i386 No Idle Hz - aka Dynticks v051125-1

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/apic.c
===================================================================
@@ -26,6 +26,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
 #include <linux/cpu.h>
+#include <linux/dyn-tick.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>

@@ -932,6 +933,9 @@ void (*wait_timer_tick)(void) __devinitd
 
 #define APIC_DIVISOR 16
 
+static u32 apic_timer_val __read_mostly;
+#define APIC_TIMER_VAL	((apic_timer_val) / (HZ))
+
 static void __setup_APIC_LVTT(unsigned int clocks)
 {
 	unsigned int lvtt_value, tmp_value, ver;

@@ -950,7 +954,9 @@ static void __setup_APIC_LVTT(unsigned i
 				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
 				| APIC_TDR_DIV_16);
 
-	apic_write_around(APIC_TMICT, clocks/APIC_DIVISOR);
+	apic_timer_val = clocks * HZ / APIC_DIVISOR;
+
+	apic_write_around(APIC_TMICT, APIC_TIMER_VAL);
 }
 
 static void __devinit setup_APIC_timer(unsigned int clocks)

@@ -969,6 +975,17 @@ static void __devinit setup_APIC_timer(u
 	local_irq_restore(flags);
 }
 
+/* Used by NO_IDLE_HZ to skip ticks on idle CPUs */
+void reprogram_apic_timer(unsigned long count)
+{
+	unsigned long flags;
+
+	count = count * apic_timer_val / HZ;
+	local_irq_save(flags);
+	apic_write_around(APIC_TMICT, count);
+	local_irq_restore(flags);
+}
+
 /*
  * In this function we calibrate APIC bus clocks to the external
  * timer. Unfortunately we cannot use jiffies and the timer irq

@@ -1064,6 +1081,9 @@ void __init setup_boot_APIC_clock(void)
 	 */
 	setup_APIC_timer(calibration_result);
 
+	setup_dyn_tick_use_apic(calibration_result);
+	set_dyn_tick_max_skip((0xFFFFFFFF / calibration_result) * APIC_DIVISOR);
+
 	local_irq_restore(flags);
 }
 

@@ -1202,6 +1222,9 @@ fastcall void smp_apic_timer_interrupt(s
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
 	irq_enter();
+
+	dyn_tick_interrupt(regs);
+
 	smp_local_timer_interrupt(regs);
 	irq_exit();
 }

@@ -1214,6 +1237,9 @@ fastcall void smp_spurious_interrupt(str
 	unsigned long v;
 
 	irq_enter();
+
+	dyn_tick_interrupt(regs);
+
 	/*
 	 * Check if this really is a spurious interrupt and ACK it
 	 * if it is a vectored one.  Just in case...

@@ -1238,6 +1264,9 @@ fastcall void smp_error_interrupt(struct
 	unsigned long v, v1;
 
 	irq_enter();
+
+	dyn_tick_interrupt(regs);
+
 	/* First tickle the hardware, only then report what went on. -- REW */
 	v = apic_read(APIC_ESR);
 	apic_write(APIC_ESR, 0);

144 lines not on this page · raw message

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/io_apic.c
===================================================================
@@ -32,6 +32,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/sysdev.h>
+#include <linux/dyn-tick.h>
 
 #include <asm/io.h>
 #include <asm/smp.h>

@@ -1179,6 +1180,7 @@ next:
 
 static struct hw_interrupt_type ioapic_level_type;
 static struct hw_interrupt_type ioapic_edge_type;
+static struct hw_interrupt_type ioapic_edge_type_irq0;
 
 #define IOAPIC_AUTO	-1
 #define IOAPIC_EDGE	0

@@ -1190,15 +1192,19 @@ static inline void ioapic_register_intr(
 		if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 				trigger == IOAPIC_LEVEL)
 			irq_desc[vector].handler = &ioapic_level_type;
-		else
+		else if (vector)
 			irq_desc[vector].handler = &ioapic_edge_type;
+		else
+			irq_desc[vector].handler = &ioapic_edge_type_irq0;
 		set_intr_gate(vector, interrupt[vector]);
 	} else	{
 		if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 				trigger == IOAPIC_LEVEL)
 			irq_desc[irq].handler = &ioapic_level_type;
-		else
+		else if (irq)
 			irq_desc[irq].handler = &ioapic_edge_type;
+		else
+			irq_desc[irq].handler = &ioapic_edge_type_irq0;
 		set_intr_gate(vector, interrupt[irq]);
 	}
 }

