sched: SCHED_DEADLINE v5

new file mode 100644
index 0000000..3582691
@@ -0,0 +1,4 @@
+#ifndef _ASM_GENERIC_MATH128_H
+#define _ASM_GENERIC_MATH128_H
+
+#endif /*_ASM_GENERIC_MATH128_H */

180 lines not on this page · raw message

new file mode 100644
index 0000000..55b123a
@@ -0,0 +1,40 @@
+#include <linux/math128.h>
+
+#ifndef mul_u64_u64
+/*
+ * a * b = (ah * 2^32 + al) * (bh * 2^32 + bl) =
+ *   ah*bh * 2^64 + (ah*bl + bh*al) * 2^32 + al*bl
+ */
+u128 mul_u64_u64(u64 a, u64 b)
+{
+	u128 t1, t2, t3, t4;
+	u32 ah, al;
+	u32 bh, bl;
+
+	ah = a >> 32;
+	al = a;
+
+	bh = b >> 32;
+	bl = b;
+
+	t1.lo = 0;
+	t1.hi = (u64)ah * bh;
+
+	t2.lo = (u64)ah * bl;
+	t2.hi = t2.lo >> 32;
+	t2.lo <<= 32;
+
+	t3.lo = (u64)al * bh;
+	t3.hi = t3.lo >> 32;
+	t3.lo <<= 32;
+
+	t4.lo = (u64)al * bl;
+	t4.hi = 0;
+
+	t1 = add_u128(t1, t2);
+	t1 = add_u128(t1, t3);
+	t1 = add_u128(t1, t4);
+
+	return t1;
+}
+#endif /* mul_u64_u64 */

new file mode 100644
index 0000000..c0e2a6c
@@ -0,0 +1,39 @@
+#ifndef _ASM_MATH128_H
+#define _ASM_MATH128_H
+
+#ifdef CONFIG_X86_64
+
+#ifdef __SIZEOF_INT128__
+#define ARCH_HAS_INT128
+#endif
+
+#ifndef ARCH_HAS_INT128
+
+static inline u128 mul_u64_u64(u64 a, u64 b)
+{
+       u128 res;
+
+       asm("mulq %2"
+               : "=a" (res.lo), "=d" (res.hi)
+               :  "rm" (b), "0" (a));
+
+       return res;
+}
+#define mul_u64_u64 mul_u64_u64
+
+static inline u128 add_u128(u128 a, u128 b)
+{
+       u128 res;
+
+       asm("addq %2,%0;\n"
+           "adcq %3,%1;\n"
+               : "=rm" (res.lo), "=rm" (res.hi)
+               : "r" (b.lo), "r" (b.hi), "0" (a.lo), "1" (a.hi));
+
+       return res;
+}
+#define add_u128 add_u128
+
+#endif /* ARCH_HAS_INT128 */
+#endif /* CONFIG_X86_64 */
+#endif /* _ASM_MATH128_H */

index 28fa9d0..6f66117 100644
@@ -1103,6 +1103,7 @@ struct sched_class {
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork) (struct task_struct *p);
+	void (*task_dead) (struct task_struct *p);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_to) (struct rq *this_rq, struct task_struct *task);

index d833cc9..a622f78 100644
@@ -1962,6 +1962,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.

index 512cd14..2529fbf 100644
@@ -404,6 +404,9 @@
 #define __NR_setns			(__NR_SYSCALL_BASE+375)
 #define __NR_process_vm_readv		(__NR_SYSCALL_BASE+376)
 #define __NR_process_vm_writev		(__NR_SYSCALL_BASE+377)
+#define __NR_sched_setscheduler2	(__NR_SYSCALL_BASE+378)
+#define __NR_sched_setparam2		(__NR_SYSCALL_BASE+379)
+#define __NR_sched_getparam2		(__NR_SYSCALL_BASE+380)
 
 /*
  * The following SWIs are ARM private.

