return NULL;
@@ -616,7 +603,7 @@ static struct sched_entity *__pick_next_entity(struct sched_entity *se)
#ifdef CONFIG_SCHED_DEBUG
struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
- struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
+ struct rb_node *last = rb_last(&cfs_rq->tasks_timeline.rb_root);
if (!last)
return NULL;
@@ -806,7 +793,7 @@ void post_init_entity_util_avg(struct sched_entity *se)
/*
* For !fair tasks do:
*
- update_cfs_rq_load_avg(now, cfs_rq, false);
+ update_cfs_rq_load_avg(now, cfs_rq);
attach_entity_load_avg(cfs_rq, se);
switched_from_fair(rq, p);
*
@@ -1071,6 +1058,29 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;
+struct numa_group {
+ atomic_t refcount;
+
+ spinlock_t lock; /* nr_tasks, tasks */
+ int nr_tasks;
+ pid_t gid;
+ int active_nodes;
+
+ struct rcu_head rcu;
+ unsigned long total_faults;
+ unsigned long max_faults_cpu;
+ /*
+ * Faults_cpu is used to decide whether memory should move
+ * towards the CPU. As a consequence, these stats are weighted
+ * more by CPU use than by memory faults.
+ */
+ unsigned long *faults_cpu;
+ unsigned long faults[0];
+};
+
+static inline unsigned long group_faults_priv(struct numa_group *ng);
+static inline unsigned long group_faults_shared(struct numa_group *ng);
+
static unsigned int task_nr_scan_windows(struct task_struct *p)
{
unsigned long rss = 0;
@@ -1107,13 +1117,47 @@ static unsigned int task_scan_min(struct task_struct *p)
return max_t(unsigned int, floor, scan);
}
+static unsigned int task_scan_start(struct task_struct *p)
+{
+ unsigned long smin = task_scan_min(p);
+ unsigned long period = smin;
+
+ /* Scale the maximum scan period with the amount of shared memory. */
+ if (p->numa_group) {
+ struct numa_group *ng = p->numa_group;
+ unsigned long shared = group_faults_shared(ng);
+ unsigned long private = group_faults_priv(ng);
+
+ period *= atomic_read(&ng->refcount);
+ period *= shared + 1;
+ period /= private + shared + 1;
+ }
+
+ return max(smin, period);
+}
+
static unsigned int task_scan_max(struct task_struct *p)
{
- unsigned int smin = task_scan_min(p);
- unsigned int smax;
+ unsigned long smin = task_scan_min(p);
+ unsigned long smax;
/* Watch for min being lower than max due to floor calculations */
smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
+
+ /* Scale the maximum scan period with the amount of shared memory. */
+ if (p->numa_group) {
+ struct numa_group *ng = p->numa_group;
+ unsigned long shared = group_faults_shared(ng);
+ unsigned long private = group_faults_priv(ng);
+ unsigned long period = smax;
+
+ period *= atomic_read(&ng->refcount);
+ period *= shared + 1;
+ period /= private + shared + 1;
+
+ smax = max(smax, period);
+ }
+
return max(smin, smax);
}
@@ -1129,26 +1173,6 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
}
-struct numa_group {
- atomic_t refcount;
-
- spinlock_t lock; /* nr_tasks, tasks */
- int nr_tasks;
- pid_t gid;
- int active_nodes;
-
- struct rcu_head rcu;
- unsigned long total_faults;
- unsigned long max_faults_cpu;
- /*
- * Faults_cpu is used to decide whether memory should move
- * towards the CPU. As a consequence, these stats are weighted
- * more by CPU use than by memory faults.
- */
- unsigned long *faults_cpu;
- unsigned long faults[0];
-};
-
/* Shared or private faults. */
#define NR_NUMA_HINT_FAULT_TYPES 2
@@ -1198,6 +1222,30 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
}
+static inline unsigned long group_faults_priv(struct numa_group *ng)
+{
+ unsigned long faults = 0;
+ int node;
+
+ for_each_online_node(node) {
+ faults += ng->faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+
+ return faults;
+}
+
+static inline unsigned long group_faults_shared(struct numa_group *ng)
+{
+ unsigned long faults = 0;
+ int node;
+
+ for_each_online_node(node) {
+ faults += ng->faults[task_faults_idx(NUMA_MEM, node, 0)];
+ }
+
+ return faults;
+}
+
/*
* A node triggering more than 1/3 as many NUMA faults as the maximum is
* considered part of a numa group's pseudo-interleaving set. Migrations
@@ -1378,7 +1426,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
}
-static unsigned long weighted_cpuload(const int cpu);
+static unsigned long weighted_cpuload(struct rq *rq);
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
static unsigned long capacity_of(int cpu);
@@ -1409,7 +1457,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
struct rq *rq = cpu_rq(cpu);
ns->nr_running += rq->nr_running;
- ns->load += weighted_cpuload(cpu);
+ ns->load += weighted_cpuload(rq);
ns->compute_capacity += capacity_of(cpu);
cpus++;
@@ -1808,7 +1856,7 @@ static int task_numa_migrate(struct task_struct *p)
* Reset the scan period if the task is being rescheduled on an
* alternative node to recheck if the tasks is now properly placed.
