#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/acct.h>
+#include <linux/kprobes.h>
#include <asm/tlb.h>
#include <asm/unistd.h>
(v1) * (v2_max) / (v1_max)
#define DELTA(p) \
- (SCALE(TASK_NICE(p), 40, MAX_BONUS) + INTERACTIVE_DELTA)
+ (SCALE(TASK_NICE(p) + 20, 40, MAX_BONUS) - 20 * MAX_BONUS / 40 + \
+ INTERACTIVE_DELTA)
#define TASK_INTERACTIVE(p) \
((p)->prio <= (p)->static_prio - DELTA(p))
return prio;
}
+/*
+ * We place interactive tasks back into the active array, if possible.
+ *
+ * To guarantee that this does not starve expired tasks we ignore the
+ * interactivity of a task if the first expired task had to wait more
+ * than a 'reasonable' amount of time. This deadline timeout is
+ * load-dependent, as the frequency of array switched decreases with
+ * increasing number of running tasks. We also ignore the interactivity
+ * if a better static_prio task has expired, and switch periodically
+ * regardless, to ensure that highly interactive tasks do not starve
+ * the less fortunate for unreasonably long periods.
+ */
+static inline int expired_starving(runqueue_t *rq)
+{
+ int limit;
+
+ /*
+ * Arrays were recently switched, all is well
+ */
+ if (!rq->expired_timestamp)
+ return 0;
+
+ limit = STARVATION_LIMIT * rq->nr_running;
+
+ /*
+ * It's time to switch arrays
+ */
+ if (jiffies - rq->expired_timestamp >= limit)
+ return 1;
+
+ /*
+ * There's a better selection in the expired array
+ */
+ if (rq->curr->static_prio > rq->best_expired_prio)
+ return 1;
+
+ /*
+ * All is well
+ */
+ return 0;
+}
+
/*
* __activate_task - move a task to the runqueue.
*/
-static inline void __activate_task(task_t *p, runqueue_t *rq)
+static void __activate_task(task_t *p, runqueue_t *rq)
{
- enqueue_task(p, rq->active);
+ prio_array_t *target = rq->active;
+
+ if (unlikely(batch_task(p) || expired_starving(rq)))
+ target = rq->expired;
+ enqueue_task(p, target);
rq->nr_running++;
}
unsigned long long __sleep_time = now - p->timestamp;
unsigned long sleep_time;
- if (unlikely(p->policy == SCHED_BATCH))
+ if (batch_task(p))
sleep_time = 0;
else {
if (__sleep_time > NS_MAX_SLEEP_AVG)
if (likely(sleep_time > 0)) {
/*
* User tasks that sleep a long time are categorised as
- * idle and will get just interactive status to stay active &
- * prevent them suddenly becoming cpu hogs and starving
- * other processes.
+ * idle. They will only have their sleep_avg increased to a
+ * level that makes them just interactive priority to stay
+ * active yet prevent them suddenly becoming cpu hogs and
+ * starving other processes.
*/
- if (p->mm && p->activated != -1 &&
- sleep_time > INTERACTIVE_SLEEP(p)) {
- p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG -
- DEF_TIMESLICE);
+ if (p->mm && sleep_time > INTERACTIVE_SLEEP(p)) {
+ unsigned long ceiling;
+
+ ceiling = JIFFIES_TO_NS(MAX_SLEEP_AVG -
+ DEF_TIMESLICE);
+ if (p->sleep_avg < ceiling)
+ p->sleep_avg = ceiling;
} else {
/*
* Tasks waking from uninterruptible sleep are
* limited in their sleep_avg rise as they
* are likely to be waiting on I/O
*/
- if (p->activated == -1 && p->mm) {
+ if (p->sleep_type == SLEEP_NONINTERACTIVE && p->mm) {
if (p->sleep_avg >= INTERACTIVE_SLEEP(p))
sleep_time = 0;
else if (p->sleep_avg + sleep_time >=
* This checks to make sure it's not an uninterruptible task
* that is now waking up.