62 lines not on this page · raw message

index 3de3acb..5f7309d 100644
@@ -38,6 +38,7 @@ struct rlimit;
 struct rlimit64;
 struct rusage;
 struct sched_param;
+struct sched_param2;
 struct sel_arg_struct;
 struct semaphore;
 struct sembuf;

@@ -328,11 +329,17 @@ asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
 asmlinkage long sys_nice(int increment);
 asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_setscheduler2(pid_t pid, int policy,
+					struct sched_param2 __user *param);
 asmlinkage long sys_sched_setparam(pid_t pid,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_setparam2(pid_t pid,
+					struct sched_param2 __user *param);
 asmlinkage long sys_sched_getscheduler(pid_t pid);
 asmlinkage long sys_sched_getparam(pid_t pid,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_getparam2(pid_t pid,
+					struct sched_param2 __user *param);
 asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 					unsigned long __user *user_mask_ptr);
 asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,

155 lines not on this page · raw message

index 6d0c098..c09db62 100644
@@ -39,6 +39,7 @@
 #define SCHED_BATCH		3
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
+#define SCHED_DEADLINE		6
 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
 #define SCHED_RESET_ON_FORK     0x40000000
 

@@ -130,6 +131,10 @@ struct sched_param {
  * timing constraints.
  *
  * @__unused		padding to allow future expansion without ABI issues
+ *
+ * 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_param2 {
 	int sched_priority;

@@ -1117,6 +1122,7 @@ struct sched_domain;
 #else
 #define ENQUEUE_WAKING		0
 #endif
+#define ENQUEUE_REPLENISH	8
 
 #define DEQUEUE_SLEEP		1
 

@@ -1248,6 +1254,47 @@ struct sched_rt_entity {
 #endif
 };
 
+struct sched_dl_entity {
+	struct rb_node	rb_node;
+	int nr_cpus_allowed;
+
+	/*
+	 * Original scheduling parameters. Copied here from sched_param2
+	 * 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	*/
+
+	/*
+	 * 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;
+	 */
+	int dl_throttled, dl_new;
+
+	/*
+	 * Bandwidth enforcement timer. Each -deadline task has its
+	 * own bandwidth to be enforced, thus we need one timer per task.
+	 */
+	struct hrtimer dl_timer;
+};
+
 /*
  * default timeslice is 100 msecs (used only for SCHED_RR tasks).
  * Timeslices get refilled after they expire.

@@ -1281,6 +1328,7 @@ struct task_struct {
 	const struct sched_class *sched_class;
 	struct sched_entity se;
 	struct sched_rt_entity rt;
+	struct sched_dl_entity dl;
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* list of struct preempt_notifier: */

@@ -1637,6 +1685,10 @@ struct task_struct {
  * user-space.  This allows kernel threads to set their
  * priority to a value higher than any user task. Note:
  * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ *
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+ * NORMAL/BATCH tasks.
  */
 
 #define MAX_USER_RT_PRIO	100

@@ -1645,9 +1697,23 @@ struct task_struct {
 #define MAX_PRIO		(MAX_RT_PRIO + 40)
 #define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
 
+#define MAX_DL_PRIO		0
+
+static inline int dl_prio(int prio)
+{
+	if (unlikely(prio < MAX_DL_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int dl_task(struct task_struct *p)
+{
+	return dl_prio(p->prio);
+}
+
 static inline int rt_prio(int prio)
 {
-	if (unlikely(prio < MAX_RT_PRIO))
+	if ((unsigned)prio < MAX_RT_PRIO)
 		return 1;
 	return 0;
 }

@@ -2214,7 +2280,7 @@ extern void wake_up_new_task(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(struct task_struct *p);
+extern int sched_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);

index ad54c83..b04c471 100644
@@ -1310,7 +1310,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p);
+	retval = sched_fork(p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
 
 	retval = perf_event_init_task(p);
 	if (retval)

index ae34bf5..2187152 100644
@@ -1565,7 +1565,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	unsigned long slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (dl_task(current) || rt_task(current))
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);

240 lines not on this page · raw message

688 lines not on this page · raw message

index ba9dccf..846a352 100644
@@ -50,11 +50,23 @@ static inline int rt_policy(int policy)
 	return 0;
 }
 
+static inline int dl_policy(int policy)
+{
+	if (unlikely(policy == SCHED_DEADLINE))
+		return 1;
+	return 0;
+}
+
 static inline int task_has_rt_policy(struct task_struct *p)
 {
 	return rt_policy(p->policy);
 }
 
+static inline int task_has_dl_policy(struct task_struct *p)
+{
+	return dl_policy(p->policy);
+}
+
 /*
  * This is the priority-queue data structure of the RT scheduling class:
  */

@@ -309,6 +321,15 @@ struct rt_rq {
 #endif
 };
 
+/* Deadline class' related fields in a runqueue */
+struct dl_rq {
+	/* runqueue is an rbtree, ordered by deadline */
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+
+	unsigned long dl_nr_running;
+};
+
 #ifdef CONFIG_SMP
 