*/
- p->numa_scan_period = task_scan_min(p);
+ p->numa_scan_period = task_scan_start(p);
if (env.best_task == NULL) {
ret = migrate_task_to(p, env.best_cpu);
@@ -1892,7 +1940,7 @@ static void update_task_scan_period(struct task_struct *p,
unsigned long shared, unsigned long private)
{
unsigned int period_slot;
- int ratio;
+ int lr_ratio, ps_ratio;
int diff;
unsigned long remote = p->numa_faults_locality[0];
@@ -1922,25 +1970,36 @@ static void update_task_scan_period(struct task_struct *p,
* >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
*/
period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
- ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
- if (ratio >= NUMA_PERIOD_THRESHOLD) {
- int slot = ratio - NUMA_PERIOD_THRESHOLD;
+ lr_ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
+ ps_ratio = (private * NUMA_PERIOD_SLOTS) / (private + shared);
+
+ if (ps_ratio >= NUMA_PERIOD_THRESHOLD) {
+ /*
+ * Most memory accesses are local. There is no need to
+ * do fast NUMA scanning, since memory is already local.
+ */
+ int slot = ps_ratio - NUMA_PERIOD_THRESHOLD;
+ if (!slot)
+ slot = 1;
+ diff = slot * period_slot;
+ } else if (lr_ratio >= NUMA_PERIOD_THRESHOLD) {
+ /*
+ * Most memory accesses are shared with other tasks.
+ * There is no point in continuing fast NUMA scanning,
+ * since other tasks may just move the memory elsewhere.
+ */
+ int slot = lr_ratio - NUMA_PERIOD_THRESHOLD;
if (!slot)
slot = 1;
diff = slot * period_slot;
} else {
- diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
-
/*
- * Scale scan rate increases based on sharing. There is an
- * inverse relationship between the degree of sharing and
- * the adjustment made to the scanning period. Broadly
- * speaking the intent is that there is little point
- * scanning faster if shared accesses dominate as it may
- * simply bounce migrations uselessly
+ * Private memory faults exceed (SLOTS-THRESHOLD)/SLOTS,
+ * yet they are not on the local NUMA node. Speed up
+ * NUMA scanning to get the memory moved over.
*/
- ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
- diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
+ int ratio = max(lr_ratio, ps_ratio);
+ diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
}
p->numa_scan_period = clamp(p->numa_scan_period + diff,
@@ -2448,7 +2507,7 @@ void task_numa_work(struct callback_head *work)
if (p->numa_scan_period == 0) {
p->numa_scan_period_max = task_scan_max(p);
- p->numa_scan_period = task_scan_min(p);
+ p->numa_scan_period = task_scan_start(p);
}
next_scan = now + msecs_to_jiffies(p->numa_scan_period);
@@ -2576,7 +2635,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
if (now > curr->node_stamp + period) {
if (!curr->node_stamp)
- curr->numa_scan_period = task_scan_min(curr);
+ curr->numa_scan_period = task_scan_start(curr);
curr->node_stamp += period;
if (!time_before(jiffies, curr->mm->numa_next_scan)) {
@@ -2586,59 +2645,6 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
}
}
-/*
- * Can a task be moved from prev_cpu to this_cpu without causing a load
- * imbalance that would trigger the load balancer?
- */
-static inline bool numa_wake_affine(struct sched_domain *sd,
- struct task_struct *p, int this_cpu,
- int prev_cpu, int sync)
-{
- struct numa_stats prev_load, this_load;
- s64 this_eff_load, prev_eff_load;
-
- update_numa_stats(&prev_load, cpu_to_node(prev_cpu));
- update_numa_stats(&this_load, cpu_to_node(this_cpu));
-
- /*
- * If sync wakeup then subtract the (maximum possible)
- * effect of the currently running task from the load
- * of the current CPU:
- */
- if (sync) {
- unsigned long current_load = task_h_load(current);
-
- if (this_load.load > current_load)
- this_load.load -= current_load;
- else
- this_load.load = 0;
- }
-
- /*
- * In low-load situations, where this_cpu's node is idle due to the
- * sync cause above having dropped this_load.load to 0, move the task.
