* Thomas Gleixner, Mike Kravetz
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
p->sched_class->prio_changed(rq, p, oldprio, running);
}
-/**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @p: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- *
- * Function lives here instead of kthread.c because it messes with
- * scheduler internals which require locking.
- */
-void kthread_bind(struct task_struct *p, unsigned int cpu)
-{
- struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
-
- /* Must have done schedule() in kthread() before we set_task_cpu */
- if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
- WARN_ON(1);
- return;
- }
-
- raw_spin_lock_irqsave(&rq->lock, flags);
- update_rq_clock(rq);
- set_task_cpu(p, cpu);
- p->cpus_allowed = cpumask_of_cpu(cpu);
- p->rt.nr_cpus_allowed = 1;
- p->flags |= PF_THREAD_BOUND;
- raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-EXPORT_SYMBOL(kthread_bind);
-
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
return delta < (s64)sysctl_sched_migration_cost;
}
-
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
- int old_cpu = task_cpu(p);
- struct cfs_rq *old_cfsrq = task_cfs_rq(p),
- *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
+#ifdef CONFIG_SCHED_DEBUG
+ /*
+ * We should never call set_task_cpu() on a blocked task,
+ * ttwu() will sort out the placement.
+ */
+ WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
+ !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+#endif
trace_sched_migrate_task(p, new_cpu);
- if (old_cpu != new_cpu) {
+ if (task_cpu(p) != new_cpu) {
p->se.nr_migrations++;
- perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
- 1, 1, NULL, 0);
+ perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0);
}
- p->se.vruntime -= old_cfsrq->min_vruntime -
- new_cfsrq->min_vruntime;
__set_task_cpu(p, new_cpu);
}
/*
* If the task is not on a runqueue (and not running), then
- * it is sufficient to simply update the task's cpu field.
+ * the next wake-up will properly place the task.
*/
- if (!p->se.on_rq && !task_running(rq, p)) {
- update_rq_clock(rq);
- set_task_cpu(p, dest_cpu);
+ if (!p->se.on_rq && !task_running(rq, p))
return 0;
- }
init_completion(&req->done);
req->task = p;
}
#ifdef CONFIG_SMP
+static int select_fallback_rq(int cpu, struct task_struct *p)
+{
+ int dest_cpu;
+ const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+
+ /* Look for allowed, online CPU in same node. */
+ for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
+ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+ return dest_cpu;
+
+ /* Any allowed, online CPU? */
+ dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
+ if (dest_cpu < nr_cpu_ids)
+ return dest_cpu;
+
+ /* No more Mr. Nice Guy. */
+ if (dest_cpu >= nr_cpu_ids) {
+ rcu_read_lock();
+ cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
+ rcu_read_unlock();
+ dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
+
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (p->mm && printk_ratelimit()) {
+ printk(KERN_INFO "process %d (%s) no "
+ "longer affine to cpu%d\n",
+ task_pid_nr(p), p->comm, cpu);
+ }
+ }
+
+ return dest_cpu;
+}
+
+/*
+ * Gets called from 3 sites (exec, fork, wakeup), since it is called without
+ * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
+ * by:
+ *
+ * exec: is unstable, retry loop
+ * fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
+ */
static inline
int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
{
- return p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+ int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+
+ /*
+ * In order not to call set_task_cpu() on a blocking task we need
+ * to rely on ttwu() to place the task on a valid ->cpus_allowed
+ * cpu.
+ *
+ * Since this is common to all placement strategies, this lives here.