 /*

@@ -370,6 +391,7 @@ struct rq {
 
 	struct cfs_rq cfs;
 	struct rt_rq rt;
+	struct dl_rq dl;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */

@@ -844,6 +866,7 @@ enum cpuacct_stat_index {
    for (class = sched_class_highest; class; class = class->next)
 
 extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
 extern const struct sched_class rt_sched_class;
 extern const struct sched_class fair_sched_class;
 extern const struct sched_class idle_sched_class;

@@ -876,6 +899,8 @@ 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 void init_dl_task_timer(struct sched_dl_entity *dl_se);
+
 extern void update_idle_cpu_load(struct rq *this_rq);
 
 #ifdef CONFIG_CGROUP_CPUACCT

@@ -1143,6 +1168,7 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *rt_rq, struct rq *rq);
 extern void unthrottle_offline_cfs_rqs(struct rq *rq);
 
 extern void account_cfs_bandwidth_used(int enabled, int was_enabled);

index 7b386e8..1db3750 100644
@@ -83,7 +83,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 const struct sched_class stop_sched_class = {
-	.next			= &rt_sched_class,
+	.next			= &dl_sched_class,
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,

index c09db62..fb8062c 100644
@@ -1370,6 +1370,7 @@ struct task_struct {
 	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;

index 5fa0338..051e609 100644
@@ -1811,6 +1811,7 @@ int sched_fork(struct task_struct *p)
 #endif
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
 
 	put_cpu();

@@ -5164,6 +5165,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 
 	cpumask_copy(&p->cpus_allowed, new_mask);
 	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	p->dl.nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
 /*

@@ -5880,6 +5882,7 @@ static void free_rootdomain(struct rcu_head *rcu)
 	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
+	free_cpumask_var(rd->dlo_mask);
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);

@@ -5931,8 +5934,10 @@ static int init_rootdomain(struct root_domain *rd)
 		goto out;
 	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_dlo_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;

@@ -5940,6 +5945,8 @@ static int init_rootdomain(struct root_domain *rd)
 
 free_rto_mask:
 	free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+	free_cpumask_var(rd->dlo_mask);
 free_online:
 	free_cpumask_var(rd->online);
 free_span:

@@ -7060,6 +7067,7 @@ void __init sched_init_smp(void)
 	free_cpumask_var(non_isolated_cpus);
 
 	init_sched_rt_class();
+	init_sched_dl_class();
 }
 #else
 void __init sched_init_smp(void)

1,056 lines not on this page · raw message

index c5565c3..ce4f5e1 100644
@@ -1794,7 +1794,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
 	    p->rt.nr_cpus_allowed > 1 &&
-	    rt_task(rq->curr) &&
+	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
 	    (rq->curr->rt.nr_cpus_allowed < 2 ||
 	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);

index 846a352..4b02092 100644
@@ -328,6 +328,31 @@ struct dl_rq {
 	struct rb_node *rb_leftmost;
 
 	unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Deadline values of the currently executing and the
+	 * earliest ready task on this rq. Caching these facilitates
+	 * the decision wether or not a ready but not running task
+	 * should migrate somewhere else.
+	 */
+	struct {
+		u64 curr;
+		u64 next;
+	} earliest_dl;
+
+	unsigned long dl_nr_migratory;
+	unsigned long dl_nr_total;
+	int overloaded;
+
+	/*
+	 * Tasks on this rq that can be pushed away. They are kept in
+	 * an rb-tree, ordered by tasks' deadlines, with caching
+	 * of the leftmost (earliest deadline) element.
+	 */
+	struct rb_root pushable_dl_tasks_root;
+	struct rb_node *pushable_dl_tasks_leftmost;
+#endif
 };
 
 #ifdef CONFIG_SMP

@@ -348,6 +373,13 @@ struct root_domain {
 	cpumask_var_t online;
 
 	/*
+	 * The bit corresponding to a CPU gets set here if such CPU has more
+	 * than one runnable -deadline task (as it is below for RT tasks).
+	 */
+	cpumask_var_t dlo_mask;
+	atomic_t dlo_count;
+
+	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
 	 * one runnable RT task.
 	 */