*/
- if (!p->activated) {
+ if (p->sleep_type == SLEEP_NORMAL) {
/*
* Tasks which were woken up by interrupts (ie. hw events)
* are most likely of interactive nature. So we give them
* on a CPU, first time around:
*/
if (in_interrupt())
- p->activated = 2;
+ p->sleep_type = SLEEP_INTERRUPTED;
else {
/*
* Normal first-time wakeups get a credit too for
* on-runqueue time, but it will be weighted down:
*/
- p->activated = 1;
+ p->sleep_type = SLEEP_INTERACTIVE;
}
}
p->timestamp = now;
* Tasks on involuntary sleep don't earn
* sleep_avg beyond just interactive state.
*/
- p->activated = -1;
- }
+ p->sleep_type = SLEEP_NONINTERACTIVE;
+ } else
/*
* Tasks that have marked their sleep as noninteractive get
- * woken up without updating their sleep average. (i.e. their
- * sleep is handled in a priority-neutral manner, no priority
- * boost and no penalty.)
+ * woken up with their sleep average not weighted in an
+ * interactive way.
*/
- if (old_state & TASK_NONINTERACTIVE)
- __activate_task(p, rq);
- else
- activate_task(p, rq, cpu == this_cpu);
+ if (old_state & TASK_NONINTERACTIVE)
+ p->sleep_type = SLEEP_NONINTERACTIVE;
+
+
+ activate_task(p, rq, cpu == this_cpu);
/*
* Sync wakeups (i.e. those types of wakeups where the waker
* has indicated that it will leave the CPU in short order)
finish_lock_switch(rq, prev);
if (mm)
mmdrop(mm);
- if (unlikely(prev_task_flags & PF_DEAD))
+ if (unlikely(prev_task_flags & PF_DEAD)) {
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
put_task_struct(prev);
+ }
}
/**
{
unsigned long i, sum = 0;
- for_each_cpu(i)
+ for_each_possible_cpu(i)
sum += cpu_rq(i)->nr_uninterruptible;
/*
{
unsigned long long i, sum = 0;
- for_each_cpu(i)
+ for_each_possible_cpu(i)
sum += cpu_rq(i)->nr_switches;
return sum;
{
unsigned long i, sum = 0;
- for_each_cpu(i)
+ for_each_possible_cpu(i)
sum += atomic_read(&cpu_rq(i)->nr_iowait);
return sum;
}
+unsigned long nr_active(void)
+{
+ unsigned long i, running = 0, uninterruptible = 0;
+
+ for_each_online_cpu(i) {
+ running += cpu_rq(i)->nr_running;
+ uninterruptible += cpu_rq(i)->nr_uninterruptible;
+ }
+
+ if (unlikely((long)uninterruptible < 0))
+ uninterruptible = 0;
+
+ return running + uninterruptible;
+}
+
#ifdef CONFIG_SMP
/*
return ns;
}
-/*
- * We place interactive tasks back into the active array, if possible.
- *
- * To guarantee that this does not starve expired tasks we ignore the
- * interactivity of a task if the first expired task had to wait more
- * than a 'reasonable' amount of time. This deadline timeout is
- * load-dependent, as the frequency of array switched decreases with
- * increasing number of running tasks. We also ignore the interactivity
- * if a better static_prio task has expired:
- */
-#define EXPIRED_STARVING(rq) \
- ((STARVATION_LIMIT && ((rq)->expired_timestamp && \
- (jiffies - (rq)->expired_timestamp >= \
- STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
- ((rq)->curr->static_prio > (rq)->best_expired_prio))
-
/*
* Account user cpu time to a process.