@@ -1311,7 +1317,7 @@ static void __init setup_ExtINT_IRQ0_pin
 	 * The timer IRQ doesn't have to know that behind the
 	 * scene we have a 8259A-master in AEOI mode ...
 	 */
-	irq_desc[0].handler = &ioapic_edge_type;
+	irq_desc[0].handler = &ioapic_edge_type_irq0;
 
 	/*
 	 * Add it to the IO-APIC irq-routing table:

@@ -2088,6 +2094,20 @@ static struct hw_interrupt_type ioapic_l
 #endif
 };
 
+/* Needed to disable PIT interrupts when all CPUs sleep */
+static struct hw_interrupt_type ioapic_edge_type_irq0 __read_mostly = {
+	.typename 	= "IO-APIC-edge-irq0",
+	.startup 	= startup_edge_ioapic,
+	.shutdown 	= shutdown_edge_ioapic,
+	.enable 	= unmask_IO_APIC_irq,
+	.disable 	= mask_IO_APIC_irq,
+	.ack 		= ack_edge_ioapic,
+	.end 		= end_edge_ioapic,
+#ifdef CONFIG_SMP
+	.set_affinity 	= set_ioapic_affinity,
+#endif
+};
+
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/irq.c
===================================================================
@@ -18,6 +18,7 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
+#include <linux/dyn-tick.h>
 
 DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp;
 EXPORT_PER_CPU_SYMBOL(irq_stat);

@@ -76,6 +77,8 @@ fastcall unsigned int do_IRQ(struct pt_r
 	}
 #endif
 
+	dyn_tick_interrupt(regs);
+
 #ifdef CONFIG_4KSTACKS
 
 	curctx = (union irq_ctx *) current_thread_info();

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/process.c
===================================================================
@@ -39,6 +39,7 @@
 #include <linux/ptrace.h>
 #include <linux/random.h>
 #include <linux/kprobes.h>
+#include <linux/dyn-tick.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>

@@ -193,6 +194,8 @@ void cpu_idle(void)
 			if (cpu_is_offline(cpu))
 				play_dead();
 
+			idle_reprogram_timer();
+
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
 			idle();
 		}

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/smp.c
===================================================================
@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
+#include <linux/dyn-tick.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>

@@ -313,6 +314,8 @@ fastcall void smp_invalidate_interrupt(s
 {
 	unsigned long cpu;
 
+	dyn_tick_interrupt(regs);
+
 	cpu = get_cpu();
 
 	if (!cpu_isset(cpu, flush_cpumask))

@@ -600,6 +603,8 @@ void smp_send_stop(void)
 fastcall void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
+
+	dyn_tick_interrupt(regs);
 }
 
 fastcall void smp_call_function_interrupt(struct pt_regs *regs)

@@ -609,6 +614,9 @@ fastcall void smp_call_function_interrup
 	int wait = call_data->wait;
 
 	ack_APIC_irq();
+
+	dyn_tick_interrupt(regs);
+
 	/*
 	 * Notify initiating CPU that I've grabbed the data and am
 	 * about to execute the function

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/time.c
===================================================================
@@ -46,6 +46,7 @@
 #include <linux/bcd.h>
 #include <linux/efi.h>
 #include <linux/mca.h>
+#include <linux/dyn-tick.h>
 
 #include <asm/io.h>
 #include <asm/smp.h>

@@ -245,7 +246,7 @@ EXPORT_SYMBOL(profile_pc);
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "do_timer()" routine every clocktick
  */
-static inline void do_timer_interrupt(int irq, struct pt_regs *regs)
+static inline void do_timer_interrupt(int irq, struct pt_regs *regs, int lost)
 {
 #ifdef CONFIG_X86_IO_APIC
 	if (timer_ack) {

@@ -263,7 +264,8 @@ static inline void do_timer_interrupt(in
 	}
 #endif
 
-	do_timer_interrupt_hook(regs);
+	if (!dyn_tick_enabled() || lost)
+		do_timer_interrupt_hook(regs);
 
 
 	if (MCA_bus) {

@@ -288,6 +290,8 @@ static inline void do_timer_interrupt(in
  */
 irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 {
+	int lost;
+
 	/*
 	 * Here we are in the timer irq handler. We just have irqs locally
 	 * disabled but we don't know if the timer_bh is running on the other

@@ -297,9 +301,9 @@ irqreturn_t timer_interrupt(int irq, voi
 	 */
 	write_seqlock(&xtime_lock);
 
-	cur_timer->mark_offset();
- 
-	do_timer_interrupt(irq, regs);
+	lost = cur_timer->mark_offset();
+
+	do_timer_interrupt(irq, regs, lost);
 
 	write_sequnlock(&xtime_lock);
 	return IRQ_HANDLED;

