14 files changed, 573 insertions, 344 deletions

diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile
index 84ec46b38f7..0d54650e78f 100644
--- a/arch/alpha/kernel/Makefile
+++ b/arch/alpha/kernel/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_PCI)	+= pci.o pci_iommu.o pci-sysfs.o
 obj-$(CONFIG_SRM_ENV)	+= srm_env.o
 obj-$(CONFIG_MODULES)	+= module.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_RTC_DRV_ALPHA) += rtc.o
 
 ifdef CONFIG_ALPHA_GENERIC
 
diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c
index 89566b346c0..f4c7ab6f43b 100644
--- a/arch/alpha/kernel/alpha_ksyms.c
+++ b/arch/alpha/kernel/alpha_ksyms.c
@@ -40,6 +40,7 @@ EXPORT_SYMBOL(strrchr);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(___memset);
 EXPORT_SYMBOL(__memsetw);
 EXPORT_SYMBOL(__constant_c_memset);
 EXPORT_SYMBOL(copy_page);
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index 28e4429596f..1c8625cb0e2 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -66,21 +66,7 @@ do_entInt(unsigned long type, unsigned long vector,
 		break;
 	case 1:
 		old_regs = set_irq_regs(regs);
-#ifdef CONFIG_SMP
-	  {
-		long cpu;
-
-		smp_percpu_timer_interrupt(regs);
-		cpu = smp_processor_id();
-		if (cpu != boot_cpuid) {
-		        kstat_incr_irqs_this_cpu(RTC_IRQ, irq_to_desc(RTC_IRQ));
-		} else {
-			handle_irq(RTC_IRQ);
-		}
-	  }
-#else
 		handle_irq(RTC_IRQ);
-#endif
 		set_irq_regs(old_regs);
 		return;
 	case 2:
@@ -228,7 +214,7 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr,
  */
 
 struct irqaction timer_irqaction = {
-	.handler	= timer_interrupt,
+	.handler	= rtc_timer_interrupt,
 	.name		= "timer",
 };
 
diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h
index 7fa62488bd1..f54bdf658cd 100644
--- a/arch/alpha/kernel/machvec_impl.h
+++ b/arch/alpha/kernel/machvec_impl.h
@@ -43,10 +43,7 @@
 #define CAT1(x,y)  x##y
 #define CAT(x,y)   CAT1(x,y)
 
-#define DO_DEFAULT_RTC \
-	.rtc_port = 0x70, \
-	.rtc_get_time = common_get_rtc_time, \
-	.rtc_set_time = common_set_rtc_time
+#define DO_DEFAULT_RTC			.rtc_port = 0x70
 
 #define DO_EV4_MMU							\
 	.max_asn =			EV4_MAX_ASN,			\
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index d821b17047e..c52e7f0ee5f 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -83,6 +83,8 @@ struct alpha_pmu_t {
 	long pmc_left[3];
 	 /* Subroutine for allocation of PMCs.  Enforces constraints. */
 	int (*check_constraints)(struct perf_event **, unsigned long *, int);
+	/* Subroutine for checking validity of a raw event for this PMU. */
+	int (*raw_event_valid)(u64 config);
 };
 
 /*
@@ -203,6 +205,12 @@ success:
 }
 
 
+static int ev67_raw_event_valid(u64 config)
+{
+	return config >= EV67_CYCLES && config < EV67_LAST_ET;
+};
+
+
 static const struct alpha_pmu_t ev67_pmu = {
 	.event_map = ev67_perfmon_event_map,
 	.max_events = ARRAY_SIZE(ev67_perfmon_event_map),
@@ -211,7 +219,8 @@ static const struct alpha_pmu_t ev67_pmu = {
 	.pmc_count_mask = {EV67_PCTR_0_COUNT_MASK,  EV67_PCTR_1_COUNT_MASK,  0},
 	.pmc_max_period = {(1UL<<20) - 1, (1UL<<20) - 1, 0},
 	.pmc_left = {16, 4, 0},
-	.check_constraints = ev67_check_constraints
+	.check_constraints = ev67_check_constraints,
+	.raw_event_valid = ev67_raw_event_valid,
 };
 