- * Moving to an idle socket will not create a bad imbalance.
- *
- * Otherwise check if the nodes are near enough in load to allow this
- * task to be woken on this_cpu's node.
- */
- if (this_load.load > 0) {
- unsigned long task_load = task_h_load(p);
-
- this_eff_load = 100;
- this_eff_load *= prev_load.compute_capacity;
-
- prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
- prev_eff_load *= this_load.compute_capacity;
-
- this_eff_load *= this_load.load + task_load;
- prev_eff_load *= prev_load.load - task_load;
-
- return this_eff_load <= prev_eff_load;
- }
-
- return true;
-}
#else
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
@@ -2652,14 +2658,6 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
}
-#ifdef CONFIG_SMP
-static inline bool numa_wake_affine(struct sched_domain *sd,
- struct task_struct *p, int this_cpu,
- int prev_cpu, int sync)
-{
- return true;
-}
-#endif /* !SMP */
#endif /* CONFIG_NUMA_BALANCING */
static void
@@ -2790,6 +2788,31 @@ static inline void update_cfs_shares(struct sched_entity *se)
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
+static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
+{
+ struct rq *rq = rq_of(cfs_rq);
+
+ if (&rq->cfs == cfs_rq) {
+ /*
+ * There are a few boundary cases this might miss but it should
+ * get called often enough that that should (hopefully) not be
+ * a real problem -- added to that it only calls on the local
+ * CPU, so if we enqueue remotely we'll miss an update, but
+ * the next tick/schedule should update.
+ *
+ * It will not get called when we go idle, because the idle
+ * thread is a different class (!fair), nor will the utilization
+ * number include things like RT tasks.
+ *
+ * As is, the util number is not freq-invariant (we'd have to
+ * implement arch_scale_freq_capacity() for that).
+ *
+ * See cpu_util().
+ */
+ cpufreq_update_util(rq, 0);
+ }
+}
+
#ifdef CONFIG_SMP
/*
* Approximate:
@@ -2968,6 +2991,18 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
sa->last_update_time += delta << 10;
/*
+ * running is a subset of runnable (weight) so running can't be set if
+ * runnable is clear. But there are some corner cases where the current
+ * se has been already dequeued but cfs_rq->curr still points to it.
+ * This means that weight will be 0 but not running for a sched_entity
+ * but also for a cfs_rq if the latter becomes idle. As an example,
+ * this happens during idle_balance() which calls
+ * update_blocked_averages()
+ */
+ if (!weight)
+ running = 0;
+
+ /*
* Now we know we crossed measurement unit boundaries. The *_avg
* accrues by two steps:
*
@@ -3276,29 +3311,6 @@ static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
#endif /* CONFIG_FAIR_GROUP_SCHED */
-static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
-{
- if (&this_rq()->cfs == cfs_rq) {
- /*
- * There are a few boundary cases this might miss but it should
- * get called often enough that that should (hopefully) not be
- * a real problem -- added to that it only calls on the local
- * CPU, so if we enqueue remotely we'll miss an update, but
- * the next tick/schedule should update.
- *
- * It will not get called when we go idle, because the idle
- * thread is a different class (!fair), nor will the utilization
- * number include things like RT tasks.
- *
- * As is, the util number is not freq-invariant (we'd have to
- * implement arch_scale_freq_capacity() for that).
- *
- * See cpu_util().
- */
- cpufreq_update_util(rq_of(cfs_rq), 0);
- }
-}
-
/*
* Unsigned subtract and clamp on underflow.
*
@@ -3320,7 +3332,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
* update_cfs_rq_load_avg - update the cfs_rq's load/util averages
* @now: current time, as per cfs_rq_clock_task()
* @cfs_rq: cfs_rq to update
- * @update_freq: should we call cfs_rq_util_change() or will the call do so
*
* The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
* avg. The immediate corollary is that all (fair) tasks must be attached, see
@@ -3334,7 +3345,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
* call update_tg_load_avg() when this function returns true.
*/
static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
struct sched_avg *sa = &cfs_rq->avg;
int decayed, removed_load = 0, removed_util = 0;
@@ -3362,7 +3373,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
- if (update_freq && (decayed || removed_util))
+ if (decayed || removed_util)
cfs_rq_util_change(cfs_rq);
return decayed || removed_load;
@@ -3390,7 +3401,7 @@ static inline void update_load_avg(struct sched_entity *se, int flags)
if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
__update_load_avg_se(now, cpu, cfs_rq, se);
- decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
+ decayed = update_cfs_rq_load_avg(now, cfs_rq);
decayed |= propagate_entity_load_avg(se);
if (decayed && (flags & UPDATE_TG))
@@ -3534,7 +3545,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf);
#else /* CONFIG_SMP */
static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
return 0;
}
@@ -3544,7 +3555,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
static inline void update_load_avg(struct sched_entity *se, int not_used1)
{
- cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
+ cfs_rq_util_change(cfs_rq_of(se));
}
static inline void
@@ -4875,7 +4886,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
* passed.