@@ -890,6 +922,7 @@ extern void sched_init_granularity(void);
 extern void update_max_interval(void);
 extern void update_group_power(struct sched_domain *sd, int cpu);
 extern int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu);
+extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 

index 9bc48a0..0262c16 100644
@@ -554,6 +554,8 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = rq->clock_task;
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	dl_se->runtime -= delta_exec;
 	if (dl_runtime_exceeded(rq, dl_se)) {
 		__dequeue_task_dl(rq, curr, 0);

index fb8062c..dc5b753 100644
@@ -1265,6 +1265,7 @@ struct sched_dl_entity {
 	 */
 	u64 dl_runtime;		/* maximum runtime for each instance	*/
 	u64 dl_deadline;	/* relative deadline of each instance	*/
+	u64 dl_period;		/* separation of two instances (period) */
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,

index 051e609..fd09961 100644
@@ -1724,6 +1724,7 @@ static void __sched_fork(struct task_struct *p)
 	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	p->dl.dl_runtime = p->dl.runtime = 0;
 	p->dl.dl_deadline = p->dl.deadline = 0;
+	p->dl.dl_period = 0;
 	p->dl.flags = 0;
 
 	INIT_LIST_HEAD(&p->rt.run_list);

@@ -4092,6 +4093,10 @@ __setparam_dl(struct task_struct *p, const struct sched_param2 *param2)
 	init_dl_task_timer(dl_se);
 	dl_se->dl_runtime = param2->sched_runtime;
 	dl_se->dl_deadline = param2->sched_deadline;
+	if (param2->sched_period != 0)
+		dl_se->dl_period = param2->sched_period;
+	else
+		dl_se->dl_period = dl_se->dl_deadline;
 	dl_se->flags = param2->sched_flags;
 	dl_se->dl_throttled = 0;
 	dl_se->dl_new = 1;

@@ -4105,19 +4110,23 @@ __getparam_dl(struct task_struct *p, struct sched_param2 *param2)
 	param2->sched_priority = p->rt_priority;
 	param2->sched_runtime = dl_se->dl_runtime;
 	param2->sched_deadline = dl_se->dl_deadline;
+	param2->sched_period = dl_se->dl_period;
 	param2->sched_flags = dl_se->flags;
 }
 
 /*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
- * than the runtime.
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline.
  */
 static bool
 __checkparam_dl(const struct sched_param2 *prm)
 {
-	return prm && (&prm->sched_deadline) != 0 &&
-	       (s64)(&prm->sched_deadline - &prm->sched_runtime) >= 0;
+	return prm && prm->sched_deadline != 0 &&
+	       (prm->sched_period == 0 ||
+		(s64)(prm->sched_period - prm->sched_deadline) >= 0) &&
+	       (s64)(prm->sched_deadline - prm->sched_runtime) >= 0;
 }
 
 /*

index 0262c16..75de7cc 100644
@@ -286,7 +286,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	 * arbitrary large.
 	 */
 	while (dl_se->runtime <= 0) {
-		dl_se->deadline += dl_se->dl_deadline;
+		dl_se->deadline += dl_se->dl_period;
 		dl_se->runtime += dl_se->dl_runtime;
 	}
 

@@ -326,9 +326,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
  *
  * This function returns true if:
  *
- *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
+ *   runtime / (deadline - t) > dl_runtime / dl_period ,
  *
  * IOW we can't recycle current parameters.
+ *
+ * Notice that the bandwidth check is done against the period. For
+ * task with deadline equal to period this is the same of using
+ * dl_deadline instead of dl_period in the equation above.
  */
 static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 {

@@ -347,7 +351,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 	 * to the (absolute) deadline. Therefore, overflowing the u64
 	 * type is very unlikely to occur in both cases.
 	 */
-	left = mul_u64_u64(dl_se->dl_deadline, dl_se->runtime);
+	left = mul_u64_u64(dl_se->dl_period, dl_se->runtime);
 	right = mul_u64_u64((dl_se->deadline - t), dl_se->dl_runtime);
 
 	if (cmp_u128(left, right) > 0)

index dc5b753..3599db7 100644
@@ -1254,6 +1254,15 @@ struct sched_rt_entity {
 #endif
 };
 
+#ifdef CONFIG_SCHEDSTATS
+struct sched_stats_dl {
+	u64			last_dmiss;
+	u64			last_rorun;
+	u64			dmiss_max;
+	u64			rorun_max;
+};
+#endif
+
 struct sched_dl_entity {
 	struct rb_node	rb_node;
 	int nr_cpus_allowed;

@@ -1294,6 +1303,10 @@ struct sched_dl_entity {
 	 * own bandwidth to be enforced, thus we need one timer per task.
 	 */
 	struct hrtimer dl_timer;
+
+#ifdef CONFIG_SCHEDSTATS
+	struct sched_stats_dl stats;
+#endif
 };
 