+ *
+ * [ this allows ->select_task() to simply return task_cpu(p) and
+ * not worry about this generic constraint ]
+ */
+ if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
+ !cpu_online(cpu)))
+ cpu = select_fallback_rq(task_cpu(p), p);
+
+ return cpu;
}
#endif
if (task_contributes_to_load(p))
rq->nr_uninterruptible--;
p->state = TASK_WAKING;
+
+ if (p->sched_class->task_waking)
+ p->sched_class->task_waking(rq, p);
+
__task_rq_unlock(rq);
cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
- if (p->sched_class->task_wake_up)
- p->sched_class->task_wake_up(rq, p);
+ if (p->sched_class->task_woken)
+ p->sched_class->task_woken(rq, p);
if (unlikely(rq->idle_stamp)) {
u64 delta = rq->clock - rq->idle_stamp;
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
-#ifdef CONFIG_SMP
- cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
-#endif
set_task_cpu(p, cpu);
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
{
unsigned long flags;
struct rq *rq;
+ int cpu = get_cpu();
+
+#ifdef CONFIG_SMP
+ /*
+ * Fork balancing, do it here and not earlier because:
+ * - cpus_allowed can change in the fork path
+ * - any previously selected cpu might disappear through hotplug
+ *
+ * We still have TASK_WAKING but PF_STARTING is gone now, meaning
+ * ->cpus_allowed is stable, we have preemption disabled, meaning
+ * cpu_online_mask is stable.
+ */
+ cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+ set_task_cpu(p, cpu);
+#endif
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_WAKING);
trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
- if (p->sched_class->task_wake_up)
- p->sched_class->task_wake_up(rq, p);
+ if (p->sched_class->task_woken)
+ p->sched_class->task_woken(rq, p);
#endif
task_rq_unlock(rq, &flags);
+ put_cpu();
}
#ifdef CONFIG_PREEMPT_NOTIFIERS
}
/*
- * If dest_cpu is allowed for this process, migrate the task to it.
- * This is accomplished by forcing the cpu_allowed mask to only
- * allow dest_cpu, which will force the cpu onto dest_cpu. Then
- * the cpu_allowed mask is restored.
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
*/
-static void sched_migrate_task(struct task_struct *p, int dest_cpu)
+void sched_exec(void)
{
+ struct task_struct *p = current;
struct migration_req req;
+ int dest_cpu, this_cpu;
unsigned long flags;
struct rq *rq;
+again:
+ this_cpu = get_cpu();
+ dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
+ if (dest_cpu == this_cpu) {
+ put_cpu();
+ return;
+ }
+
rq = task_rq_lock(p, &flags);
+ put_cpu();
+
+ /*
+ * select_task_rq() can race against ->cpus_allowed
+ */
if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
- || unlikely(!cpu_active(dest_cpu)))
- goto out;
+ || unlikely(!cpu_active(dest_cpu))) {
+ task_rq_unlock(rq, &flags);
+ goto again;
+ }
/* force the process onto the specified CPU */
if (migrate_task(p, dest_cpu, &req)) {
return;
}
-out:
task_rq_unlock(rq, &flags);
}
/*
- * sched_exec - execve() is a valuable balancing opportunity, because at
- * this point the task has the smallest effective memory and cache footprint.
- */
-void sched_exec(void)
-{
- int new_cpu, this_cpu = get_cpu();
- new_cpu = select_task_rq(current, SD_BALANCE_EXEC, 0);
- put_cpu();
- if (new_cpu != this_cpu)
- sched_migrate_task(current, new_cpu);
-}
-
-/*
* pull_task - move a task from a remote runqueue to the local runqueue.
* Both runqueues must be locked.