*/
if (p->in_iowait)
- cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+ cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
for_each_sched_entity(se) {
if (se->on_rq)
@@ -5125,9 +5136,9 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
}
/* Used instead of source_load when we know the type == 0 */
-static unsigned long weighted_cpuload(const int cpu)
+static unsigned long weighted_cpuload(struct rq *rq)
{
- return cfs_rq_runnable_load_avg(&cpu_rq(cpu)->cfs);
+ return cfs_rq_runnable_load_avg(&rq->cfs);
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -5172,7 +5183,7 @@ static void cpu_load_update_idle(struct rq *this_rq)
/*
* bail if there's load or we're actually up-to-date.
*/
- if (weighted_cpuload(cpu_of(this_rq)))
+ if (weighted_cpuload(this_rq))
return;
cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), 0);
@@ -5193,7 +5204,7 @@ void cpu_load_update_nohz_start(void)
* concurrently we'll exit nohz. And cpu_load write can race with
* cpu_load_update_idle() but both updater would be writing the same.
*/
- this_rq->cpu_load[0] = weighted_cpuload(cpu_of(this_rq));
+ this_rq->cpu_load[0] = weighted_cpuload(this_rq);
}
/*
@@ -5209,7 +5220,7 @@ void cpu_load_update_nohz_stop(void)
if (curr_jiffies == this_rq->last_load_update_tick)
return;
- load = weighted_cpuload(cpu_of(this_rq));
+ load = weighted_cpuload(this_rq);
rq_lock(this_rq, &rf);
update_rq_clock(this_rq);
cpu_load_update_nohz(this_rq, curr_jiffies, load);
@@ -5235,7 +5246,7 @@ static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load)
*/
void cpu_load_update_active(struct rq *this_rq)
{
- unsigned long load = weighted_cpuload(cpu_of(this_rq));
+ unsigned long load = weighted_cpuload(this_rq);
if (tick_nohz_tick_stopped())
cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), load);
@@ -5253,7 +5264,7 @@ void cpu_load_update_active(struct rq *this_rq)
static unsigned long source_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long total = weighted_cpuload(cpu);
+ unsigned long total = weighted_cpuload(rq);
if (type == 0 || !sched_feat(LB_BIAS))
return total;
@@ -5268,7 +5279,7 @@ static unsigned long source_load(int cpu, int type)
static unsigned long target_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long total = weighted_cpuload(cpu);
+ unsigned long total = weighted_cpuload(rq);
if (type == 0 || !sched_feat(LB_BIAS))
return total;
@@ -5290,7 +5301,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
- unsigned long load_avg = weighted_cpuload(cpu);
+ unsigned long load_avg = weighted_cpuload(rq);
if (nr_running)
return load_avg / nr_running;
@@ -5345,20 +5356,115 @@ static int wake_wide(struct task_struct *p)
return 1;
}
+struct llc_stats {
+ unsigned long nr_running;
+ unsigned long load;
+ unsigned long capacity;
+ int has_capacity;
+};
+
+static bool get_llc_stats(struct llc_stats *stats, int cpu)
+{
+ struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
+
+ if (!sds)
+ return false;
+
+ stats->nr_running = READ_ONCE(sds->nr_running);
+ stats->load = READ_ONCE(sds->load);
+ stats->capacity = READ_ONCE(sds->capacity);
+ stats->has_capacity = stats->nr_running < per_cpu(sd_llc_size, cpu);
+
+ return true;
+}
+
+/*
+ * Can a task be moved from prev_cpu to this_cpu without causing a load
+ * imbalance that would trigger the load balancer?
+ *
+ * Since we're running on 'stale' values, we might in fact create an imbalance
+ * but recomputing these values is expensive, as that'd mean iteration 2 cache
+ * domains worth of CPUs.
+ */
+static bool
+wake_affine_llc(struct sched_domain *sd, struct task_struct *p,
+ int this_cpu, int prev_cpu, int sync)
+{
+ struct llc_stats prev_stats, this_stats;
+ s64 this_eff_load, prev_eff_load;
+ unsigned long task_load;
+
+ if (!get_llc_stats(&prev_stats, prev_cpu) ||
+ !get_llc_stats(&this_stats, this_cpu))
+ return false;
+
+ /*
+ * If sync wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current LLC.
