sched: high-res preemption tick

Use HR-timers (when available) to deliver an accurate preemption tick.

The regular scheduler tick that runs at 1/HZ can be too coarse when nice
level are used. The fairness system will still keep the cpu utilisation 'fair'
by then delaying the task that got an excessive amount of CPU time but try to
minimize this by delivering preemption points spot-on.

The average frequency of this extra interrupt is sched_latency / nr_latency.
Which need not be higher than 1/HZ, its just that the distribution within the
sched_latency period is important.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 18 insertions, 1 deletions

diff --git a/include/asm-x86/thread_info_32.h b/include/asm-x86/thread_info_32.h
index 22a8cbcd35e2..ef58fd2a6eb0 100644
--- a/include/asm-x86/thread_info_32.h
+++ b/include/asm-x86/thread_info_32.h
@@ -132,6 +132,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	6	/* syscall auditing active */
 #define TIF_SECCOMP		7	/* secure computing */
 #define TIF_RESTORE_SIGMASK	8	/* restore signal mask in do_signal() */
+#define TIF_HRTICK_RESCHED	9	/* reprogram hrtick timer */
 #define TIF_MEMDIE		16
 #define TIF_DEBUG		17	/* uses debug registers */
 #define TIF_IO_BITMAP		18	/* uses I/O bitmap */
@@ -147,6 +148,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_HRTICK_RESCHED	(1<<TIF_HRTICK_RESCHED)
 #define _TIF_DEBUG		(1<<TIF_DEBUG)
 #define _TIF_IO_BITMAP		(1<<TIF_IO_BITMAP)
 #define _TIF_FREEZE		(1<<TIF_FREEZE)
diff --git a/include/asm-x86/thread_info_64.h b/include/asm-x86/thread_info_64.h
index beae2bfb62ca..7f6ee68f0002 100644
--- a/include/asm-x86/thread_info_64.h
+++ b/include/asm-x86/thread_info_64.h
@@ -115,6 +115,7 @@ static inline struct thread_info *stack_thread_info(void)
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
+#define TIF_HRTICK_RESCHED	11	/* reprogram hrtick timer */
 /* 16 free */
 #define TIF_IA32		17	/* 32bit process */ 
 #define TIF_FORK		18	/* ret_from_fork */
@@ -133,6 +134,7 @@ static inline struct thread_info *stack_thread_info(void)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_MCE_NOTIFY		(1<<TIF_MCE_NOTIFY)
+#define _TIF_HRTICK_RESCHED	(1<<TIF_HRTICK_RESCHED)
 #define _TIF_IA32		(1<<TIF_IA32)
 #define _TIF_FORK		(1<<TIF_FORK)
 #define _TIF_ABI_PENDING	(1<<TIF_ABI_PENDING)
@@ -146,6 +148,9 @@ static inline struct thread_info *stack_thread_info(void)
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
 
+#define _TIF_DO_NOTIFY_MASK \
+	(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
+
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW (_TIF_DEBUG|_TIF_IO_BITMAP)
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 7a9398e19704..ecc8e2685e2b 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -217,6 +217,11 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 	return timer->base->get_time();
 }
 
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+	return timer->base->cpu_base->hres_active;
+}
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -248,6 +253,10 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 	return timer->base->softirq_time;
 }
 
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+	return 0;
+}
 #endif
 
 extern ktime_t ktime_get(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7907845c2348..43e0339d65fc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -257,6 +257,7 @@ extern void trap_init(void);
 extern void account_process_tick(struct task_struct *task, int user);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
+extern void hrtick_resched(void);
 
 extern void sched_show_task(struct task_struct *p);
 
@@ -849,7 +850,7 @@ struct sched_class {
 #endif
 
 	void (*set_curr_task) (struct rq *rq);
-	void (*task_tick) (struct rq *rq, struct task_struct *p);
+	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_new) (struct rq *rq, struct task_struct *p);
 	void (*set_cpus_allowed)(struct task_struct *p, cpumask_t *newmask);