@@ -425,7 +429,7 @@ static struct sysdev_class timer_sysclas
 
 
 /* XXX this driverfs stuff should probably go elsewhere later -john */
-static struct sys_device device_timer = {
+struct sys_device device_timer = {
 	.id	= 0,
 	.cls	= &timer_sysclass,
 };

@@ -481,5 +485,7 @@ void __init time_init(void)
 	cur_timer = select_timer();
 	printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
 
+	dyn_tick_time_init(cur_timer);
+
 	time_init_hook();
 }

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/timers/timer_pit.c
===================================================================
@@ -32,9 +32,10 @@ static int __init init_pit(char* overrid
 	return 0;
 }
 
-static void mark_offset_pit(void)
+static int mark_offset_pit(void)
 {
 	/* nothing needed */
+	return 1;
 }
 
 static unsigned long long monotonic_clock_pit(void)

@@ -148,6 +149,38 @@ static unsigned long get_offset_pit(void
 	return count;
 }
 
+void disable_pit_timer(void)
+{
+	irq_desc[0].handler->disable(0);
+}
+
+void enable_pit_timer(void)
+{
+	irq_desc[0].handler->enable(0);
+}
+
+/*
+ * Reprograms the next timer interrupt
+ * PIT timer reprogramming code taken from APM code.
+ * Note that PIT timer is a 16-bit timer, which allows max
+ * skip of only few seconds.
+ */
+void reprogram_pit_timer(unsigned long jiffies_to_skip)
+{
+	int skip;
+	extern spinlock_t i8253_lock;
+	unsigned long flags;
+
+	skip = jiffies_to_skip * LATCH;
+	if (skip > 0xffff)
+		skip = 0xffff;
+
+	spin_lock_irqsave(&i8253_lock, flags);
+	outb_p(0x34, PIT_MODE);		/* binary, mode 2, LSB/MSB, ch 0 */
+	outb_p(skip & 0xff, PIT_CH0);	/* LSB */
+	outb(skip >> 8, PIT_CH0);	/* MSB */
+	spin_unlock_irqrestore(&i8253_lock, flags);
+}
 
 /* tsc timer_opts struct */
 struct timer_opts timer_pit = {

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/timers/timer_pm.c
===================================================================
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/init.h>
+#include <linux/dyn-tick.h>
 #include <asm/types.h>
 #include <asm/timer.h>
 #include <asm/smp.h>

@@ -28,7 +29,7 @@
 #define PMTMR_TICKS_PER_SEC 3579545
 #define PMTMR_EXPECTED_RATE \
   ((CALIBRATE_LATCH * (PMTMR_TICKS_PER_SEC >> 10)) / (CLOCK_TICK_RATE>>10))
-
+#define PMTMR_TICKS_PER_JIFFY (PMTMR_EXPECTED_RATE / (CALIBRATE_LATCH/LATCH))
 
 /* The I/O port the PMTMR resides at.
  * The location is detected during setup_arch(),

@@ -127,7 +128,13 @@ pm_good:
 	if (verify_pmtmr_rate() != 0)
 		return -ENODEV;
 
+	printk("Using %u PM timer ticks per jiffy \n", PMTMR_TICKS_PER_JIFFY);
+
+	offset_tick = read_pmtmr();
+	setup_pit_timer();
+
 	init_cpu_khz();
+	set_dyn_tick_max_skip(((0xFFFFFF / 1000000) * 286 * HZ) >> 10);
 	return 0;
 }
 

@@ -148,10 +155,9 @@ static inline u32 cyc2us(u32 cycles)
  * this gets called during each timer interrupt
  *   - Called while holding the writer xtime_lock
  */
-static void mark_offset_pmtmr(void)
+static int mark_offset_pmtmr(void)
 {
 	u32 lost, delta, last_offset;
-	static int first_run = 1;
 	last_offset = offset_tick;
 
 	write_seqlock(&monotonic_lock);

@@ -161,29 +167,20 @@ static void mark_offset_pmtmr(void)
 	/* calculate tick interval */
 	delta = (offset_tick - last_offset) & ACPI_PM_MASK;
 
-	/* convert to usecs */
-	delta = cyc2us(delta);
-
 	/* update the monotonic base value */
-	monotonic_base += delta * NSEC_PER_USEC;
+	monotonic_base += cyc2us(delta) * NSEC_PER_USEC;
 	write_sequnlock(&monotonic_lock);
 