+ */
+ if (sync) {
+ unsigned long current_load = task_h_load(current);
+
+ /* in this case load hits 0 and this LLC is considered 'idle' */
+ if (current_load > this_stats.load)
+ return true;
+
+ this_stats.load -= current_load;
+ }
+
+ /*
+ * The has_capacity stuff is not SMT aware, but by trying to balance
+ * the nr_running on both ends we try and fill the domain at equal
+ * rates, thereby first consuming cores before siblings.
+ */
+
+ /* if the old cache has capacity, stay there */
+ if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1)
+ return false;
+
+ /* if this cache has capacity, come here */
+ if (this_stats.has_capacity && this_stats.nr_running < prev_stats.nr_running+1)
+ return true;
+
+ /*
+ * Check to see if we can move the load without causing too much
+ * imbalance.
+ */
+ task_load = task_h_load(p);
+
+ this_eff_load = 100;
+ this_eff_load *= prev_stats.capacity;
+
+ prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
+ prev_eff_load *= this_stats.capacity;
+
+ this_eff_load *= this_stats.load + task_load;
+ prev_eff_load *= prev_stats.load - task_load;
+
+ return this_eff_load <= prev_eff_load;
+}
+
static int wake_affine(struct sched_domain *sd, struct task_struct *p,
int prev_cpu, int sync)
{
int this_cpu = smp_processor_id();
- bool affine = false;
+ bool affine;
/*
- * Common case: CPUs are in the same socket, and select_idle_sibling()
- * will do its thing regardless of what we return:
+ * Default to no affine wakeups; wake_affine() should not effect a task
+ * placement the load-balancer feels inclined to undo. The conservative
+ * option is therefore to not move tasks when they wake up.
*/
- if (cpus_share_cache(prev_cpu, this_cpu))
- affine = true;
- else
- affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync);
+ affine = false;
+
+ /*
+ * If the wakeup is across cache domains, try to evaluate if movement
+ * makes sense, otherwise rely on select_idle_siblings() to do
+ * placement inside the cache domain.
+ */
+ if (!cpus_share_cache(prev_cpu, this_cpu))
+ affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync);
schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
if (affine) {
@@ -5550,7 +5656,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
shallowest_idle_cpu = i;
}
} else if (shallowest_idle_cpu == -1) {
- load = weighted_cpuload(i);
+ load = weighted_cpuload(cpu_rq(i));
if (load < min_load || (load == min_load && i == this_cpu)) {
min_load = load;
least_loaded_cpu = i;
@@ -6187,10 +6293,10 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
int new_tasks;
again:
-#ifdef CONFIG_FAIR_GROUP_SCHED
if (!cfs_rq->nr_running)
goto idle;
+#ifdef CONFIG_FAIR_GROUP_SCHED
if (prev->sched_class != &fair_sched_class)
goto simple;
@@ -6220,11 +6326,17 @@ again:
/*
* This call to check_cfs_rq_runtime() will do the
* throttle and dequeue its entity in the parent(s).
- * Therefore the 'simple' nr_running test will indeed
+ * Therefore the nr_running test will indeed
* be correct.
*/
- if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+ if (unlikely(check_cfs_rq_runtime(cfs_rq))) {
+ cfs_rq = &rq->cfs;
+
+ if (!cfs_rq->nr_running)
+ goto idle;
+
goto simple;
+ }
}
se = pick_next_entity(cfs_rq, curr);
@@ -6264,12 +6376,8 @@ again:
return p;
simple:
- cfs_rq = &rq->cfs;
#endif
- if (!cfs_rq->nr_running)
- goto idle;
-
put_prev_task(rq, prev);
do {
@@ -6917,7 +7025,7 @@ static void update_blocked_averages(int cpu)
if (throttled_hierarchy(cfs_rq))
continue;
- if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true))
+ if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
update_tg_load_avg(cfs_rq, 0);
/* Propagate pending load changes to the parent, if any: */
@@ -6990,7 +7098,7 @@ static inline void update_blocked_averages(int cpu)
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
+ update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
rq_unlock_irqrestore(rq, &rf);
}
@@ -7036,6 +7144,7 @@ struct sg_lb_stats {
struct sd_lb_stats {
struct sched_group *busiest; /* Busiest group in this sd */
struct sched_group *local; /* Local group in this sd */
+ unsigned long total_running;
unsigned long total_load; /* Total load of all groups in sd */
unsigned long total_capacity; /* Total capacity of all groups in sd */
unsigned long avg_load; /* Average load across all groups in sd */
@@ -7055,6 +7164,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
*sds = (struct sd_lb_stats){
.busiest = NULL,
.local = NULL,
+ .total_running = 0UL,
.total_load = 0UL,
.total_capacity = 0UL,
.busiest_stat = {
@@ -7363,7 +7473,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->nr_numa_running += rq->nr_numa_running;
sgs->nr_preferred_running += rq->nr_preferred_running;
#endif
- sgs->sum_weighted_load += weighted_cpuload(i);
+ sgs->sum_weighted_load += weighted_cpuload(rq);
/*
* No need to call idle_cpu() if nr_running is not 0
*/
@@ -7490,6 +7600,7 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq)
*/
static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
{
+ struct sched_domain_shared *shared = env->sd->shared;
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats *local = &sds->local_stat;
@@ -7546,6 +7657,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
next_group:
/* Now, start updating sd_lb_stats */
+ sds->total_running += sgs->sum_nr_running;
sds->total_load += sgs->group_load;
sds->total_capacity += sgs->group_capacity;
@@ -7561,6 +7673,21 @@ next_group:
env->dst_rq->rd->overload = overload;
}
+ if (!shared)
+ return;
+
+ /*
+ * Since these are sums over groups they can contain some CPUs
+ * multiple times for the NUMA domains.
