Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (26 commits)
  posix timers: fix RLIMIT_CPU && fork()
  time: ntp: fix bug in ntp_update_offset() & do_adjtimex(), fix
  time: ntp: clean up second_overflow()
  time: ntp: simplify ntp_tick_adj calculations
  time: ntp: make 64-bit constants more robust
  time: ntp: refactor do_adjtimex() some more
  time: ntp: refactor do_adjtimex()
  time: ntp: fix bug in ntp_update_offset() & do_adjtimex()
  time: ntp: micro-optimize ntp_update_offset()
  time: ntp: simplify ntp_update_offset_fll()
  time: ntp: refactor and clean up ntp_update_offset()
  time: ntp: refactor up ntp_update_frequency()
  time: ntp: clean up ntp_update_frequency()
  time: ntp: simplify the MAX_TICKADJ_SCALED definition
  time: ntp: simplify the second_overflow() code flow
  time: ntp: clean up kernel/time/ntp.c
  x86: hpet: stop HPET_COUNTER when programming periodic mode
  x86: hpet: provide separate functions to stop and start the counter
  x86: hpet: print HPET registers during setup (if hpet=verbose is used)
  time: apply NTP frequency/tick changes immediately
  ...

Documentation/kernel-parameters.txt

@@ -493,10 +493,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			Default: 64
 
 	hpet=		[X86-32,HPET] option to control HPET usage
-			Format: { enable (default) | disable | force }
+			Format: { enable (default) | disable | force |
+				verbose }
 			disable: disable HPET and use PIT instead
 			force: allow force enabled of undocumented chips (ICH4,
 			VIA, nVidia)
+			verbose: show contents of HPET registers during setup
 
 	com20020=	[HW,NET] ARCnet - COM20020 chipset
 			Format:

arch/powerpc/platforms/cell/spufs/sched.c

@@ -508,7 +508,7 @@ static void __spu_add_to_rq(struct spu_context *ctx)
 		list_add_tail(&ctx->rq, &spu_prio->runq[ctx->prio]);
 		set_bit(ctx->prio, spu_prio->bitmap);
 		if (!spu_prio->nr_waiting++)
-			__mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK);
+			mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK);
 	}
 }
 

arch/x86/kernel/hpet.c

@@ -80,6 +80,7 @@ static inline void hpet_clear_mapping(void)
  */
 static int boot_hpet_disable;
 int hpet_force_user;
+static int hpet_verbose;
 
 static int __init hpet_setup(char *str)
 {
@@ -88,6 +89,8 @@ static int __init hpet_setup(char *str)
 			boot_hpet_disable = 1;
 		if (!strncmp("force", str, 5))
 			hpet_force_user = 1;
+		if (!strncmp("verbose", str, 7))
+			hpet_verbose = 1;
 	}
 	return 1;
 }
@@ -119,6 +122,43 @@ int is_hpet_enabled(void)
 }
 EXPORT_SYMBOL_GPL(is_hpet_enabled);
 
+static void _hpet_print_config(const char *function, int line)
+{
+	u32 i, timers, l, h;
+	printk(KERN_INFO "hpet: %s(%d):\n", function, line);
+	l = hpet_readl(HPET_ID);
+	h = hpet_readl(HPET_PERIOD);
+	timers = ((l & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
+	printk(KERN_INFO "hpet: ID: 0x%x, PERIOD: 0x%x\n", l, h);
+	l = hpet_readl(HPET_CFG);
+	h = hpet_readl(HPET_STATUS);
+	printk(KERN_INFO "hpet: CFG: 0x%x, STATUS: 0x%x\n", l, h);
+	l = hpet_readl(HPET_COUNTER);
+	h = hpet_readl(HPET_COUNTER+4);
+	printk(KERN_INFO "hpet: COUNTER_l: 0x%x, COUNTER_h: 0x%x\n", l, h);
+
+	for (i = 0; i < timers; i++) {
+		l = hpet_readl(HPET_Tn_CFG(i));
+		h = hpet_readl(HPET_Tn_CFG(i)+4);
+		printk(KERN_INFO "hpet: T%d: CFG_l: 0x%x, CFG_h: 0x%x\n",
+		       i, l, h);
+		l = hpet_readl(HPET_Tn_CMP(i));
+		h = hpet_readl(HPET_Tn_CMP(i)+4);
+		printk(KERN_INFO "hpet: T%d: CMP_l: 0x%x, CMP_h: 0x%x\n",
+		       i, l, h);
+		l = hpet_readl(HPET_Tn_ROUTE(i));
+		h = hpet_readl(HPET_Tn_ROUTE(i)+4);
+		printk(KERN_INFO "hpet: T%d ROUTE_l: 0x%x, ROUTE_h: 0x%x\n",
+		       i, l, h);
+	}
+}
+
+#define hpet_print_config()					\
+do {								\
+	if (hpet_verbose)					\
+		_hpet_print_config(__FUNCTION__, __LINE__);	\
+} while (0)
+
 /*
  * When the hpet driver (/dev/hpet) is enabled, we need to reserve
  * timer 0 and timer 1 in case of RTC emulation.
@@ -191,27 +231,37 @@ static struct clock_event_device hpet_clockevent = {
 	.rating		= 50,
 };
 