 /*

64 lines not on this page · raw message

66 lines not on this page · raw message

index 4b02092..996a992 100644
@@ -329,6 +329,8 @@ struct dl_rq {
 
 	unsigned long dl_nr_running;
 
+	u64 exec_clock;
+
 #ifdef CONFIG_SMP
 	/*
 	 * Deadline values of the currently executing and the

@@ -355,6 +357,11 @@ struct dl_rq {
 #endif
 };
 
+#ifdef CONFIG_SCHED_DEBUG
+struct sched_dl_entity *__pick_dl_last_entity(struct dl_rq *dl_rq);
+void print_dl_stats(struct seq_file *m, int cpu);
+#endif
+
 #ifdef CONFIG_SMP
 
 /*

@@ -1201,7 +1208,7 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
-extern void init_dl_rq(struct dl_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
 extern void unthrottle_offline_cfs_rqs(struct rq *rq);
 
 extern void account_cfs_bandwidth_used(int enabled, int was_enabled);

index ff791ea..e37da43 100644
@@ -27,6 +27,7 @@ static int			wakeup_cpu;
 static int			wakeup_current_cpu;
 static unsigned			wakeup_prio = -1;
 static int			wakeup_rt;
+static int			wakeup_dl;
 
 static arch_spinlock_t wakeup_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;

@@ -428,9 +429,17 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	tracing_record_cmdline(p);
 	tracing_record_cmdline(current);
 
-	if ((wakeup_rt && !rt_task(p)) ||
-			p->prio >= wakeup_prio ||
-			p->prio >= current->prio)
+	/*
+	 * Semantic is like this:
+	 *  - wakeup tracer handles all tasks in the system, independently
+	 *    from their scheduling class;
+	 *  - wakeup_rt tracer handles tasks belonging to sched_dl and
+	 *    sched_rt class;
+	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
+	 */
+	if ((wakeup_dl && !dl_task(p)) ||
+	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (p->prio >= wakeup_prio || p->prio >= current->prio))
 		return;
 
 	pc = preempt_count();

@@ -442,7 +451,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	arch_spin_lock(&wakeup_lock);
 
 	/* check for races. */
-	if (!tracer_enabled || p->prio >= wakeup_prio)
+	if (!tracer_enabled || (!dl_task(p) && p->prio >= wakeup_prio))
 		goto out_locked;
 
 	/* reset the trace */

@@ -550,16 +559,25 @@ static int __wakeup_tracer_init(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	wakeup_dl = 0;
 	wakeup_rt = 0;
 	return __wakeup_tracer_init(tr);
 }
 
 static int wakeup_rt_tracer_init(struct trace_array *tr)
 {
+	wakeup_dl = 0;
 	wakeup_rt = 1;
 	return __wakeup_tracer_init(tr);
 }
 
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+	wakeup_dl = 1;
+	wakeup_rt = 0;
+	return __wakeup_tracer_init(tr);
+}
+
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
 	stop_wakeup_tracer(tr);

@@ -622,6 +640,20 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.use_max_tr	= 1,
 };
 
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+	.name		= "wakeup_dl",
+	.init		= wakeup_dl_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.wait_pipe	= poll_wait_pipe,
+	.print_max	= 1,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+};
+
 __init static int init_wakeup_tracer(void)
 {
 	int ret;

@@ -634,6 +666,10 @@ __init static int init_wakeup_tracer(void)
 	if (ret)
 		return ret;
 
+	ret = register_tracer(&wakeup_dl_tracer);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 device_initcall(init_wakeup_tracer);

index 288541f..849063e 100644
@@ -765,11 +765,17 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 #ifdef CONFIG_SCHED_TRACER
 static int trace_wakeup_test_thread(void *data)
 {
-	/* Make this a RT thread, doesn't need to be too high */
-	static const struct sched_param param = { .sched_priority = 5 };
+	/* Make this a -deadline thread */
+	struct sched_param2 paramx = {
+		.sched_priority = 0,
+		.sched_runtime = 100000ULL,
+		.sched_deadline = 10000000ULL,
+		.sched_period = 10000000ULL
+		.sched_flags = 0
+	};
 	struct completion *x = data;
 
-	sched_setscheduler(current, SCHED_FIFO, &param);
+	sched_setscheduler2(current, SCHED_DEADLINE, &paramx);
 
 	/* Make it know we have a new prio */
 	complete(x);