*/
{
struct pt_regs *regs = get_irq_regs();
- pr_err("BUG: scheduling while atomic: %s/%d/0x%08x\n",
- prev->comm, prev->pid, preempt_count());
+ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
+ prev->comm, prev->pid, preempt_count());
debug_show_held_locks(prev);
print_modules();
post_schedule(rq);
- if (unlikely(reacquire_kernel_lock(current) < 0))
+ if (unlikely(reacquire_kernel_lock(current) < 0)) {
+ prev = rq->curr;
+ switch_count = &prev->nivcsw;
goto need_resched_nonpreemptible;
+ }
preempt_enable_no_resched();
if (need_resched())
unsigned state;
state = p->state ? __ffs(p->state) + 1 : 0;
- pr_info("%-13.13s %c", p->comm,
+ printk(KERN_INFO "%-13.13s %c", p->comm,
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
if (state == TASK_RUNNING)
- pr_cont(" running ");
+ printk(KERN_CONT " running ");
else
- pr_cont(" %08lx ", thread_saved_pc(p));
+ printk(KERN_CONT " %08lx ", thread_saved_pc(p));
#else
if (state == TASK_RUNNING)
- pr_cont(" running task ");
+ printk(KERN_CONT " running task ");
else
- pr_cont(" %016lx ", thread_saved_pc(p));
+ printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
free = stack_not_used(p);
#endif
- pr_cont("%5lu %5d %6d 0x%08lx\n", free,
+ printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
task_pid_nr(p), task_pid_nr(p->real_parent),
(unsigned long)task_thread_info(p)->flags);
struct task_struct *g, *p;
#if BITS_PER_LONG == 32
- pr_info(" task PC stack pid father\n");
+ printk(KERN_INFO
+ " task PC stack pid father\n");
#else
- pr_info(" task PC stack pid father\n");
+ printk(KERN_INFO
+ " task PC stack pid father\n");
#endif
read_lock(&tasklist_lock);
do_each_thread(g, p) {
struct rq *rq;
int ret = 0;
+ /*
+ * Since we rely on wake-ups to migrate sleeping tasks, don't change
+ * the ->cpus_allowed mask from under waking tasks, which would be
+ * possible when we change rq->lock in ttwu(), so synchronize against
+ * TASK_WAKING to avoid that.
+ *
+ * Make an exception for freshly cloned tasks, since cpuset namespaces
+ * might move the task about, we have to validate the target in
+ * wake_up_new_task() anyway since the cpu might have gone away.
+ */
+again:
+ while (p->state == TASK_WAKING && !(p->flags & PF_STARTING))
+ cpu_relax();
+
rq = task_rq_lock(p, &flags);
+
+ if (p->state == TASK_WAKING && !(p->flags & PF_STARTING)) {
+ task_rq_unlock(rq, &flags);
+ goto again;
+ }
+
if (!cpumask_intersects(new_mask, cpu_active_mask)) {
ret = -EINVAL;
goto out;
static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
{
struct rq *rq_dest, *rq_src;
- int ret = 0, on_rq;
+ int ret = 0;
if (unlikely(!cpu_active(dest_cpu)))
return ret;
if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
goto fail;
- on_rq = p->se.on_rq;
- if (on_rq)
+ /*
+ * If we're not on a rq, the next wake-up will ensure we're
+ * placed properly.
+ */
+ if (p->se.on_rq) {
deactivate_task(rq_src, p, 0);
-
- set_task_cpu(p, dest_cpu);
- if (on_rq) {
+ set_task_cpu(p, dest_cpu);
activate_task(rq_dest, p, 0);
check_preempt_curr(rq_dest, p, 0);
}
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
int dest_cpu;
- const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));
again:
- /* Look for allowed, online CPU in same node. */
- for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
- if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
- goto move;
-
- /* Any allowed, online CPU? */
- dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
- if (dest_cpu < nr_cpu_ids)
- goto move;
-
- /* No more Mr. Nice Guy. */
- if (dest_cpu >= nr_cpu_ids) {
- cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
- dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
-
- /*
- * Don't tell them about moving exiting tasks or
- * kernel threads (both mm NULL), since they never
- * leave kernel.