-static void hpet_start_counter(void)
+static void hpet_stop_counter(void)
 {
 	unsigned long cfg = hpet_readl(HPET_CFG);
-
 	cfg &= ~HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 	hpet_writel(0, HPET_COUNTER);
 	hpet_writel(0, HPET_COUNTER + 4);
+}
+
+static void hpet_start_counter(void)
+{
+	unsigned long cfg = hpet_readl(HPET_CFG);
 	cfg |= HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 }
 
+static void hpet_restart_counter(void)
+{
+	hpet_stop_counter();
+	hpet_start_counter();
+}
+
 static void hpet_resume_device(void)
 {
 	force_hpet_resume();
 }
 
-static void hpet_restart_counter(void)
+static void hpet_resume_counter(void)
 {
 	hpet_resume_device();
-	hpet_start_counter();
+	hpet_restart_counter();
 }
 
 static void hpet_enable_legacy_int(void)
@@ -259,29 +309,23 @@ static int hpet_setup_msi_irq(unsigned int irq);
 static void hpet_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt, int timer)
 {
-	unsigned long cfg, cmp, now;
+	unsigned long cfg;
 	uint64_t delta;
 
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
+		hpet_stop_counter();
 		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
 		delta >>= evt->shift;
-		now = hpet_readl(HPET_COUNTER);
-		cmp = now + (unsigned long) delta;
 		cfg = hpet_readl(HPET_Tn_CFG(timer));
 		/* Make sure we use edge triggered interrupts */
 		cfg &= ~HPET_TN_LEVEL;
 		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
 		       HPET_TN_SETVAL | HPET_TN_32BIT;
 		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		/*
-		 * The first write after writing TN_SETVAL to the
-		 * config register sets the counter value, the second
-		 * write sets the period.
-		 */
-		hpet_writel(cmp, HPET_Tn_CMP(timer));
-		udelay(1);
 		hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
+		hpet_start_counter();
+		hpet_print_config();
 		break;
 
 	case CLOCK_EVT_MODE_ONESHOT:
@@ -308,6 +352,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 			irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 			enable_irq(hdev->irq);
 		}
+		hpet_print_config();
 		break;
 	}
 }
@@ -526,6 +571,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 
 	num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT);
 	num_timers++; /* Value read out starts from 0 */
+	hpet_print_config();
 
 	hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
 	if (!hpet_devs)
@@ -695,7 +741,7 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.shift		= HPET_SHIFT,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-	.resume		= hpet_restart_counter,
+	.resume		= hpet_resume_counter,
 #ifdef CONFIG_X86_64
 	.vread		= vread_hpet,
 #endif
@@ -707,7 +753,7 @@ static int hpet_clocksource_register(void)
 	cycle_t t1;
 
 	/* Start the counter */
-	hpet_start_counter();
+	hpet_restart_counter();
 
 	/* Verify whether hpet counter works */
 	t1 = read_hpet();
@@ -793,6 +839,7 @@ int __init hpet_enable(void)
 	 * information and the number of channels
 	 */
 	id = hpet_readl(HPET_ID);
+	hpet_print_config();
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 	/*
@@ -845,6 +892,7 @@ static __init int hpet_late_init(void)
 		return -ENODEV;
 
 	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
+	hpet_print_config();
 
 	for_each_online_cpu(cpu) {
 		hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);

arch/x86/kernel/quirks.c

@@ -172,7 +172,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_4,
 			 ich_force_enable_hpet);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7,
 			 ich_force_enable_hpet);
-
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3a16,	/* ICH10 */
+			 ich_force_enable_hpet);
 
 static struct pci_dev *cached_dev;
 

drivers/infiniband/hw/ipath/ipath_driver.c

@@ -2715,7 +2715,7 @@ static void ipath_hol_signal_up(struct ipath_devdata *dd)
  * to prevent HoL blocking, then start the HoL timer that
  * periodically continues, then stop procs, so they can detect
  * link down if they want, and do something about it.
- * Timer may already be running, so use __mod_timer, not add_timer.
+ * Timer may already be running, so use mod_timer, not add_timer.
  */
 void ipath_hol_down(struct ipath_devdata *dd)
 {
@@ -2724,7 +2724,7 @@ void ipath_hol_down(struct ipath_devdata *dd)
 	dd->ipath_hol_next = IPATH_HOL_DOWNCONT;
 	dd->ipath_hol_timer.expires = jiffies +
 		msecs_to_jiffies(ipath_hol_timeout_ms);
-	__mod_timer(&dd->ipath_hol_timer, dd->ipath_hol_timer.expires);
+	mod_timer(&dd->ipath_hol_timer, dd->ipath_hol_timer.expires);
 }
 