* @p: the process that the cpu time gets accounted to
if (!rq->expired_timestamp)
rq->expired_timestamp = jiffies;
- if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
+ if (!TASK_INTERACTIVE(p) || expired_starving(rq)) {
enqueue_task(p, rq->expired);
if (p->static_prio < rq->best_expired_prio)
rq->best_expired_prio = p->static_prio;
#endif
+static inline int interactive_sleep(enum sleep_type sleep_type)
+{
+ return (sleep_type == SLEEP_INTERACTIVE ||
+ sleep_type == SLEEP_INTERRUPTED);
+}
+
/*
* schedule() is the main scheduler function.
*/
* schedule() atomically, we ignore that path for now.
* Otherwise, whine if we are scheduling when we should not be.
*/
- if (likely(!current->exit_state)) {
- if (unlikely(in_atomic())) {
- printk(KERN_ERR "scheduling while atomic: "
- "%s/0x%08x/%d\n",
- current->comm, preempt_count(), current->pid);
- dump_stack();
- }
+ if (unlikely(in_atomic() && !current->exit_state)) {
+ printk(KERN_ERR "BUG: scheduling while atomic: "
+ "%s/0x%08x/%d\n",
+ current->comm, preempt_count(), current->pid);
+ dump_stack();
}
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
queue = array->queue + idx;
next = list_entry(queue->next, task_t, run_list);
- if (!rt_task(next) && next->activated > 0) {
+ if (!rt_task(next) && interactive_sleep(next->sleep_type)) {
unsigned long long delta = now - next->timestamp;
if (unlikely((long long)(now - next->timestamp) < 0))
delta = 0;
- if (next->activated == 1)
+ if (next->sleep_type == SLEEP_INTERACTIVE)
delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;
array = next->array;
dequeue_task(next, array);
next->prio = new_prio;
enqueue_task(next, array);
- } else
- requeue_task(next, array);
+ }
}
- next->activated = 0;
+ next->sleep_type = SLEEP_NORMAL;
switch_tasks:
if (next == rq->idle)
schedstat_inc(rq, sched_goidle);
}
#endif
+#ifdef CONFIG_SCHED_MC
+static DEFINE_PER_CPU(struct sched_domain, core_domains);
+static struct sched_group sched_group_core[NR_CPUS];
+#endif
+
+#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
+static int cpu_to_core_group(int cpu)
+{
+ return first_cpu(cpu_sibling_map[cpu]);
+}
+#elif defined(CONFIG_SCHED_MC)
+static int cpu_to_core_group(int cpu)
+{
+ return cpu;
+}
+#endif
+
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static struct sched_group sched_group_phys[NR_CPUS];
static int cpu_to_phys_group(int cpu)
{
-#ifdef CONFIG_SCHED_SMT
+#if defined(CONFIG_SCHED_MC)
+ cpumask_t mask = cpu_coregroup_map(cpu);
+ return first_cpu(mask);
+#elif defined(CONFIG_SCHED_SMT)
return first_cpu(cpu_sibling_map[cpu]);
#else
return cpu;
{
return cpu_to_node(cpu);
}
+static void init_numa_sched_groups_power(struct sched_group *group_head)
+{
+ struct sched_group *sg = group_head;
+ int j;
+
+ if (!sg)
+ return;
+next_sg:
+ for_each_cpu_mask(j, sg->cpumask) {
+ struct sched_domain *sd;
+
+ sd = &per_cpu(phys_domains, j);
+ if (j != first_cpu(sd->groups->cpumask)) {
+ /*
+ * Only add "power" once for each
+ * physical package.
