1 files changed, 87 insertions, 140 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 360e71d455ccd..70f145e024877 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -163,12 +163,6 @@ EXPORT_SYMBOL(__cputime_usec_factor);
 void (*dtl_consumer)(struct dtl_entry *, u64);
 #endif
 
-#ifdef CONFIG_PPC64
-#define get_accounting(tsk)	(&get_paca()->accounting)
-#else
-#define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
-#endif
-
 static void calc_cputime_factors(void)
 {
 	struct div_result res;
@@ -421,21 +415,6 @@ void vtime_flush(struct task_struct *tsk)
 	acct->softirq_time = 0;
 }
 
-#ifdef CONFIG_PPC32
-/*
- * Called from the context switch with interrupts disabled, to charge all
- * accumulated times to the current process, and to prepare accounting on
- * the next process.
- */
-void arch_vtime_task_switch(struct task_struct *prev)
-{
-	struct cpu_accounting_data *acct = get_accounting(current);
-
-	acct->starttime = get_accounting(prev)->starttime;
-	acct->startspurr = get_accounting(prev)->startspurr;
-}
-#endif /* CONFIG_PPC32 */
-
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #define calc_cputime_factors()
 #endif
@@ -513,6 +492,35 @@ static inline void clear_irq_work_pending(void)
 		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
+void arch_irq_work_raise(void)
+{
+	preempt_disable();
+	set_irq_work_pending_flag();
+	/*
+	 * Non-nmi code running with interrupts disabled will replay
+	 * irq_happened before it re-enables interrupts, so setthe
+	 * decrementer there instead of causing a hardware exception
+	 * which would immediately hit the masked interrupt handler
+	 * and have the net effect of setting the decrementer in
+	 * irq_happened.
+	 *
+	 * NMI interrupts can not check this when they return, so the
+	 * decrementer hardware exception is raised, which will fire
+	 * when interrupts are next enabled.
+	 *
+	 * BookE does not support this yet, it must audit all NMI
+	 * interrupt handlers to ensure they call nmi_enter() so this
+	 * check would be correct.
+	 */
+	if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) {
+		set_dec(1);
+	} else {
+		hard_irq_disable();
+		local_paca->irq_happened |= PACA_IRQ_DEC;
+	}
+	preempt_enable();
+}
+
 #else /* 32-bit */
 
 DEFINE_PER_CPU(u8, irq_work_pending);
@@ -521,8 +529,6 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
 #define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
-#endif /* 32 vs 64 bit */
-
 void arch_irq_work_raise(void)
 {
 	preempt_disable();
@@ -531,6 +537,8 @@ void arch_irq_work_raise(void)
 	preempt_enable();
 }
 
+#endif /* 32 vs 64 bit */
+
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0
@@ -538,60 +546,16 @@ void arch_irq_work_raise(void)
 
 #endif /* CONFIG_IRQ_WORK */
 
-static void __timer_interrupt(void)
-{
-	struct pt_regs *regs = get_irq_regs();
-	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
-	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
-	u64 now;
-
-	trace_timer_interrupt_entry(regs);
-
-	if (test_irq_work_pending()) {
-		clear_irq_work_pending();
-		irq_work_run();
-	}
-
-	now = get_tb_or_rtc();
-	if (now >= *next_tb) {
-		*next_tb = ~(u64)0;
-		if (evt->event_handler)
-			evt->event_handler(evt);
-		__this_cpu_inc(irq_stat.timer_irqs_event);
-	} else {
-		now = *next_tb - now;
-		if (now <= decrementer_max)
-			set_dec(now);
-		/* We may have raced with new irq work */
-		if (test_irq_work_pending())
-			set_dec(1);
-		__this_cpu_inc(irq_stat.timer_irqs_others);
-	}
-
-#ifdef CONFIG_PPC64
-	/* collect purr register values often, for accurate calculations */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
-		cu->current_tb = mfspr(SPRN_PURR);
-	}
-#endif
-
-	trace_timer_interrupt_exit(regs);
-}
-
 /*
  * timer_interrupt - gets called when the decrementer overflows,
  * with interrupts disabled.
  */
-void timer_interrupt(struct pt_regs * regs)
+void timer_interrupt(struct pt_regs *regs)
 {
-	struct pt_regs *old_regs;
+	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
 	u64 *next_tb = this_cpu_ptr(&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);
+	struct pt_regs *old_regs;
+	u64 now;
 
 	/* Some implementations of hotplug will get timer interrupts while
 	 * offline, just ignore these and we also need to set
@@ -599,11 +563,23 @@ void timer_interrupt(struct pt_regs * regs)
 	 * don't replay timer interrupt when return, otherwise we'll trap
 	 * here infinitely :(
 	 */
-	if (!cpu_online(smp_processor_id())) {
+	if (unlikely(!cpu_online(smp_processor_id()))) {
 		*next_tb = ~(u64)0;
+		set_dec(decrementer_max);
 		return;
 	}
 