 	/* convert to ticks */
 	delta += offset_delay;
-	lost = delta / (USEC_PER_SEC / HZ);
-	offset_delay = delta % (USEC_PER_SEC / HZ);
-
+	lost = delta / PMTMR_TICKS_PER_JIFFY;
+	offset_delay = delta % PMTMR_TICKS_PER_JIFFY;
 
 	/* compensate for lost ticks */
 	if (lost >= 2)
 		jiffies_64 += lost - 1;
 
-	/* don't calculate delay for first run,
-	   or if we've got less then a tick */
-	if (first_run || (lost < 1)) {
-		first_run = 0;
-		offset_delay = 0;
-	}
+	return lost;
 }
 
 static int pmtmr_resume(void)

@@ -192,6 +189,7 @@ static int pmtmr_resume(void)
 	/* Assume this is the last mark offset time */
 	offset_tick = read_pmtmr();
 	write_sequnlock(&monotonic_lock);
+	offset_delay = 0;
 	return 0;
 }
 

@@ -243,7 +241,7 @@ static unsigned long get_offset_pmtmr(vo
 	now = read_pmtmr();
 	delta = (now - offset)&ACPI_PM_MASK;
 
-	return (unsigned long) offset_delay + cyc2us(delta);
+	return (unsigned long) cyc2us(delta + offset_delay);
 }
 
 

142 lines not on this page · raw message

Index: linux-2.6.15-rc2-dt/include/asm-i386/apic.h
===================================================================
@@ -121,6 +121,7 @@ extern void nmi_watchdog_tick (struct pt
 extern int APIC_init_uniprocessor (void);
 extern void disable_APIC_timer(void);
 extern void enable_APIC_timer(void);
+extern void reprogram_apic_timer(unsigned long count);
 
 extern void enable_NMI_through_LVT0 (void * dummy);
 

@@ -134,6 +135,7 @@ extern int disable_timer_pin_1;
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
+static inline void reprogram_apic_timer(unsigned long count) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 

67 lines not on this page · raw message

Index: linux-2.6.15-rc2-dt/include/asm-i386/timer.h
===================================================================
@@ -1,5 +1,6 @@
 #ifndef _ASMi386_TIMER_H
 #define _ASMi386_TIMER_H
+#include <linux/jiffies.h>
 #include <linux/init.h>
 #include <linux/pm.h>
 

@@ -19,7 +20,7 @@
  */
 struct timer_opts {
 	char* name;
-	void (*mark_offset)(void);
+	int (*mark_offset)(void);
 	unsigned long (*get_offset)(void);
 	unsigned long long (*monotonic_clock)(void);
 	void (*delay)(unsigned long);

@@ -38,6 +39,9 @@ struct init_timer_opts {
 extern struct timer_opts* __init select_timer(void);
 extern void clock_fallback(void);
 void setup_pit_timer(void);
+extern void disable_pit_timer(void);
+extern void enable_pit_timer(void);
+extern void reprogram_pit_timer(unsigned long jiffies_to_skip);
 
 /* Modifiers for buggy PIT handling */
 

@@ -67,4 +71,37 @@ extern unsigned long calibrate_tsc_hpet(
 #ifdef CONFIG_X86_PM_TIMER
 extern struct init_timer_opts timer_pmtmr_init;
 #endif
+#ifdef CONFIG_NO_IDLE_HZ
+static inline void tsc_sanity_check(int lost)
+{
+}
+#else /* CONFIG_NO_IDLE_HZ */
+extern void cpufreq_delayed_get(void);
+
+static inline void tsc_sanity_check(int lost)
+{
+	static int lost_count = 0;
+
+	if (lost >= 2) {
+		jiffies_64 += lost-1;
+
+		/* sanity check to ensure we're not always losing ticks */
+		if (lost_count++ > 100) {
+			printk(KERN_WARNING "Losing too many ticks!\n");
+			printk(KERN_WARNING "TSC cannot be used as a timesource.  \n");
+			printk(KERN_WARNING "Possible reasons for this are:\n");
+			printk(KERN_WARNING "  You're running with Speedstep,\n");
+			printk(KERN_WARNING "  You don't have DMA enabled for your hard disk (see hdparm),\n");
+			printk(KERN_WARNING "  Incorrect TSC synchronization on an SMP system (see dmesg).\n");
+			printk(KERN_WARNING "Falling back to a sane timesource now.\n");
+
+			clock_fallback();
+		}
+		/* ... but give the TSC a fair chance */
+		if (lost_count > 25)
+			cpufreq_delayed_get();
+	} else
+		lost_count = 0;
+}
+#endif /* CONFIG_NO_IDLE_HZ */
 #endif