+ *
+ * Currently only wake_affine_llc() and find_busiest_group()
+ * uses these numbers, only the last is affected by this problem.
+ *
+ * XXX fix that.
+ */
+ WRITE_ONCE(shared->nr_running, sds->total_running);
+ WRITE_ONCE(shared->load, sds->total_load);
+ WRITE_ONCE(shared->capacity, sds->total_capacity);
}
/**
@@ -7790,6 +7917,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
if (!sds.busiest || busiest->sum_nr_running == 0)
goto out_balanced;
+ /* XXX broken for overlapping NUMA groups */
sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
/ sds.total_capacity;
@@ -7892,7 +8020,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
capacity = capacity_of(i);
- wl = weighted_cpuload(i);
+ wl = weighted_cpuload(rq);
/*
* When comparing with imbalance, use weighted_cpuload()
@@ -9171,7 +9299,7 @@ static void set_curr_task_fair(struct rq *rq)
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
- cfs_rq->tasks_timeline = RB_ROOT;
+ cfs_rq->tasks_timeline = RB_ROOT_CACHED;
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
#ifndef CONFIG_64BIT
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6c23e30c0e5c..257f4f0b4532 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -158,7 +158,7 @@ static void cpuidle_idle_call(void)
}
/*
- * Suspend-to-idle ("freeze") is a system state in which all user space
+ * Suspend-to-idle ("s2idle") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
* activity happens here and in iterrupts (if any). In that case bypass
* the cpuidle governor and go stratight for the deepest idle state
@@ -167,9 +167,9 @@ static void cpuidle_idle_call(void)
* until a proper wakeup interrupt happens.
*/
- if (idle_should_freeze() || dev->use_deepest_state) {
- if (idle_should_freeze()) {
- entered_state = cpuidle_enter_freeze(drv, dev);
+ if (idle_should_enter_s2idle() || dev->use_deepest_state) {
+ if (idle_should_enter_s2idle()) {
+ entered_state = cpuidle_enter_s2idle(drv, dev);
if (entered_state > 0) {
local_irq_enable();
goto exit_idle;
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
new file mode 100644
index 000000000000..a92fddc22747
--- /dev/null
+++ b/kernel/sched/membarrier.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * membarrier system call
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/syscalls.h>
+#include <linux/membarrier.h>
+#include <linux/tick.h>
+#include <linux/cpumask.h>
+
+#include "sched.h" /* for cpu_rq(). */
+
+/*
+ * Bitmask made from a "or" of all commands within enum membarrier_cmd,
+ * except MEMBARRIER_CMD_QUERY.
+ */
+#define MEMBARRIER_CMD_BITMASK \
+ (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+
+static void ipi_mb(void *info)
+{
+ smp_mb(); /* IPIs should be serializing but paranoid. */
+}
+
+static void membarrier_private_expedited(void)
+{
+ int cpu;
+ bool fallback = false;
+ cpumask_var_t tmpmask;
+
+ if (num_online_cpus() == 1)
+ return;
+
+ /*
+ * Matches memory barriers around rq->curr modification in
+ * scheduler.
+ */
+ smp_mb(); /* system call entry is not a mb. */
+
+ /*
+ * Expedited membarrier commands guarantee that they won't
+ * block, hence the GFP_NOWAIT allocation flag and fallback
+ * implementation.
+ */
+ if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) {
+ /* Fallback for OOM. */
+ fallback = true;
+ }
+
+ cpus_read_lock();
+ for_each_online_cpu(cpu) {
+ struct task_struct *p;
+
+ /*
+ * Skipping the current CPU is OK even through we can be
+ * migrated at any point. The current CPU, at the point
+ * where we read raw_smp_processor_id(), is ensured to
+ * be in program order with respect to the caller
+ * thread. Therefore, we can skip this CPU from the
+ * iteration.
