1 files changed, 89 insertions, 68 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index ce4cb772dc7..9fff9cdcc51 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -42,6 +42,7 @@
 #include <linux/timex.h>
 #include <linux/kernel_stat.h>
 #include <linux/time.h>
+#include <linux/clockchips.h>
 #include <linux/init.h>
 #include <linux/profile.h>
 #include <linux/cpu.h>
@@ -106,7 +107,7 @@ struct clock_event_device decrementer_clockevent = {
 	.irq            = 0,
 	.set_next_event = decrementer_set_next_event,
 	.set_mode       = decrementer_set_mode,
-	.features       = CLOCK_EVT_FEAT_ONESHOT,
+	.features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
 };
 EXPORT_SYMBOL(decrementer_clockevent);
 
@@ -143,7 +144,7 @@ EXPORT_SYMBOL_GPL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
 EXPORT_SYMBOL_GPL(ppc_tb_freq);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Factors for converting from cputime_t (timebase ticks) to
  * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds).
@@ -210,23 +211,23 @@ static u64 scan_dispatch_log(u64 stop_tb)
 	if (!dtl)
 		return 0;
 
-	if (i == vpa->dtl_idx)
+	if (i == be64_to_cpu(vpa->dtl_idx))
 		return 0;
-	while (i < vpa->dtl_idx) {
-		if (dtl_consumer)
-			dtl_consumer(dtl, i);
-		dtb = dtl->timebase;
-		tb_delta = dtl->enqueue_to_dispatch_time +
-			dtl->ready_to_enqueue_time;
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
+		dtb = be64_to_cpu(dtl->timebase);
+		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
+			be32_to_cpu(dtl->ready_to_enqueue_time);
 		barrier();
-		if (i + N_DISPATCH_LOG < vpa->dtl_idx) {
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
 			/* buffer has overflowed */
-			i = vpa->dtl_idx - N_DISPATCH_LOG;
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
 			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
 			continue;
 		}
 		if (dtb > stop_tb)
 			break;
+		if (dtl_consumer)
+			dtl_consumer(dtl, i);
 		stolen += tb_delta;
 		++i;
 		++dtl;
@@ -269,7 +270,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
 {
 	u64 stolen = 0;
 
-	if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) {
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
 		stolen = scan_dispatch_log(stop_tb);
 		get_paca()->system_time -= stolen;
 	}
@@ -297,6 +298,8 @@ static u64 vtime_delta(struct task_struct *tsk,
 	u64 now, nowscaled, deltascaled;
 	u64 udelta, delta, user_scaled;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	now = mftb();
 	nowscaled = read_spurr(now);
 	get_paca()->system_time += now - get_paca()->starttime;
@@ -345,6 +348,7 @@ void vtime_account_system(struct task_struct *tsk)
 	if (stolen)
 		account_steal_time(stolen);
 }
+EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
@@ -355,15 +359,15 @@ void vtime_account_idle(struct task_struct *tsk)
 }
 
 /*
- * Transfer the user and system times accumulated in the paca
- * by the exception entry and exit code to the generic process
- * user and system time records.
+ * Transfer the user time accumulated in the paca
+ * by the exception entry and exit code to the generic
+ * process user time records.
  * Must be called with interrupts disabled.
- * Assumes that vtime_account() has been called recently
- * (i.e. since the last entry from usermode) so that
+ * Assumes that vtime_account_system/idle() has been called
+ * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
-void account_process_tick(struct task_struct *tsk, int user_tick)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
 
@@ -375,13 +379,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	account_user_time(tsk, utime, utimescaled);
 }
 
-void vtime_task_switch(struct task_struct *prev)
-{
-	vtime_account(prev);
-	account_process_tick(prev, 0);
-}
-
-#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
+#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #define calc_cputime_factors()
 #endif
 
@@ -481,43 +479,13 @@ void arch_irq_work_raise(void)
 
 #endif /* CONFIG_IRQ_WORK */
 
-/*
- * timer_interrupt - gets called when the decrementer overflows,
- * with interrupts disabled.
- */
-void timer_interrupt(struct pt_regs * regs)
+void __timer_interrupt(void)
 {
-	struct pt_regs *old_regs;
+	struct pt_regs *regs = get_irq_regs();
 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
 	struct clock_event_device *evt = &__get_cpu_var(decrementers);
 	u64 now;
 