+ */
+ continue;
+ }
+
+ sg->cpu_power += sd->groups->cpu_power;
+ }
+ sg = sg->next;
+ if (sg != group_head)
+ goto next_sg;
+}
#endif
/*
sd->parent = p;
sd->groups = &sched_group_phys[group];
+#ifdef CONFIG_SCHED_MC
+ p = sd;
+ sd = &per_cpu(core_domains, i);
+ group = cpu_to_core_group(i);
+ *sd = SD_MC_INIT;
+ sd->span = cpu_coregroup_map(i);
+ cpus_and(sd->span, sd->span, *cpu_map);
+ sd->parent = p;
+ sd->groups = &sched_group_core[group];
+#endif
+
#ifdef CONFIG_SCHED_SMT
p = sd;
sd = &per_cpu(cpu_domains, i);
}
#endif
+#ifdef CONFIG_SCHED_MC
+ /* Set up multi-core groups */
+ for_each_cpu_mask(i, *cpu_map) {
+ cpumask_t this_core_map = cpu_coregroup_map(i);
+ cpus_and(this_core_map, this_core_map, *cpu_map);
+ if (i != first_cpu(this_core_map))
+ continue;
+ init_sched_build_groups(sched_group_core, this_core_map,
+ &cpu_to_core_group);
+ }
+#endif
+
+
/* Set up physical groups */
for (i = 0; i < MAX_NUMNODES; i++) {
cpumask_t nodemask = node_to_cpumask(i);
power = SCHED_LOAD_SCALE;
sd->groups->cpu_power = power;
#endif
+#ifdef CONFIG_SCHED_MC
+ sd = &per_cpu(core_domains, i);
+ power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1)
+ * SCHED_LOAD_SCALE / 10;
+ sd->groups->cpu_power = power;
+
+ sd = &per_cpu(phys_domains, i);
+ /*
+ * This has to be < 2 * SCHED_LOAD_SCALE
+ * Lets keep it SCHED_LOAD_SCALE, so that
+ * while calculating NUMA group's cpu_power
+ * we can simply do
+ * numa_group->cpu_power += phys_group->cpu_power;
+ *
+ * See "only add power once for each physical pkg"
+ * comment below
+ */
+ sd->groups->cpu_power = SCHED_LOAD_SCALE;
+#else
sd = &per_cpu(phys_domains, i);
power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
(cpus_weight(sd->groups->cpumask)-1) / 10;
sd->groups->cpu_power = power;
-
-#ifdef CONFIG_NUMA
- sd = &per_cpu(allnodes_domains, i);
- if (sd->groups) {
- power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
- (cpus_weight(sd->groups->cpumask)-1) / 10;
- sd->groups->cpu_power = power;
- }
#endif
}
#ifdef CONFIG_NUMA
- for (i = 0; i < MAX_NUMNODES; i++) {
- struct sched_group *sg = sched_group_nodes[i];
- int j;
-
- if (sg == NULL)
- continue;
-next_sg:
- for_each_cpu_mask(j, sg->cpumask) {
- struct sched_domain *sd;
- int power;
+ for (i = 0; i < MAX_NUMNODES; i++)
+ init_numa_sched_groups_power(sched_group_nodes[i]);
- sd = &per_cpu(phys_domains, j);
- if (j != first_cpu(sd->groups->cpumask)) {
- /*
- * Only add "power" once for each
- * physical package.
- */
- continue;
- }
- power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
- (cpus_weight(sd->groups->cpumask)-1) / 10;
-
- sg->cpu_power += power;
- }
- sg = sg->next;
- if (sg != sched_group_nodes[i])
- goto next_sg;
- }
+ init_numa_sched_groups_power(sched_group_allnodes);
#endif
/* Attach the domains */
struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i);
+#elif defined(CONFIG_SCHED_MC)
+ sd = &per_cpu(core_domains, i);
#else
sd = &per_cpu(phys_domains, i);
#endif
runqueue_t *rq;
int i, j, k;
- for_each_cpu(i) {
+ for_each_possible_cpu(i) {
prio_array_t *array;
rq = cpu_rq(i);
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
prev_jiffy = jiffies;
- printk(KERN_ERR "Debug: sleeping function called from invalid"
+ printk(KERN_ERR "BUG: sleeping function called from invalid"
" context at %s:%d\n", file, line);
printk("in_atomic():%d, irqs_disabled():%d\n",
in_atomic(), irqs_disabled());