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 <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
amarioguy · Jan 25, 2008 · 8f4d37e · 8f4d37e
1 parent 02b67cc
commit 8f4d37e
Show file tree

Hide file tree

Showing 12 changed files with 295 additions and 21 deletions.
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
@@ -283,7 +283,7 @@ sysret_careful:
 sysret_signal:
 	TRACE_IRQS_ON
 	sti
-	testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
+	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz    1f
 
 	/* Really a signal */
@@ -377,7 +377,7 @@ int_very_careful:
 	jmp int_restore_rest
 
 int_signal:
-	testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
+	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz 1f
 	movq %rsp,%rdi		# &ptregs -> arg1
 	xorl %esi,%esi		# oldset -> arg2
@@ -603,7 +603,7 @@ retint_careful:
 	jmp retint_check
 
 retint_signal:
-	testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
+	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz    retint_swapgs
 	TRACE_IRQS_ON
 	sti

diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
@@ -658,6 +658,9 @@ void do_notify_resume(struct pt_regs *regs, void *_unused,
 	/* deal with pending signal delivery */
 	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
 		do_signal(regs);
+
+	if (thread_info_flags & _TIF_HRTICK_RESCHED)
+		hrtick_resched();
 
 	clear_thread_flag(TIF_IRET);
 }
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
@@ -480,6 +480,9 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 	/* deal with pending signal delivery */
 	if (thread_info_flags & (_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK))
 		do_signal(regs);
+
+	if (thread_info_flags & _TIF_HRTICK_RESCHED)
+		hrtick_resched();
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)

diff --git 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
@@ -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
@@ -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
@@ -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);
 

diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
@@ -54,3 +54,5 @@ config HZ
 	default 300 if HZ_300
 	default 1000 if HZ_1000
 
+config SCHED_HRTICK
+	def_bool HIGH_RES_TIMERS && X86