@@ -781,8 +787,8 @@ static int trace_wakeup_test_thread(void *data)
 	/* we are awake, now wait to disappear */
 	while (!kthread_should_stop()) {
 		/*
-		 * This is an RT task, do short sleeps to let
-		 * others run.
+		 * This will likely be the system top priority
+		 * task, do short sleeps to let others run.
 		 */
 		msleep(100);
 	}

@@ -795,21 +801,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 {
 	unsigned long save_max = tracing_max_latency;
 	struct task_struct *p;
-	struct completion isrt;
+	struct completion is_ready;
 	unsigned long count;
 	int ret;
 
-	init_completion(&isrt);
+	init_completion(&is_ready);
 
-	/* create a high prio thread */
-	p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+	/* create a -deadline thread */
+	p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
 	if (IS_ERR(p)) {
 		printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
 		return -1;
 	}
 
-	/* make sure the thread is running at an RT prio */
-	wait_for_completion(&isrt);
+	/* make sure the thread is running at -deadline policy */
+	wait_for_completion(&is_ready);
 
 	/* start the tracing */
 	ret = tracer_init(trace, tr);

@@ -821,7 +827,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	/* reset the max latency */
 	tracing_max_latency = 0;
 
-	/* sleep to let the RT thread sleep too */
+	/* sleep to let the thread sleep too */
 	msleep(100);
 
 	/*

index e4baff5..b5ab616 100644
@@ -10,6 +10,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/securebits.h>
+#include <linux/rbtree.h>
 #include <net/net_namespace.h>
 
 #ifdef CONFIG_SMP

@@ -134,6 +135,14 @@ extern struct cred init_cred;
 
 #define INIT_TASK_COMM "swapper"
 
+#ifdef CONFIG_RT_MUTEXES
+# define INIT_RT_MUTEXES(tsk)						\
+	.pi_waiters = RB_ROOT,						\
+	.pi_waiters_leftmost = NULL,
+#else
+# define INIT_RT_MUTEXES(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)

@@ -200,6 +209,7 @@ extern struct cred init_cred;
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
 	INIT_CPUSET_SEQ							\
+	INIT_RT_MUTEXES(tsk)						\
 }
 
 

index de17134..3aed8d7 100644
@@ -13,7 +13,7 @@
 #define __LINUX_RT_MUTEX_H
 
 #include <linux/linkage.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
 #include <linux/spinlock_types.h>
 
 extern int max_lock_depth; /* for sysctl */

@@ -22,12 +22,14 @@ extern int max_lock_depth; /* for sysctl */
  * The rt_mutex structure
  *
  * @wait_lock:	spinlock to protect the structure
- * @wait_list:	pilist head to enqueue waiters in priority order
+ * @waiters:	rbtree root to enqueue waiters in priority order
+ * @waiters_leftmost: top waiter
  * @owner:	the mutex owner
  */
 struct rt_mutex {
 	raw_spinlock_t		wait_lock;
-	struct plist_head	wait_list;
+	struct rb_root          waiters;
+	struct rb_node          *waiters_leftmost;
 	struct task_struct	*owner;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	int			save_state;

@@ -66,7 +68,7 @@ struct hrtimer_sleeper;
 
 #define __RT_MUTEX_INITIALIZER(mutexname) \
 	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
-	, .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \
+	, .waiters = RB_ROOT \
 	, .owner = NULL \
 	__DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
 

@@ -98,12 +100,4 @@ extern int rt_mutex_trylock(struct rt_mutex *lock);
 
 extern void rt_mutex_unlock(struct rt_mutex *lock);
 
-#ifdef CONFIG_RT_MUTEXES
-# define INIT_RT_MUTEXES(tsk)						\
-	.pi_waiters	= PLIST_HEAD_INIT(tsk.pi_waiters),	\
-	INIT_RT_MUTEX_DEBUG(tsk)
-#else
-# define INIT_RT_MUTEXES(tsk)
-#endif
-
 #endif

index 3599db7..1d74c3e 100644
@@ -57,6 +57,7 @@ struct sched_param {
 #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>

@@ -1531,7 +1532,8 @@ struct task_struct {
 
 #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;
 #endif

index b04c471..12c531b 100644
@@ -1111,7 +1111,8 @@ static void rt_mutex_init_task(struct task_struct *p)
 {
 	raw_spin_lock_init(&p->pi_lock);
 #ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&p->pi_waiters);
+	p->pi_waiters = RB_ROOT;
+	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
 #endif
 }

index 16502d3..0f339ca 100644
@@ -23,7 +23,7 @@
 #include <linux/kallsyms.h>
 #include <linux/syscalls.h>
 #include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
 #include <linux/fs.h>
 #include <linux/debug_locks.h>
 