 
@@ -609,7 +618,9 @@ static int __hw_perf_event_init(struct perf_event *event)
 	} else if (attr->type == PERF_TYPE_HW_CACHE) {
 		return -EOPNOTSUPP;
 	} else if (attr->type == PERF_TYPE_RAW) {
-		ev = attr->config & 0xff;
+		if (!alpha_pmu->raw_event_valid(attr->config))
+			return -EINVAL;
+		ev = attr->config;
 	} else {
 		return -EOPNOTSUPP;
 	}
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index f2360a74e5d..1941a07b581 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -46,6 +46,23 @@
 void (*pm_power_off)(void) = machine_power_off;
 EXPORT_SYMBOL(pm_power_off);
 
+#ifdef CONFIG_ALPHA_WTINT
+/*
+ * Sleep the CPU.
+ * EV6, LCA45 and QEMU know how to power down, skipping N timer interrupts.
+ */
+void arch_cpu_idle(void)
+{
+	wtint(0);
+	local_irq_enable();
+}
+
+void arch_cpu_idle_dead(void)
+{
+	wtint(INT_MAX);
+}
+#endif /* ALPHA_WTINT */
+
 struct halt_info {
 	int mode;
 	char *restart_cmd;
diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h
index d3e52d3fd59..da2d6ec9c37 100644
--- a/arch/alpha/kernel/proto.h
+++ b/arch/alpha/kernel/proto.h
@@ -135,17 +135,15 @@ extern void unregister_srm_console(void);
 /* smp.c */
 extern void setup_smp(void);
 extern void handle_ipi(struct pt_regs *);
-extern void smp_percpu_timer_interrupt(struct pt_regs *);
 
 /* bios32.c */
 /* extern void reset_for_srm(void); */
 
 /* time.c */
-extern irqreturn_t timer_interrupt(int irq, void *dev);
+extern irqreturn_t rtc_timer_interrupt(int irq, void *dev);
+extern void init_clockevent(void);
 extern void common_init_rtc(void);
 extern unsigned long est_cycle_freq;
-extern unsigned int common_get_rtc_time(struct rtc_time *time);
-extern int common_set_rtc_time(struct rtc_time *time);
 