+	/* Ensure a positive value is written to the decrementer, or else
+	 * some CPUs will continue to take decrementer exceptions. When the
+	 * PPC_WATCHDOG (decrementer based) is configured, keep this at most
+	 * 31 bits, which is about 4 seconds on most systems, which gives
+	 * the watchdog a chance of catching timer interrupt hard lockups.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+		set_dec(0x7fffffff);
+	else
+		set_dec(decrementer_max);
+
 	/* Conditionally hard-enable interrupts now that the DEC has been
 	 * bumped to its maximum value
 	 */
@@ -617,13 +593,46 @@ void timer_interrupt(struct pt_regs * regs)
 
 	old_regs = set_irq_regs(regs);
 	irq_enter();
+	trace_timer_interrupt_entry(regs);
+
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
+	}
+
+	now = get_tb_or_rtc();
+	if (now >= *next_tb) {
+		*next_tb = ~(u64)0;
+		if (evt->event_handler)
+			evt->event_handler(evt);
+		__this_cpu_inc(irq_stat.timer_irqs_event);
+	} else {
+		now = *next_tb - now;
+		if (now <= decrementer_max)
+			set_dec(now);
+		/* We may have raced with new irq work */
+		if (test_irq_work_pending())
+			set_dec(1);
+		__this_cpu_inc(irq_stat.timer_irqs_others);
+	}
 
-	__timer_interrupt();
+	trace_timer_interrupt_exit(regs);
 	irq_exit();
 	set_irq_regs(old_regs);
 }
 EXPORT_SYMBOL(timer_interrupt);
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void timer_broadcast_interrupt(void)
+{
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+
+	*next_tb = ~(u64)0;
+	tick_receive_broadcast();
+	__this_cpu_inc(irq_stat.broadcast_irqs_event);
+}
+#endif
+
 /*
  * Hypervisor decrementer interrupts shouldn't occur but are sometimes
  * left pending on exit from a KVM guest.  We don't need to do anything
@@ -781,21 +790,19 @@ void __init generic_calibrate_decr(void)
 	}
 }
 
-int update_persistent_clock(struct timespec now)
+int update_persistent_clock64(struct timespec64 now)
 {
 	struct rtc_time tm;
 
 	if (!ppc_md.set_rtc_time)
 		return -ENODEV;
 
-	to_tm(now.tv_sec + 1 + timezone_offset, &tm);
-	tm.tm_year -= 1900;
-	tm.tm_mon -= 1;
+	rtc_time64_to_tm(now.tv_sec + 1 + timezone_offset, &tm);
 
 	return ppc_md.set_rtc_time(&tm);
 }
 
-static void __read_persistent_clock(struct timespec *ts)
+static void __read_persistent_clock(struct timespec64 *ts)
 {
 	struct rtc_time tm;
 	static int first = 1;
@@ -819,11 +826,10 @@ static void __read_persistent_clock(struct timespec *ts)
 	}
 	ppc_md.get_rtc_time(&tm);
 
-	ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
-			    tm.tm_hour, tm.tm_min, tm.tm_sec);
+	ts->tv_sec = rtc_tm_to_time64(&tm);
 }
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	__read_persistent_clock(ts);
 
@@ -971,15 +977,6 @@ static int decrementer_shutdown(struct clock_event_device *dev)
 	return 0;
 }
 
-/* Interrupt handler for the timer broadcast IPI */
-void tick_broadcast_ipi_handler(void)
-{
-	u64 *next_tb = this_cpu_ptr(&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);
@@ -1141,56 +1138,6 @@ void __init time_init(void)
 #endif
 }
 
-
-#define FEBRUARY	2
-#define	STARTOFTIME	1970
-#define SECDAY		86400L
-#define SECYR		(SECDAY * 365)
-#define	leapyear(year)		((year) % 4 == 0 && \
-				 ((year) % 100 != 0 || (year) % 400 == 0))
-#define	days_in_year(a) 	(leapyear(a) ? 366 : 365)
-#define	days_in_month(a) 	(month_days[(a) - 1])
-
-static int month_days[12] = {
-	31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31
-};
-
-void to_tm(int tim, struct rtc_time * tm)
-{
-	register int    i;
-	register long   hms, day;
-
-	day = tim / SECDAY;
-	hms = tim % SECDAY;
-
-	/* Hours, minutes, seconds are easy */
-	tm->tm_hour = hms / 3600;
-	tm->tm_min = (hms % 3600) / 60;
-	tm->tm_sec = (hms % 3600) % 60;
-
-	/* Number of years in days */
-	for (i = STARTOFTIME; day >= days_in_year(i); i++)
-		day -= days_in_year(i);
-	tm->tm_year = i;
-
-	/* Number of months in days left */
-	if (leapyear(tm->tm_year))
-		days_in_month(FEBRUARY) = 29;
-	for (i = 1; day >= days_in_month(i); i++)
-		day -= days_in_month(i);
-	days_in_month(FEBRUARY) = 28;
-	tm->tm_mon = i;
-
-	/* Days are what is left over (+1) from all that. */
-	tm->tm_mday = day + 1;
-
-	/*
-	 * No-one uses the day of the week.
-	 */
-	tm->tm_wday = -1;
-}
-EXPORT_SYMBOL(to_tm);
-
 /*
  * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
  * result.