68 lines not on this page · raw message

Index: linux-2.6.15-rc2-dt/include/linux/timer.h
===================================================================
@@ -97,5 +97,6 @@ static inline void add_timer(struct time
 extern void init_timers(void);
 extern void run_local_timers(void);
 extern void it_real_fn(unsigned long);
+extern void conditional_run_local_timers(void);
 
 #endif

208 lines not on this page · raw message

Index: linux-2.6.15-rc2-dt/kernel/timer.c
===================================================================
@@ -869,6 +869,13 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
+void conditional_run_local_timers(void)
+{
+	tvec_base_t *base  = &__get_cpu_var(tvec_bases);
+
+	if (base->timer_jiffies != jiffies)
+		run_local_timers();
+}
 /*
  * Called by the timer interrupt. xtime_lock must already be taken
  * by the timer IRQ!

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/timers/timer_cyclone.c
===================================================================
@@ -45,7 +45,7 @@ static seqlock_t monotonic_lock = SEQLOC
 	} while (high != cyclone_timer[1]);
 
 
-static void mark_offset_cyclone(void)
+static int mark_offset_cyclone(void)
 {
 	unsigned long lost, delay;
 	unsigned long delta = last_cyclone_low;

@@ -101,6 +101,8 @@ static void mark_offset_cyclone(void)
 	 */
 	if (lost && abs(delay - delay_at_last_interrupt) > (900000/HZ))
 		jiffies_64++;
+
+	return lost;
 }
 
 static unsigned long get_offset_cyclone(void)

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/timers/timer_hpet.c
===================================================================
@@ -101,7 +101,7 @@ static unsigned long get_offset_hpet(voi
 	return edx;
 }
 
-static void mark_offset_hpet(void)
+static int mark_offset_hpet(void)
 {
 	unsigned long long this_offset, last_offset;
 	unsigned long offset;

@@ -124,6 +124,8 @@ static void mark_offset_hpet(void)
 	this_offset = ((unsigned long long)last_tsc_high<<32)|last_tsc_low;
 	monotonic_base += cycles_2_ns(this_offset - last_offset);
 	write_sequnlock(&monotonic_lock);
+
+	return 1;
 }
 
 static void delay_hpet(unsigned long loops)

Index: linux-2.6.15-rc2-dt/arch/i386/kernel/timers/timer_none.c
===================================================================
@@ -1,9 +1,10 @@
 #include <linux/init.h>
 #include <asm/timer.h>
 
-static void mark_offset_none(void)
+static int mark_offset_none(void)
 {
 	/* nothing needed */
+	return 1;
 }
 
 static unsigned long get_offset_none(void)

Index: linux-2.6.15-rc2-dt/drivers/acpi/processor_idle.c
===================================================================
@@ -38,6 +38,7 @@
 #include <linux/dmi.h>
 #include <linux/moduleparam.h>
 #include <linux/sched.h>	/* need_resched() */
+#include <linux/dyn-tick.h>
 
 #include <asm/io.h>
 #include <asm/uaccess.h>

@@ -182,6 +183,17 @@ static void acpi_safe_halt(void)
 
 static atomic_t c3_cpu_count;
 
+static inline int skipped_since_bm_check(void)
+{
+	/*
+	 * If we've been skipping ticks in the last few ticks there wouldn't be
+	 * any busmaster activity.
+	 */
+	if (dyn_tick->last_skip + dyn_tick->skip >= jiffies)
+		return dyn_tick->skip;
+	return 0;
+}
+
 static void acpi_processor_idle(void)
 {
 	struct acpi_processor *pr = NULL;

@@ -227,6 +239,18 @@ static void acpi_processor_idle(void)
 	if (pr->flags.bm_check) {
 		u32 bm_status = 0;
 		unsigned long diff = jiffies - pr->power.bm_check_timestamp;
+		int skipped = 0;
+
+		if (dyn_tick_enabled()) {
+			skipped = skipped_since_bm_check();
+			if (skipped) {
+				diff = 0;
+				do {
+					if (!(pr->power.bm_activity >>= 1))
+						break;
+				} while (skipped--);
+			}
+		}
 
 		if (diff > 32)
 			diff = 32;

@@ -242,7 +266,8 @@ static void acpi_processor_idle(void)
 		acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS,
 				  &bm_status, ACPI_MTX_DO_NOT_LOCK);
 		if (bm_status) {
-			pr->power.bm_activity++;
+			if (!skipped)
+				pr->power.bm_activity++;
 			acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS,
 					  1, ACPI_MTX_DO_NOT_LOCK);
 		}