@@ -56,7 +56,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
 
 void rt_mutex_debug_task_free(struct task_struct *task)
 {
-	DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
 	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
 }
 

@@ -153,16 +153,14 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
 void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 {
 	memset(waiter, 0x11, sizeof(*waiter));
-	plist_node_init(&waiter->list_entry, MAX_PRIO);
-	plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	RB_CLEAR_NODE(&waiter->tree_entry);
 	waiter->deadlock_task_pid = NULL;
 }
 
 void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 {
 	put_pid(waiter->deadlock_task_pid);
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 

261 lines not on this page · raw message

index 53a66c8..b65442f 100644
@@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
  * This is the control structure for tasks blocked on a rt_mutex,
  * which is allocated on the kernel stack on of the blocked task.
  *
- * @list_entry:		pi node to enqueue into the mutex waiters list
- * @pi_list_entry:	pi node to enqueue into the mutex owner waiters list
+ * @tree_entry:		pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry:	pi node to enqueue into the mutex owner waiters tree
  * @task:		task reference to the blocked task
  */
 struct rt_mutex_waiter {
-	struct plist_node	list_entry;
-	struct plist_node	pi_list_entry;
+	struct rb_node          tree_entry;
+	struct rb_node          pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
 #ifdef CONFIG_DEBUG_RT_MUTEXES

@@ -57,11 +57,11 @@ struct rt_mutex_waiter {
 };
 
 /*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
  */
 static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
 {
-	return !plist_head_empty(&lock->wait_list);
+	return !RB_EMPTY_ROOT(&lock->waiters);
 }
 
 static inline struct rt_mutex_waiter *

@@ -69,8 +69,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *w;
 
-	w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
-			       list_entry);
+	w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+		     tree_entry);
 	BUG_ON(w->lock != lock);
 
 	return w;

@@ -78,14 +78,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 
 static inline int task_has_pi_waiters(struct task_struct *p)
 {
-	return !plist_head_empty(&p->pi_waiters);
+	return !RB_EMPTY_ROOT(&p->pi_waiters);
 }
 
 static inline struct rt_mutex_waiter *
 task_top_pi_waiter(struct task_struct *p)
 {
-	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
-				  pi_list_entry);
+	return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+			pi_tree_entry);
 }
 
 /*

index fd09961..e1f312a 100644
@@ -7245,10 +7245,6 @@ void __init sched_init(void)
 	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
 #endif
 
-#ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&init_task.pi_waiters);
-#endif
-
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
 	 */

index 1d74c3e..c99f5d8 100644
@@ -1296,8 +1296,12 @@ struct sched_dl_entity {
 	 * @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;
+	int dl_throttled, dl_new, dl_boosted;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its

@@ -1536,6 +1540,8 @@ struct task_struct {
 	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

@@ -2187,6 +2193,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
 {

index 12c531b..fe01cc2 100644
@@ -1114,6 +1114,7 @@ static void rt_mutex_init_task(struct task_struct *p)
 	p->pi_waiters = RB_ROOT;
 	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
+	p->pi_top_task = NULL;
 #endif
 }
 

index c9a71eb..7187c50 100644
@@ -199,6 +199,14 @@ int rt_mutex_getprio(struct task_struct *task)
 		   task->normal_prio);
 }
 
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+	if (likely(!task_has_pi_waiters(task)))
+		return NULL;
+
+	return task_top_pi_waiter(task)->task;
+}
+
 /*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *

@@ -208,7 +216,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
 {
 	int prio = rt_mutex_getprio(task);
 
-	if (task->prio != prio)
+	if (task->prio != prio || dl_prio(prio))
 		rt_mutex_setprio(task, prio);
 }
 

@@ -638,7 +646,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->task->prio == task->prio) {
+	if (!waiter || (waiter->task->prio == task->prio &&
+			!dl_prio(task->prio))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}

index e1f312a..b304610 100644
@@ -3838,7 +3838,7 @@ EXPORT_SYMBOL(sleep_on_timeout);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, on_rq, running;
+	int oldprio, on_rq, running, enqueue_flag = 0;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 

@@ -3865,6 +3865,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	}
 
 	trace_sched_pi_setprio(p, prio);
+	p->pi_top_task = rt_mutex_get_top_task(p);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
 	on_rq = p->on_rq;