- */
- if (p->mm && printk_ratelimit()) {
- pr_info("process %d (%s) no longer affine to cpu%d\n",
- task_pid_nr(p), p->comm, dead_cpu);
- }
- }
+ dest_cpu = select_fallback_rq(dead_cpu, p);
-move:
/* It can have affinity changed while we were choosing. */
if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
goto again;
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
if (!(sd->flags & SD_LOAD_BALANCE)) {
- pr_cont("does not load-balance\n");
+ printk("does not load-balance\n");
if (sd->parent)
- pr_err("ERROR: !SD_LOAD_BALANCE domain has parent\n");
+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+ " has parent");
return -1;
}
- pr_cont("span %s level %s\n", str, sd->name);
+ printk(KERN_CONT "span %s level %s\n", str, sd->name);
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
- pr_err("ERROR: domain->span does not contain CPU%d\n", cpu);
+ printk(KERN_ERR "ERROR: domain->span does not contain "
+ "CPU%d\n", cpu);
}
if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
- pr_err("ERROR: domain->groups does not contain CPU%d\n", cpu);
+ printk(KERN_ERR "ERROR: domain->groups does not contain"
+ " CPU%d\n", cpu);
}
printk(KERN_DEBUG "%*s groups:", level + 1, "");
do {
if (!group) {
- pr_cont("\n");
- pr_err("ERROR: group is NULL\n");
+ printk("\n");
+ printk(KERN_ERR "ERROR: group is NULL\n");
break;
}
if (!group->cpu_power) {
- pr_cont("\n");
- pr_err("ERROR: domain->cpu_power not set\n");
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: domain->cpu_power not "
+ "set\n");
break;
}
if (!cpumask_weight(sched_group_cpus(group))) {
- pr_cont("\n");
- pr_err("ERROR: empty group\n");
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: empty group\n");
break;
}
if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
- pr_cont("\n");
- pr_err("ERROR: repeated CPUs\n");
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: repeated CPUs\n");
break;
}
cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
- pr_cont(" %s", str);
+ printk(KERN_CONT " %s", str);
if (group->cpu_power != SCHED_LOAD_SCALE) {
- pr_cont(" (cpu_power = %d)", group->cpu_power);
+ printk(KERN_CONT " (cpu_power = %d)",
+ group->cpu_power);
}
group = group->next;
} while (group != sd->groups);
- pr_cont("\n");
+ printk(KERN_CONT "\n");
if (!cpumask_equal(sched_domain_span(sd), groupmask))
- pr_err("ERROR: groups don't span domain->span\n");
+ printk(KERN_ERR "ERROR: groups don't span domain->span\n");
if (sd->parent &&
!cpumask_subset(groupmask, sched_domain_span(sd->parent)))
- pr_err("ERROR: parent span is not a superset of domain->span\n");
+ printk(KERN_ERR "ERROR: parent span is not a superset "
+ "of domain->span\n");
return 0;
}
sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, num);
if (!sg) {
- pr_warning("Can not alloc domain group for node %d\n", num);
+ printk(KERN_WARNING "Can not alloc domain group for node %d\n",
+ num);
return -ENOMEM;
}
d->sched_group_nodes[num] = sg;
sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, num);
if (!sg) {
- pr_warning("Can not alloc domain group for node %d\n",
- j);
+ printk(KERN_WARNING
+ "Can not alloc domain group for node %d\n", j);
return -ENOMEM;
}
sg->cpu_power = 0;
d->sched_group_nodes = kcalloc(nr_node_ids,
sizeof(struct sched_group *), GFP_KERNEL);
if (!d->sched_group_nodes) {
- pr_warning("Can not alloc sched group node list\n");
+ printk(KERN_WARNING "Can not alloc sched group node list\n");
return sa_notcovered;
}
sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
return sa_send_covered;
d->rd = alloc_rootdomain();
if (!d->rd) {
- pr_warning("Cannot alloc root domain\n");
+ printk(KERN_WARNING "Cannot alloc root domain\n");
return sa_tmpmask;
}
return sa_rootdomain;
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
static inline int preempt_count_equals(int preempt_offset)
{
- int nested = preempt_count() & ~PREEMPT_ACTIVE;
+ int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
}
return;
prev_jiffy = jiffies;
- pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
- file, line);
- pr_err("in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
- in_atomic(), irqs_disabled(),
- current->pid, current->comm);
+ printk(KERN_ERR
+ "BUG: sleeping function called from invalid context at %s:%d\n",
+ file, line);
+ printk(KERN_ERR
+ "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+ in_atomic(), irqs_disabled(),
+ current->pid, current->comm);
debug_show_held_locks(current);
if (irqs_disabled())
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->moved_group)
- tsk->sched_class->moved_group(tsk);
+ tsk->sched_class->moved_group(tsk, on_rq);
#endif
if (unlikely(running))