 /* smc37c93x.c */
 extern void SMC93x_Init(void);
diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
new file mode 100644
index 00000000000..c8d284d8521
--- /dev/null
+++ b/arch/alpha/kernel/rtc.c
@@ -0,0 +1,323 @@
+/*
+ *  linux/arch/alpha/kernel/rtc.c
+ *
+ *  Copyright (C) 1991, 1992, 1995, 1999, 2000  Linus Torvalds
+ *
+ * This file contains date handling.
+ */
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mc146818rtc.h>
+#include <linux/bcd.h>
+#include <linux/rtc.h>
+#include <linux/platform_device.h>
+
+#include <asm/rtc.h>
+
+#include "proto.h"
+
+
+/*
+ * Support for the RTC device.
+ *
+ * We don't want to use the rtc-cmos driver, because we don't want to support
+ * alarms, as that would be indistinguishable from timer interrupts.
+ *
+ * Further, generic code is really, really tied to a 1900 epoch.  This is
+ * true in __get_rtc_time as well as the users of struct rtc_time e.g.
+ * rtc_tm_to_time.  Thankfully all of the other epochs in use are later
+ * than 1900, and so it's easy to adjust.
+ */
+
+static unsigned long rtc_epoch;
+
+static int __init
+specifiy_epoch(char *str)
+{
+	unsigned long epoch = simple_strtoul(str, NULL, 0);
+	if (epoch < 1900)
+		printk("Ignoring invalid user specified epoch %lu\n", epoch);
+	else
+		rtc_epoch = epoch;
+	return 1;
+}
+__setup("epoch=", specifiy_epoch);
+
+static void __init
+init_rtc_epoch(void)
+{
+	int epoch, year, ctrl;
+
+	if (rtc_epoch != 0) {
+		/* The epoch was specified on the command-line.  */
+		return;
+	}
+
+	/* Detect the epoch in use on this computer.  */
+	ctrl = CMOS_READ(RTC_CONTROL);
+	year = CMOS_READ(RTC_YEAR);
+	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+		year = bcd2bin(year);
+
+	/* PC-like is standard; used for year >= 70 */
+	epoch = 1900;
+	if (year < 20) {
+		epoch = 2000;
+	} else if (year >= 20 && year < 48) {
+		/* NT epoch */
+		epoch = 1980;
+	} else if (year >= 48 && year < 70) {
+		/* Digital UNIX epoch */
+		epoch = 1952;
+	}
+	rtc_epoch = epoch;
+
+	printk(KERN_INFO "Using epoch %d for rtc year %d\n", epoch, year);
+}
+
+static int
+alpha_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	__get_rtc_time(tm);
+
+	/* Adjust for non-default epochs.  It's easier to depend on the
+	   generic __get_rtc_time and adjust the epoch here than create
+	   a copy of __get_rtc_time with the edits we need.  */
+	if (rtc_epoch != 1900) {
+		int year = tm->tm_year;
+		/* Undo the century adjustment made in __get_rtc_time.  */
+		if (year >= 100)
+			year -= 100;
+		year += rtc_epoch - 1900;
+		/* Redo the century adjustment with the epoch in place.  */
+		if (year <= 69)
+			year += 100;
+		tm->tm_year = year;
+	}
+
+	return rtc_valid_tm(tm);
+}
+
+static int
+alpha_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct rtc_time xtm;
+
+	if (rtc_epoch != 1900) {
+		xtm = *tm;
+		xtm.tm_year -= rtc_epoch - 1900;
+		tm = &xtm;
+	}
+
+	return __set_rtc_time(tm);
+}
+
+static int
+alpha_rtc_set_mmss(struct device *dev, unsigned long nowtime)
+{
+	int retval = 0;
+	int real_seconds, real_minutes, cmos_minutes;
+	unsigned char save_control, save_freq_select;
+
+	/* Note: This code only updates minutes and seconds.  Comments
+	   indicate this was to avoid messing with unknown time zones,
+	   and with the epoch nonsense described above.  In order for
+	   this to work, the existing clock cannot be off by more than
+	   15 minutes.
+
+	   ??? This choice is may be out of date.  The x86 port does
+	   not have problems with timezones, and the epoch processing has
+	   now been fixed in alpha_set_rtc_time.
+
+	   In either case, one can always force a full rtc update with
+	   the userland hwclock program, so surely 15 minute accuracy
+	   is no real burden.  */
+
+	/* In order to set the CMOS clock precisely, we have to be called
+	   500 ms after the second nowtime has started, because when
+	   nowtime is written into the registers of the CMOS clock, it will
+	   jump to the next second precisely 500 ms later. Check the Motorola
+	   MC146818A or Dallas DS12887 data sheet for details.  */
+
+	/* irq are locally disabled here */
+	spin_lock(&rtc_lock);
+	/* Tell the clock it's being set */
+	save_control = CMOS_READ(RTC_CONTROL);
+	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
+
+	/* Stop and reset prescaler */
+	save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+	CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
+
+	cmos_minutes = CMOS_READ(RTC_MINUTES);
+	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+		cmos_minutes = bcd2bin(cmos_minutes);
+
+	real_seconds = nowtime % 60;
+	real_minutes = nowtime / 60;
+	if (((abs(real_minutes - cmos_minutes) + 15) / 30) & 1) {
+		/* correct for half hour time zone */