+ */
+ if (cpu == raw_smp_processor_id())
+ continue;
+ rcu_read_lock();
+ p = task_rcu_dereference(&cpu_rq(cpu)->curr);
+ if (p && p->mm == current->mm) {
+ if (!fallback)
+ __cpumask_set_cpu(cpu, tmpmask);
+ else
+ smp_call_function_single(cpu, ipi_mb, NULL, 1);
+ }
+ rcu_read_unlock();
+ }
+ if (!fallback) {
+ smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+ free_cpumask_var(tmpmask);
+ }
+ cpus_read_unlock();
+
+ /*
+ * Memory barrier on the caller thread _after_ we finished
+ * waiting for the last IPI. Matches memory barriers around
+ * rq->curr modification in scheduler.
+ */
+ smp_mb(); /* exit from system call is not a mb */
+}
+
+/**
+ * sys_membarrier - issue memory barriers on a set of threads
+ * @cmd: Takes command values defined in enum membarrier_cmd.
+ * @flags: Currently needs to be 0. For future extensions.
+ *
+ * If this system call is not implemented, -ENOSYS is returned. If the
+ * command specified does not exist, not available on the running
+ * kernel, or if the command argument is invalid, this system call
+ * returns -EINVAL. For a given command, with flags argument set to 0,
+ * this system call is guaranteed to always return the same value until
+ * reboot.
+ *
+ * All memory accesses performed in program order from each targeted thread
+ * is guaranteed to be ordered with respect to sys_membarrier(). If we use
+ * the semantic "barrier()" to represent a compiler barrier forcing memory
+ * accesses to be performed in program order across the barrier, and
+ * smp_mb() to represent explicit memory barriers forcing full memory
+ * ordering across the barrier, we have the following ordering table for
+ * each pair of barrier(), sys_membarrier() and smp_mb():
+ *
+ * The pair ordering is detailed as (O: ordered, X: not ordered):
+ *
+ * barrier() smp_mb() sys_membarrier()
+ * barrier() X X O
+ * smp_mb() X O O
+ * sys_membarrier() O O O
+ */
+SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+{
+ if (unlikely(flags))
+ return -EINVAL;
+ switch (cmd) {
+ case MEMBARRIER_CMD_QUERY:
+ {
+ int cmd_mask = MEMBARRIER_CMD_BITMASK;
+
+ if (tick_nohz_full_enabled())
+ cmd_mask &= ~MEMBARRIER_CMD_SHARED;
+ return cmd_mask;
+ }
+ case MEMBARRIER_CMD_SHARED:
+ /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+ if (tick_nohz_full_enabled())
+ return -EINVAL;
+ if (num_online_cpus() > 1)
+ synchronize_sched();
+ return 0;
+ case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
+ membarrier_private_expedited();
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 45caf937ef90..0af5ca9e3e3f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -970,7 +970,7 @@ static void update_curr_rt(struct rq *rq)
return;
/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+ cpufreq_update_util(rq, SCHED_CPUFREQ_RT);
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index eeef1a3086d1..746ac78ff492 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -426,8 +426,7 @@ struct cfs_rq {
u64 min_vruntime_copy;
#endif
- struct rb_root tasks_timeline;
- struct rb_node *rb_leftmost;
+ struct rb_root_cached tasks_timeline;
/*
* 'curr' points to currently running entity on this cfs_rq.
@@ -550,8 +549,7 @@ struct rt_rq {
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
- struct rb_root rb_root;
- struct rb_node *rb_leftmost;
+ struct rb_root_cached root;
unsigned long dl_nr_running;
@@ -575,8 +573,7 @@ struct dl_rq {
* an rb-tree, ordered by tasks' deadlines, with caching
* of the leftmost (earliest deadline) element.