 /*
@@ -2763,7 +2763,7 @@ void ipath_hol_event(unsigned long opaque)
 	else {
 		dd->ipath_hol_timer.expires = jiffies +
 			msecs_to_jiffies(ipath_hol_timeout_ms);
-		__mod_timer(&dd->ipath_hol_timer,
+		mod_timer(&dd->ipath_hol_timer,
 			dd->ipath_hol_timer.expires);
 	}
 }

include/linux/timer.h

@@ -86,8 +86,8 @@ static inline int timer_pending(const struct timer_list * timer)
 
 extern void add_timer_on(struct timer_list *timer, int cpu);
 extern int del_timer(struct timer_list * timer);
-extern int __mod_timer(struct timer_list *timer, unsigned long expires);
 extern int mod_timer(struct timer_list *timer, unsigned long expires);
+extern int mod_timer_pending(struct timer_list *timer, unsigned long expires);
 
 /*
  * The jiffies value which is added to now, when there is no timer
@@ -146,25 +146,7 @@ static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
 }
 #endif
 
-/**
- * add_timer - start a timer
- * @timer: the timer to be added
- *
- * The kernel will do a ->function(->data) callback from the
- * timer interrupt at the ->expires point in the future. The
- * current time is 'jiffies'.
- *
- * The timer's ->expires, ->function (and if the handler uses it, ->data)
- * fields must be set prior calling this function.
- *
- * Timers with an ->expires field in the past will be executed in the next
- * timer tick.
- */
-static inline void add_timer(struct timer_list *timer)
-{
-	BUG_ON(timer_pending(timer));
-	__mod_timer(timer, timer->expires);
-}
+extern void add_timer(struct timer_list *timer);
 
 #ifdef CONFIG_SMP
   extern int try_to_del_timer_sync(struct timer_list *timer);

include/linux/timex.h

@@ -190,7 +190,7 @@ struct timex {
  * offset and maximum frequency tolerance.
  */
 #define SHIFT_USEC 16		/* frequency offset scale (shift) */
-#define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
+#define PPM_SCALE ((s64)NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
 #define PPM_SCALE_INV_SHIFT 19
 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \
 		       PPM_SCALE + 1)

kernel/posix-cpu-timers.c

@@ -1370,7 +1370,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
 	}
-	return 0;
+
+	return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
 }
 
 /*

kernel/relay.c

@@ -750,7 +750,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 			 * from the scheduler (trying to re-grab
 			 * rq->lock), so defer it.
 			 */
-			__mod_timer(&buf->timer, jiffies + 1);
+			mod_timer(&buf->timer, jiffies + 1);
 	}
 
 	old = buf->data;

kernel/time/clockevents.c

@@ -68,6 +68,17 @@ void clockevents_set_mode(struct clock_event_device *dev,
 	if (dev->mode != mode) {
 		dev->set_mode(mode, dev);
 		dev->mode = mode;
+
+		/*
+		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
+		 * on it, so fix it up and emit a warning:
+		 */
+		if (mode == CLOCK_EVT_MODE_ONESHOT) {
+			if (unlikely(!dev->mult)) {
+				dev->mult = 1;
+				WARN_ON(1);
+			}
+		}
 	}
 }
 
@@ -168,15 +179,6 @@ void clockevents_register_device(struct clock_event_device *dev)
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 	BUG_ON(!dev->cpumask);
 
-	/*
-	 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
-	 * on it, so fix it up and emit a warning:
-	 */
-	if (unlikely(!dev->mult)) {
-		dev->mult = 1;
-		WARN_ON(1);
-	}
-
 	spin_lock(&clockevents_lock);
 
 	list_add(&dev->list, &clockevent_devices);

kernel/timer.c

@@ -589,11 +589,14 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
 	}
 }
 
-int __mod_timer(struct timer_list *timer, unsigned long expires)
+static inline int
+__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 {
 	struct tvec_base *base, *new_base;
 	unsigned long flags;
-	int ret = 0;
+	int ret;
+
+	ret = 0;
 
 	timer_stats_timer_set_start_info(timer);
 	BUG_ON(!timer->function);
@@ -603,6 +606,9 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer_pending(timer)) {
 		detach_timer(timer, 0);
 		ret = 1;
+	} else {
+		if (pending_only)
+			goto out_unlock;
 	}
 
 	debug_timer_activate(timer);
@@ -629,42 +635,28 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 
 	timer->expires = expires;
 	internal_add_timer(base, timer);
+
+out_unlock:
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
 }
 
