sched/deadline: Add SCHED_DEADLINE structures & implementation

Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.

Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.

Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.

The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.

The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.

To summarize, this patch:
 - introduces the data structures, constants and symbols needed;
 - implements the core logic of the scheduling algorithm in the new
   scheduling class file;
 - provides all the glue code between the new scheduling class and
   the core scheduler and refines the interactions between sched/dl
   and the other existing scheduling classes.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -97,6 +97,10 @@ struct sched_param {
  * 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;
@@ -1088,6 +1092,45 @@ struct sched_rt_entity {
 #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	*/
+
+	/*
+	 * 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;
+};
 
 struct rcu_node;
 
@@ -1124,6 +1167,7 @@ struct task_struct {
 #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: */
@@ -2099,7 +2143,7 @@ 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(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);

include/linux/sched/deadline.h

@@ -0,0 +1,24 @@
+#ifndef _SCHED_DEADLINE_H
+#define _SCHED_DEADLINE_H
+
+/*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+ * NORMAL/BATCH tasks.
+ */
+
+#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);
+}
+
+#endif /* _SCHED_DEADLINE_H */

include/uapi/linux/sched.h

@@ -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
 

kernel/fork.c

@@ -1311,7 +1311,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(clone_flags, p);
+	retval = sched_fork(clone_flags, p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
 
 	retval = perf_event_init_task(p);
 	if (retval)

kernel/hrtimer.c

@@ -46,6 +46,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
@@ -1610,7 +1611,7 @@ 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);

kernel/sched/Makefile

@@ -11,7 +11,8 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o completion.o
 obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o