*/
- struct rb_root pushable_dl_tasks_root;
- struct rb_node *pushable_dl_tasks_leftmost;
+ struct rb_root_cached pushable_dl_tasks_root;
#else
struct dl_bw dl_bw;
#endif
@@ -769,7 +766,7 @@ struct rq {
#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
int hrtick_csd_pending;
- struct call_single_data hrtick_csd;
+ call_single_data_t hrtick_csd;
#endif
struct hrtimer hrtick_timer;
#endif
@@ -1120,11 +1117,15 @@ extern int group_balance_cpu(struct sched_group *sg);
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
void register_sched_domain_sysctl(void);
+void dirty_sched_domain_sysctl(int cpu);
void unregister_sched_domain_sysctl(void);
#else
static inline void register_sched_domain_sysctl(void)
{
}
+static inline void dirty_sched_domain_sysctl(int cpu)
+{
+}
static inline void unregister_sched_domain_sysctl(void)
{
}
@@ -2070,19 +2071,13 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
{
struct update_util_data *data;
- data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+ data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data,
+ cpu_of(rq)));
if (data)
data->func(data, rq_clock(rq), flags);
}
-
-static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
-{
- if (cpu_of(rq) == smp_processor_id())
- cpufreq_update_util(rq, flags);
-}
#else
static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
-static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
#endif /* CONFIG_CPU_FREQ */
#ifdef arch_scale_freq_capacity
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 3d5610dcce11..2227e183e202 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -33,9 +33,6 @@ void swake_up(struct swait_queue_head *q)
{
unsigned long flags;
- if (!swait_active(q))
- return;
-
raw_spin_lock_irqsave(&q->lock, flags);
swake_up_locked(q);
raw_spin_unlock_irqrestore(&q->lock, flags);
@@ -51,9 +48,6 @@ void swake_up_all(struct swait_queue_head *q)
struct swait_queue *curr;
LIST_HEAD(tmp);
- if (!swait_active(q))
- return;
-
raw_spin_lock_irq(&q->lock);
list_splice_init(&q->task_list, &tmp);
while (!list_empty(&tmp)) {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 79895aec281e..5d0062cc10cb 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -261,8 +261,6 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
static int init_rootdomain(struct root_domain *rd)
{
- memset(rd, 0, sizeof(*rd));
-
if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
goto out;
if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
@@ -311,7 +309,7 @@ static struct root_domain *alloc_rootdomain(void)
{
struct root_domain *rd;
- rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+ rd = kzalloc(sizeof(*rd), GFP_KERNEL);
if (!rd)
return NULL;
@@ -337,7 +335,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc)
if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
kfree(sg->sgc);
- kfree(sg);
+ if (atomic_dec_and_test(&sg->ref))
+ kfree(sg);
sg = tmp;
} while (sg != first);
}
@@ -345,15 +344,12 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc)
static void destroy_sched_domain(struct sched_domain *sd)
{
/*
- * If its an overlapping domain it has private groups, iterate and
- * nuke them all.
+ * A normal sched domain may have multiple group references, an
+ * overlapping domain, having private groups, only one. Iterate,
+ * dropping group/capacity references, freeing where none remain.
*/
- if (sd->flags & SD_OVERLAP) {
- free_sched_groups(sd->groups, 1);
- } else if (atomic_dec_and_test(&sd->groups->ref)) {
- kfree(sd->groups->sgc);
- kfree(sd->groups);
- }
+ free_sched_groups(sd->groups, 1);
+
if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
kfree(sd->shared);
kfree(sd);
@@ -463,6 +459,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
rq_attach_root(rq, rd);
tmp = rq->sd;
rcu_assign_pointer(rq->sd, sd);
+ dirty_sched_domain_sysctl(cpu);
destroy_sched_domains(tmp);
update_top_cache_domain(cpu);
@@ -476,7 +473,7 @@ static int __init isolated_cpu_setup(char *str)
alloc_bootmem_cpumask_var(&cpu_isolated_map);
ret = cpulist_parse(str, cpu_isolated_map);
if (ret) {
- pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
+ pr_err("sched: Error, all isolcpus= values must be between 0 and %u\n", nr_cpu_ids);
return 0;
}
return 1;
@@ -670,6 +667,7 @@ build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
else
cpumask_copy(sg_span, sched_domain_span(sd));
+ atomic_inc(&sg->ref);
return sg;
}
@@ -1595,7 +1593,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
}
}
-struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
+static struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
struct sched_domain *child, int cpu)
{
@@ -1854,7 +1852,17 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
/* Let the architecture update CPU core mappings: */
new_topology = arch_update_cpu_topology();
- n = doms_new ? ndoms_new : 0;
+ if (!doms_new) {
+ WARN_ON_ONCE(dattr_new);
+ n = 0;
+ doms_new = alloc_sched_domains(1);
+ if (doms_new) {
+ n = 1;
+ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
+ }
+ } else {
+ n = ndoms_new;
+ }
/* Destroy deleted domains: */
for (i = 0; i < ndoms_cur; i++) {
@@ -1870,11 +1878,10 @@ match1:
}
n = ndoms_cur;
- if (doms_new == NULL) {
+ if (!doms_new) {
n = 0;
doms_new = &fallback_doms;
cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
- WARN_ON_ONCE(dattr_new);
}
/* Build new domains: */
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-06-11 00:59:41 +0200