-	/* Ensure a positive value is written to the decrementer, or else
-	 * some CPUs will continue to take decrementer exceptions.
-	 */
-	set_dec(DECREMENTER_MAX);
-
-	/* Some implementations of hotplug will get timer interrupts while
-	 * offline, just ignore these
-	 */
-	if (!cpu_online(smp_processor_id()))
-		return;
-
-	/* Conditionally hard-enable interrupts now that the DEC has been
-	 * bumped to its maximum value
-	 */
-	may_hard_irq_enable();
-
-	__get_cpu_var(irq_stat).timer_irqs++;
-
-#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
-	if (atomic_read(&ppc_n_lost_interrupts) != 0)
-		do_IRQ(regs);
-#endif
-
-	old_regs = set_irq_regs(regs);
-	irq_enter();
-
 	trace_timer_interrupt_entry(regs);
 
 	if (test_irq_work_pending()) {
@@ -530,10 +498,15 @@ void timer_interrupt(struct pt_regs * regs)
 		*next_tb = ~(u64)0;
 		if (evt->event_handler)
 			evt->event_handler(evt);
+		__get_cpu_var(irq_stat).timer_irqs_event++;
 	} else {
 		now = *next_tb - now;
 		if (now <= DECREMENTER_MAX)
 			set_dec((int)now);
+		/* We may have raced with new irq work */
+		if (test_irq_work_pending())
+			set_dec(1);
+		__get_cpu_var(irq_stat).timer_irqs_others++;
 	}
 
 #ifdef CONFIG_PPC64
@@ -545,7 +518,48 @@ void timer_interrupt(struct pt_regs * regs)
 #endif
 
 	trace_timer_interrupt_exit(regs);
+}
+
+/*
+ * timer_interrupt - gets called when the decrementer overflows,
+ * with interrupts disabled.
+ */
+void timer_interrupt(struct pt_regs * regs)
+{
+	struct pt_regs *old_regs;
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+	/* Ensure a positive value is written to the decrementer, or else
+	 * some CPUs will continue to take decrementer exceptions.
+	 */
+	set_dec(DECREMENTER_MAX);
+
+	/* Some implementations of hotplug will get timer interrupts while
+	 * offline, just ignore these and we also need to set
+	 * decrementers_next_tb as MAX to make sure __check_irq_replay
+	 * don't replay timer interrupt when return, otherwise we'll trap
+	 * here infinitely :(
+	 */
+	if (!cpu_online(smp_processor_id())) {
+		*next_tb = ~(u64)0;
+		return;
+	}
 
+	/* Conditionally hard-enable interrupts now that the DEC has been
+	 * bumped to its maximum value
+	 */
+	may_hard_irq_enable();
+
+
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
+	if (atomic_read(&ppc_n_lost_interrupts) != 0)
+		do_IRQ(regs);
+#endif
+
+	old_regs = set_irq_regs(regs);
+	irq_enter();
+
+	__timer_interrupt();
 	irq_exit();
 	set_irq_regs(old_regs);
 }
@@ -610,7 +624,7 @@ unsigned long long sched_clock(void)
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
-	const unsigned int *fp;
+	const __be32 *fp;
 	int found = 0;
 
 	/* The cpu node should have timebase and clock frequency properties */
@@ -629,7 +643,6 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
 	return found;
 }
 
-/* should become __cpuinit when secondary_cpu_time_init also is */
 void start_cpu_decrementer(void)
 {
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
@@ -667,7 +680,7 @@ int update_persistent_clock(struct timespec now)
 	struct rtc_time tm;
 
 	if (!ppc_md.set_rtc_time)
-		return 0;
+		return -ENODEV;
 
 	to_tm(now.tv_sec + 1 + timezone_offset, &tm);
 	tm.tm_year -= 1900;
@@ -774,13 +787,8 @@ void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
 
 void update_vsyscall_tz(void)
 {
-	/* Make userspace gettimeofday spin until we're done. */
-	++vdso_data->tb_update_count;
-	smp_mb();
 	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
 	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-	smp_mb();
-	++vdso_data->tb_update_count;
 }
 
 static void __init clocksource_init(void)
@@ -807,6 +815,11 @@ static int decrementer_set_next_event(unsigned long evt,
 {
 	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
 	set_dec(evt);
+
+	/* We may have raced with new irq work */
+	if (test_irq_work_pending())
+		set_dec(1);
+
 	return 0;
 }
 
@@ -817,6 +830,15 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 		decrementer_set_next_event(DECREMENTER_MAX, dev);
 }
 
+/* Interrupt handler for the timer broadcast IPI */
+void tick_broadcast_ipi_handler(void)
+{
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+	*next_tb = get_tb_or_rtc();
+	__timer_interrupt();
+}
+
 static void register_decrementer_clockevent(int cpu)
 {
 	struct clock_event_device *dec = &per_cpu(decrementers, cpu);
@@ -920,6 +942,7 @@ void __init time_init(void)
 	clocksource_init();
 
 	init_decrementer_clockevent();
+	tick_setup_hrtimer_broadcast();
 }
 
 
@@ -1052,10 +1075,8 @@ static int __init rtc_init(void)
 		return -ENODEV;
 
 	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 module_init(rtc_init);