1 files changed, 73 insertions, 3 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 52453a2d0a79..ad4f4fbd002e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -74,6 +74,13 @@ extern void update_cpu_load_active(struct rq *this_rq);
 #define NICE_0_SHIFT            SCHED_LOAD_SHIFT
 
 /*
+ * Single value that decides SCHED_DEADLINE internal math precision.
+ * 10 -> just above 1us
+ * 9  -> just above 0.5us
+ */
+#define DL_SCALE (10)
+
+/*
  * These are the 'tuning knobs' of the scheduler:
  */
 
@@ -107,7 +114,7 @@ static inline int task_has_dl_policy(struct task_struct *p)
         return dl_policy(p->policy);
 }
 
-static inline int dl_time_before(u64 a, u64 b)
+static inline bool dl_time_before(u64 a, u64 b)
 {
         return (s64)(a - b) < 0;
 }
@@ -115,8 +122,8 @@ static inline int dl_time_before(u64 a, u64 b)
 /*
  * Tells if entity @a should preempt entity @b.
  */
-static inline
-int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+static inline bool
+dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
 {
         return dl_time_before(a->deadline, b->deadline);
 }
@@ -136,6 +143,50 @@ struct rt_bandwidth {
         u64                     rt_runtime;
         struct hrtimer          rt_period_timer;
 };
+/*
+ * 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;
+        u64 dl_period;
+};
+
+static inline int dl_bandwidth_enabled(void)
+{
+        return sysctl_sched_dl_runtime >= 0;
+}
+
+extern struct dl_bw *dl_bw_of(int i);
+
+struct dl_bw {
+        raw_spinlock_t lock;
+        u64 bw, total_bw;
+};
+
+static inline u64 global_dl_period(void);
+static inline u64 global_dl_runtime(void);
 
 extern struct mutex sched_domains_mutex;
 
@@ -423,6 +474,8 @@ struct dl_rq {
          */
         struct rb_root pushable_dl_tasks_root;
         struct rb_node *pushable_dl_tasks_leftmost;
+#else
+        struct dl_bw dl_bw;
 #endif
 };
 
@@ -449,6 +502,7 @@ struct root_domain {
          */
         cpumask_var_t dlo_mask;
         atomic_t dlo_count;
+        struct dl_bw dl_bw;
 
         /*
          * The "RT overload" flag: it gets set if a CPU has more than
@@ -897,7 +951,18 @@ static inline u64 global_rt_runtime(void)
         return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
+static inline u64 global_dl_period(void)
+{
+        return (u64)sysctl_sched_dl_period * NSEC_PER_USEC;
+}
+
+static inline u64 global_dl_runtime(void)
+{
+        if (sysctl_sched_dl_runtime < 0)
+                return RUNTIME_INF;
 
+        return (u64)sysctl_sched_dl_runtime * NSEC_PER_USEC;
+}
 
 static inline int task_current(struct rq *rq, struct task_struct *p)
 {
@@ -1145,6 +1210,7 @@ extern void update_max_interval(void);
 extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
+extern void init_sched_dl_class(void);
 
 extern void resched_task(struct task_struct *p);
 extern void resched_cpu(int cpu);
@@ -1152,8 +1218,12 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
+extern struct dl_bandwidth def_dl_bandwidth;
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 
+unsigned long to_ratio(u64 period, u64 runtime);
+
 extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);