#include <linux/tsacct_kern.h>
#include <asm/tlb.h>
-#include <asm-generic/vmlinux.lds.h>
#ifdef CONFIG_PARAVIRT
# include <asm/paravirt.h>
void __dl_clear_params(struct task_struct *p);
-/*
- * To keep the bandwidth of -deadline tasks and groups under control
- * we need some place where:
- * - store the maximum -deadline bandwidth of the system (the group);
- * - cache the fraction of that bandwidth that is currently allocated.
- *
- * This is all done in the data structure below. It is similar to the
- * one used for RT-throttling (rt_bandwidth), with the main difference
- * that, since here we are only interested in admission control, we
- * do not decrease any runtime while the group "executes", neither we
- * need a timer to replenish it.
- *
- * With respect to SMP, the bandwidth is given on a per-CPU basis,
- * meaning that:
- * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
- * - dl_total_bw array contains, in the i-eth element, the currently
- * allocated bandwidth on the i-eth CPU.
- * Moreover, groups consume bandwidth on each CPU, while tasks only
- * consume bandwidth on the CPU they're running on.
- * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
- * that will be shown the next time the proc or cgroup controls will
- * be red. It on its turn can be changed by writing on its own
- * control.
- */
struct dl_bandwidth {
raw_spinlock_t dl_runtime_lock;
u64 dl_runtime;
return sysctl_sched_rt_runtime >= 0;
}
+/*
+ * To keep the bandwidth of -deadline tasks under control
+ * we need some place where:
+ * - store the maximum -deadline bandwidth of each cpu;
+ * - cache the fraction of bandwidth that is currently allocated in
+ * each root domain;
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, bandwidth is given on a per root domain basis,
+ * meaning that:
+ * - bw (< 100%) is the deadline bandwidth of each CPU;
+ * - total_bw is the currently allocated bandwidth in each root domain;
+ */
struct dl_bw {
raw_spinlock_t lock;
u64 bw;
struct dl_bw dl_bw;
struct cpudl cpudl;
+ /*
+ * Indicate whether a root_domain's dl_bw has been checked or
+ * updated. It's monotonously increasing value.
+ *
+ * Also, some corner cases, like 'wrap around' is dangerous, but given
+ * that u64 is 'big enough'. So that shouldn't be a concern.
+ */
+ u64 visit_gen;
+
#ifdef HAVE_RT_PUSH_IPI
/*
* For IPI pull requests, loop across the rto_mask.
/* This is used to determine avg_idle's max value */
u64 max_idle_balance_cost;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ struct rcuwait hotplug_wait;
+#endif
#endif /* CONFIG_SMP */
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
#endif
+
+#ifdef CONFIG_SMP
+ unsigned int nr_pinned;
+#endif
+ unsigned int push_busy;
+ struct cpu_stop_work push_work;
};
#ifdef CONFIG_FAIR_GROUP_SCHED
#endif
}
+#define MDF_PUSH 0x01
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+#ifdef CONFIG_SMP
+ return p->migration_disabled;
+#else
+ return false;
+#endif
+}
#ifdef CONFIG_SCHED_SMT
extern void __update_idle_core(struct rq *rq);
#endif
};
+extern struct callback_head balance_push_callback;
+
/*
* Lockdep annotation that avoids accidental unlocks; it's like a
* sticky/continuous lockdep_assert_held().
#ifdef CONFIG_SCHED_DEBUG
rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
rf->clock_update_flags = 0;
+#ifdef CONFIG_SMP
+ SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback);
+#endif
#endif
}
{
lockdep_assert_held(&rq->lock);
- if (unlikely(head->next))
+ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
return;
head->func = (void (*)(struct callback_head *))func;
int id;
#endif
- unsigned long cpumask[0]; /* Balance mask */
+ unsigned long cpumask[]; /* Balance mask */
};
struct sched_group {
#undef SCHED_FEAT
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
/*
* To support run-time toggling of sched features, all the translation units
*/
extern const_debug unsigned int sysctl_sched_features;
+#ifdef CONFIG_JUMP_LABEL
#define SCHED_FEAT(name, enabled) \
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
-#else /* !(SCHED_DEBUG && CONFIG_JUMP_LABEL) */
+#else /* !CONFIG_JUMP_LABEL */
+
+#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+
+#endif /* CONFIG_JUMP_LABEL */
+
+#else /* !SCHED_DEBUG */
/*
* Each translation unit has its own copy of sysctl_sched_features to allow
#define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
-#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */
+#endif /* SCHED_DEBUG */
extern struct static_key_false sched_numa_balancing;
extern struct static_key_false sched_schedstats;
return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
}
-/*
- * wake flags
- */
-#define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */
-#define WF_FORK 0x02 /* Child wakeup after fork */
-#define WF_MIGRATED 0x04 /* Internal use, task got migrated */
-#define WF_ON_CPU 0x08 /* Wakee is on_cpu */
+/* Wake flags. The first three directly map to some SD flag value */
+#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
+
+#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_ON_CPU 0x40 /* Wakee is on_cpu */
+
+#ifdef CONFIG_SMP
+static_assert(WF_EXEC == SD_BALANCE_EXEC);
+static_assert(WF_FORK == SD_BALANCE_FORK);
+static_assert(WF_TTWU == SD_BALANCE_WAKE);
+#endif
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
#ifdef CONFIG_SMP
int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
- int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
+ int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
- const struct cpumask *newmask);
+ const struct cpumask *newmask,
+ u32 flags);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
+
+ struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
#endif
void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_change_group)(struct task_struct *p, int type);
#endif
-} __aligned(STRUCT_ALIGNMENT); /* STRUCT_ALIGN(), vmlinux.lds.h */
+};
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
next->sched_class->set_next_task(rq, next, false);
}
+
+/*
+ * Helper to define a sched_class instance; each one is placed in a separate
+ * section which is ordered by the linker script:
+ *
+ * include/asm-generic/vmlinux.lds.h
+ *
+ * Also enforce alignment on the instance, not the type, to guarantee layout.
+ */
+#define DEFINE_SCHED_CLASS(name) \
+const struct sched_class name##_sched_class \
+ __aligned(__alignof__(struct sched_class)) \
+ __section("__" #name "_sched_class")
+
/* Defined in include/asm-generic/vmlinux.lds.h */
extern struct sched_class __begin_sched_classes[];
extern struct sched_class __end_sched_classes[];
extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
extern struct task_struct *pick_next_task_idle(struct rq *rq);
+#define SCA_CHECK 0x01
+#define SCA_MIGRATE_DISABLE 0x02
+#define SCA_MIGRATE_ENABLE 0x04
+
#ifdef CONFIG_SMP
extern void update_group_capacity(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq);
-extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
+extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+
+static inline struct task_struct *get_push_task(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ lockdep_assert_held(&rq->lock);
+
+ if (rq->push_busy)
+ return NULL;
+
+ if (p->nr_cpus_allowed == 1)
+ return NULL;
+
+ rq->push_busy = true;
+ return get_task_struct(p);
+}
+
+extern int push_cpu_stop(void *arg);
#endif
projects / linux-2.6-microblaze.git / blobdiff