@@ -3874,19 +3875,42 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	if (dl_prio(prio))
+	/*
+	 * Boosting condition are:
+	 * 1. -rt task is running and holds mutex A
+	 *      --> -dl task blocks on mutex A
+	 *
+	 * 2. -dl task is running and holds mutex A
+	 *      --> -dl task blocks on mutex A and could preempt the
+	 *          running task
+	 */
+	if (dl_prio(prio)) {
+		if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+			dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+			p->dl.dl_boosted = 1;
+			p->dl.dl_throttled = 0;
+			enqueue_flag = ENQUEUE_REPLENISH;
+		} else
+			p->dl.dl_boosted = 0;
 		p->sched_class = &dl_sched_class;
-	else if (rt_prio(prio))
+	} else if (rt_prio(prio)) {
+		if (dl_prio(oldprio))
+			p->dl.dl_boosted = 0;
+		if (oldprio < prio)
+			enqueue_flag = ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
-	else
+	} else {
+		if (dl_prio(oldprio))
+			p->dl.dl_boosted = 0;
 		p->sched_class = &fair_sched_class;
+	}
 
 	p->prio = prio;
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+		enqueue_task(rq, p, enqueue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:

208 lines not on this page · raw message

index 996a992..04ec6df 100644
@@ -67,6 +67,20 @@ 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)
+{
+	return (s64)(a - b) < 0;
+}
+
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline
+int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+	return dl_time_before(a->deadline, b->deadline);
+}
+
 /*
  * This is the priority-queue data structure of the RT scheduling class:
  */

index c99f5d8..a8bda36 100644
@@ -1276,6 +1276,7 @@ struct sched_dl_entity {
 	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,

@@ -2168,6 +2169,13 @@ int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
+extern unsigned int sysctl_sched_dl_period;
+extern int sysctl_sched_dl_runtime;
+
+int sched_dl_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
 #ifdef CONFIG_SCHED_AUTOGROUP
 extern unsigned int sysctl_sched_autogroup_enabled;
 

530 lines not on this page · raw message

87 lines not on this page · raw message

118 lines not on this page · raw message

index 4ab1187..778140f 100644
@@ -352,6 +352,20 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rt_handler,
 	},
+	{
+		.procname	= "sched_dl_period_us",
+		.data		= &sysctl_sched_dl_period,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sched_dl_handler,
+	},
+	{
+		.procname	= "sched_dl_runtime_us",
+		.data		= &sysctl_sched_dl_runtime,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= sched_dl_handler,
+	},
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",

index 23cfcc3..85451e9 100644
@@ -6106,6 +6106,7 @@ static void free_rootdomain(struct rcu_head *rcu)
 	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
+	cpudl_cleanup(&rd->cpudl);
 	free_cpumask_var(rd->dlo_mask);
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);

@@ -6164,6 +6165,8 @@ static int init_rootdomain(struct root_domain *rd)
 		goto free_dlo_mask;
 
 	init_dl_bw(&rd->dl_bw);
+	if (cpudl_init(&rd->cpudl) != 0)
+		goto free_dlo_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;

208 lines not on this page · raw message

new file mode 100644
index 0000000..7f93e64
@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID     -1
+
+struct array_item {
+	u64 dl;
+	int cpu;
+};
+
+struct cpudl {
+	raw_spinlock_t lock;
+	int size;
+	int cpu_to_idx[NR_CPUS];
+	struct array_item elements[NR_CPUS];
+	cpumask_var_t free_cpus;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct cpumask *dlo_mask,
+		struct task_struct *p, struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */

112 lines not on this page · raw message

index d32b7b6..6e32ddd 100644
@@ -5,6 +5,7 @@
 #include <linux/stop_machine.h>
 
 #include "cpupri.h"
+#include "cpudl.h"
 
 extern __read_mostly int scheduler_running;
 

@@ -444,6 +445,7 @@ struct root_domain {
 	cpumask_var_t dlo_mask;
 	atomic_t dlo_count;
 	struct dl_bw dl_bw;
+	struct cpudl cpudl;
 
 	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than

index 941a83a..3e28ed3 100644
@@ -346,7 +346,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  * disrupting the schedulability of the system. Otherwise, we should
  * refill the runtime and set the deadline a period in the future,
  * because keeping the current (absolute) deadline of the task would
- * result in breaking guarantees promised to other tasks.
+ * result in breaking guarantees promised to other tasks (refer to
+ * Documentation/scheduler/sched-deadline.txt for more informations).
  *
  * This function returns true if:
  *