-EXPORT_SYMBOL(__mod_timer);
-
 /**
- * add_timer_on - start a timer on a particular CPU
- * @timer: the timer to be added
- * @cpu: the CPU to start it on
+ * mod_timer_pending - modify a pending timer's timeout
+ * @timer: the pending timer to be modified
+ * @expires: new timeout in jiffies
  *
- * This is not very scalable on SMP. Double adds are not possible.
+ * mod_timer_pending() is the same for pending timers as mod_timer(),
+ * but will not re-activate and modify already deleted timers.
+ *
+ * It is useful for unserialized use of timers.
  */
-void add_timer_on(struct timer_list *timer, int cpu)
+int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-	struct tvec_base *base = per_cpu(tvec_bases, cpu);
-	unsigned long flags;
-
-	timer_stats_timer_set_start_info(timer);
-	BUG_ON(timer_pending(timer) || !timer->function);
-	spin_lock_irqsave(&base->lock, flags);
-	timer_set_base(timer, base);
-	debug_timer_activate(timer);
-	internal_add_timer(base, timer);
-	/*
-	 * Check whether the other CPU is idle and needs to be
-	 * triggered to reevaluate the timer wheel when nohz is
-	 * active. We are protected against the other CPU fiddling
-	 * with the timer by holding the timer base lock. This also
-	 * makes sure that a CPU on the way to idle can not evaluate
-	 * the timer wheel.
-	 */
-	wake_up_idle_cpu(cpu);
-	spin_unlock_irqrestore(&base->lock, flags);
+	return __mod_timer(timer, expires, true);
 }
+EXPORT_SYMBOL(mod_timer_pending);
 
 /**
  * mod_timer - modify a timer's timeout
@@ -688,9 +680,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-	BUG_ON(!timer->function);
-
-	timer_stats_timer_set_start_info(timer);
 	/*
 	 * This is a common optimization triggered by the
 	 * networking code - if the timer is re-modified
@@ -699,11 +688,61 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer->expires == expires && timer_pending(timer))
 		return 1;
 
-	return __mod_timer(timer, expires);
+	return __mod_timer(timer, expires, false);
 }
-
 EXPORT_SYMBOL(mod_timer);
 
+/**
+ * add_timer - start a timer
+ * @timer: the timer to be added
+ *
+ * The kernel will do a ->function(->data) callback from the
+ * timer interrupt at the ->expires point in the future. The
+ * current time is 'jiffies'.
+ *
+ * The timer's ->expires, ->function (and if the handler uses it, ->data)
+ * fields must be set prior calling this function.
+ *
+ * Timers with an ->expires field in the past will be executed in the next
+ * timer tick.
+ */
+void add_timer(struct timer_list *timer)
+{
+	BUG_ON(timer_pending(timer));
+	mod_timer(timer, timer->expires);
+}
+EXPORT_SYMBOL(add_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+	struct tvec_base *base = per_cpu(tvec_bases, cpu);
+	unsigned long flags;
+
+	timer_stats_timer_set_start_info(timer);
+	BUG_ON(timer_pending(timer) || !timer->function);
+	spin_lock_irqsave(&base->lock, flags);
+	timer_set_base(timer, base);
+	debug_timer_activate(timer);
+	internal_add_timer(base, timer);
+	/*
+	 * Check whether the other CPU is idle and needs to be
+	 * triggered to reevaluate the timer wheel when nohz is
+	 * active. We are protected against the other CPU fiddling
+	 * with the timer by holding the timer base lock. This also
+	 * makes sure that a CPU on the way to idle can not evaluate
+	 * the timer wheel.
+	 */
+	wake_up_idle_cpu(cpu);
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+
 /**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
@@ -733,7 +772,6 @@ int del_timer(struct timer_list *timer)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
@@ -767,7 +805,6 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 /**
@@ -796,7 +833,6 @@ int del_timer_sync(struct timer_list *timer)
 		cpu_relax();
 	}
 }
-
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
@@ -1268,7 +1304,7 @@ signed long __sched schedule_timeout(signed long timeout)
 	expire = timeout + jiffies;
 
 	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-	__mod_timer(&timer, expire);
+	__mod_timer(&timer, expire, false);
 	schedule();
 	del_singleshot_timer_sync(&timer);