#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
+#include <linux/plist.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
#include <asm/processor.h>
+#define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */
+
+/*
+ * Extended scheduling parameters data structure.
+ *
+ * This is needed because the original struct sched_param can not be
+ * altered without introducing ABI issues with legacy applications
+ * (e.g., in sched_getparam()).
+ *
+ * However, the possibility of specifying more than just a priority for
+ * the tasks may be useful for a wide variety of application fields, e.g.,
+ * multimedia, streaming, automation and control, and many others.
+ *
+ * This variant (sched_attr) is meant at describing a so-called
+ * sporadic time-constrained task. In such model a task is specified by:
+ * - the activation period or minimum instance inter-arrival time;
+ * - the maximum (or average, depending on the actual scheduling
+ * discipline) computation time of all instances, a.k.a. runtime;
+ * - the deadline (relative to the actual activation time) of each
+ * instance.
+ * Very briefly, a periodic (sporadic) task asks for the execution of
+ * some specific computation --which is typically called an instance--
+ * (at most) every period. Moreover, each instance typically lasts no more
+ * than the runtime and must be completed by time instant t equal to
+ * the instance activation time + the deadline.
+ *
+ * This is reflected by the actual fields of the sched_attr structure:
+ *
+ * @size size of the structure, for fwd/bwd compat.
+ *
+ * @sched_policy task's scheduling policy
+ * @sched_flags for customizing the scheduler behaviour
+ * @sched_nice task's nice value (SCHED_NORMAL/BATCH)
+ * @sched_priority task's static priority (SCHED_FIFO/RR)
+ * @sched_deadline representative of the task's deadline
+ * @sched_runtime representative of the task's runtime
+ * @sched_period representative of the task's period
+ *
+ * Given this task model, there are a multiplicity of scheduling algorithms
+ * and policies, that can be used to ensure all the tasks will make their
+ * timing constraints.
+ *
+ * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
+ * only user of this new interface. More information about the algorithm
+ * available in the scheduling class file or in Documentation/.
+ */
+struct sched_attr {
+ u32 size;
+
+ u32 sched_policy;
+ u64 sched_flags;
+
+ /* SCHED_NORMAL, SCHED_BATCH */
+ s32 sched_nice;
+
+ /* SCHED_FIFO, SCHED_RR */
+ u32 sched_priority;
+
+ /* SCHED_DEADLINE */
+ u64 sched_runtime;
+ u64 sched_deadline;
+ u64 sched_period;
+};
+
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0)
-#define task_is_dead(task) ((task)->exit_state != 0)
#define task_is_stopped_or_traced(task) \
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
#endif
};
+struct sched_dl_entity {
+ struct rb_node rb_node;
+
+ /*
+ * Original scheduling parameters. Copied here from sched_attr
+ * during sched_setscheduler2(), they will remain the same until
+ * the next sched_setscheduler2().
+ */
+ u64 dl_runtime; /* maximum runtime for each instance */
+ u64 dl_deadline; /* relative deadline of each instance */
+ u64 dl_period; /* separation of two instances (period) */
+ u64 dl_bw; /* dl_runtime / dl_deadline */
+
+ /*
+ * Actual scheduling parameters. Initialized with the values above,
+ * they are continously updated during task execution. Note that
+ * the remaining runtime could be < 0 in case we are in overrun.
+ */
+ s64 runtime; /* remaining runtime for this instance */
+ u64 deadline; /* absolute deadline for this instance */
+ unsigned int flags; /* specifying the scheduler behaviour */
+
+ /*
+ * Some bool flags:
+ *
+ * @dl_throttled tells if we exhausted the runtime. If so, the
+ * task has to wait for a replenishment to be performed at the
+ * next firing of dl_timer.
+ *
+ * @dl_new tells if a new instance arrived. If so we must
+ * start executing it with full runtime and reset its absolute
+ * deadline;
+ *
+ * @dl_boosted tells if we are boosted due to DI. If so we are
+ * outside bandwidth enforcement mechanism (but only until we
+ * exit the critical section).
+ */
+ int dl_throttled, dl_new, dl_boosted;
+
+ /*
+ * Bandwidth enforcement timer. Each -deadline task has its
+ * own bandwidth to be enforced, thus we need one timer per task.
+ */
+ struct hrtimer dl_timer;
+};
struct rcu_node;
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
+ struct sched_dl_entity dl;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* list of struct preempt_notifier: */
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
+ struct rb_node pushable_dl_tasks;
#endif
struct mm_struct *mm, *active_mm;
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
- struct plist_head pi_waiters;
+ struct rb_root pi_waiters;
+ struct rb_node *pi_waiters_leftmost;
/* Deadlock detection and priority inheritance handling */
struct rt_mutex_waiter *pi_blocked_on;
+ /* Top pi_waiters task */
+ struct task_struct *pi_top_task;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
unsigned int numa_scan_period;
unsigned int numa_scan_period_max;
int numa_preferred_nid;
- int numa_migrate_deferred;
unsigned long numa_migrate_retry;
u64 node_stamp; /* migration stamp */
struct callback_head numa_work;
* Scheduling placement decisions are made based on the these counts.
* The values remain static for the duration of a PTE scan
*/
- unsigned long *numa_faults;
+ unsigned long *numa_faults_memory;
unsigned long total_numa_faults;
/*
* numa_faults_buffer records faults per node during the current
- * scan window. When the scan completes, the counts in numa_faults
- * decay and these values are copied.
+ * scan window. When the scan completes, the counts in
+ * numa_faults_memory decay and these values are copied.
+ */
+ unsigned long *numa_faults_buffer_memory;
+
+ /*
+ * Track the nodes the process was running on when a NUMA hinting
+ * fault was incurred.
*/
- unsigned long *numa_faults_buffer;
+ unsigned long *numa_faults_cpu;
+ unsigned long *numa_faults_buffer_cpu;
/*
* numa_faults_locality tracks if faults recorded during the last
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
extern void task_numa_free(struct task_struct *p);
-
-extern unsigned int sysctl_numa_balancing_migrate_deferred;
+extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
+ int src_nid, int dst_cpu);
#else
static inline void task_numa_fault(int last_node, int node, int pages,
int flags)
static inline void task_numa_free(struct task_struct *p)
{
}
+static inline bool should_numa_migrate_memory(struct task_struct *p,
+ struct page *page, int src_nid, int dst_cpu)
+{
+ return true;
+}
#endif
static inline struct pid *task_pid(struct task_struct *task)
* but then during bootup it turns out that sched_clock()
* is reliable after all:
*/
-extern int sched_clock_stable;
+extern int sched_clock_stable(void);
+extern void set_sched_clock_stable(void);
+extern void clear_sched_clock_stable(void);
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int,
const struct sched_param *);
+extern int sched_setattr(struct task_struct *,
+ const struct sched_attr *);
extern struct task_struct *idle_task(int cpu);
/**
* is_idle_task - is the specified task an idle task?
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif
-extern void sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern void sched_dead(struct task_struct *p);
extern void proc_caches_init(void);
}
#endif
+static inline void current_clr_polling(void)
+{
+ __current_clr_polling();
+
+ /*
+ * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
+ * Once the bit is cleared, we'll get IPIs with every new
+ * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
+ * fold.
+ */
+ smp_mb(); /* paired with resched_task() */
+
+ preempt_fold_need_resched();
+}
+
static __always_inline bool need_resched(void)
{
return unlikely(tif_need_resched());