+		real_minutes += 30;
+	}
+	real_minutes %= 60;
+
+	if (abs(real_minutes - cmos_minutes) < 30) {
+		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+			real_seconds = bin2bcd(real_seconds);
+			real_minutes = bin2bcd(real_minutes);
+		}
+		CMOS_WRITE(real_seconds,RTC_SECONDS);
+		CMOS_WRITE(real_minutes,RTC_MINUTES);
+	} else {
+		printk_once(KERN_NOTICE
+			    "set_rtc_mmss: can't update from %d to %d\n",
+			    cmos_minutes, real_minutes);
+		retval = -1;
+	}
+
+	/* The following flags have to be released exactly in this order,
+	 * otherwise the DS12887 (popular MC146818A clone with integrated
+	 * battery and quartz) will not reset the oscillator and will not
+	 * update precisely 500 ms later. You won't find this mentioned in
+	 * the Dallas Semiconductor data sheets, but who believes data
+	 * sheets anyway ...                           -- Markus Kuhn
+	 */
+	CMOS_WRITE(save_control, RTC_CONTROL);
+	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+	spin_unlock(&rtc_lock);
+
+	return retval;
+}
+
+static int
+alpha_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case RTC_EPOCH_READ:
+		return put_user(rtc_epoch, (unsigned long __user *)arg);
+	case RTC_EPOCH_SET:
+		if (arg < 1900)
+			return -EINVAL;
+		rtc_epoch = arg;
+		return 0;
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+static const struct rtc_class_ops alpha_rtc_ops = {
+	.read_time = alpha_rtc_read_time,
+	.set_time = alpha_rtc_set_time,
+	.set_mmss = alpha_rtc_set_mmss,
+	.ioctl = alpha_rtc_ioctl,
+};
+
+/*
+ * Similarly, except do the actual CMOS access on the boot cpu only.
+ * This requires marshalling the data across an interprocessor call.
+ */
+
+#if defined(CONFIG_SMP) && \
+    (defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_MARVEL))
+# define HAVE_REMOTE_RTC 1
+
+union remote_data {
+	struct rtc_time *tm;
+	unsigned long now;
+	long retval;
+};
+
+static void
+do_remote_read(void *data)
+{
+	union remote_data *x = data;
+	x->retval = alpha_rtc_read_time(NULL, x->tm);
+}
+
+static int
+remote_read_time(struct device *dev, struct rtc_time *tm)
+{
+	union remote_data x;
+	if (smp_processor_id() != boot_cpuid) {
+		x.tm = tm;
+		smp_call_function_single(boot_cpuid, do_remote_read, &x, 1);
+		return x.retval;
+	}
+	return alpha_rtc_read_time(NULL, tm);
+}
+
+static void
+do_remote_set(void *data)
+{
+	union remote_data *x = data;
+	x->retval = alpha_rtc_set_time(NULL, x->tm);
+}
+
+static int
+remote_set_time(struct device *dev, struct rtc_time *tm)
+{
+	union remote_data x;
+	if (smp_processor_id() != boot_cpuid) {
+		x.tm = tm;
+		smp_call_function_single(boot_cpuid, do_remote_set, &x, 1);
+		return x.retval;
+	}
+	return alpha_rtc_set_time(NULL, tm);
+}
+
+static void
+do_remote_mmss(void *data)
+{
+	union remote_data *x = data;
+	x->retval = alpha_rtc_set_mmss(NULL, x->now);
+}
+
+static int
+remote_set_mmss(struct device *dev, unsigned long now)
+{
+	union remote_data x;
+	if (smp_processor_id() != boot_cpuid) {
+		x.now = now;
+		smp_call_function_single(boot_cpuid, do_remote_mmss, &x, 1);
+		return x.retval;
+	}
+	return alpha_rtc_set_mmss(NULL, now);
+}
+
+static const struct rtc_class_ops remote_rtc_ops = {
+	.read_time = remote_read_time,
+	.set_time = remote_set_time,
+	.set_mmss = remote_set_mmss,
+	.ioctl = alpha_rtc_ioctl,
+};
+#endif
+
+static int __init
+alpha_rtc_init(void)
+{
+	const struct rtc_class_ops *ops;
+	struct platform_device *pdev;
+	struct rtc_device *rtc;
+	const char *name;
+
+	init_rtc_epoch();
+	name = "rtc-alpha";
+	ops = &alpha_rtc_ops;
+
+#ifdef HAVE_REMOTE_RTC
+	if (alpha_mv.rtc_boot_cpu_only)
+		ops = &remote_rtc_ops;
+#endif
+
+	pdev = platform_device_register_simple(name, -1, NULL, 0);
+	rtc = devm_rtc_device_register(&pdev->dev, name, ops, THIS_MODULE);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	platform_set_drvdata(pdev, rtc);
+	return 0;
+}
+device_initcall(alpha_rtc_init);
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index 9e3107cc5eb..b20af76f12c 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -115,10 +115,17 @@ unsigned long alpha_agpgart_size = DEFAULT_AGP_APER_SIZE;
 
 #ifdef CONFIG_ALPHA_GENERIC
 struct alpha_machine_vector alpha_mv;
+#endif
+
+#ifndef alpha_using_srm
 int alpha_using_srm;
 EXPORT_SYMBOL(alpha_using_srm);
 #endif
 
+#ifndef alpha_using_qemu
+int alpha_using_qemu;
+#endif
+
 static struct alpha_machine_vector *get_sysvec(unsigned long, unsigned long,
 					       unsigned long);
 static struct alpha_machine_vector *get_sysvec_byname(const char *);
@@ -529,11 +536,15 @@ setup_arch(char **cmdline_p)
 	atomic_notifier_chain_register(&panic_notifier_list,
 			&alpha_panic_block);
 
-#ifdef CONFIG_ALPHA_GENERIC
+#ifndef alpha_using_srm
 	/* Assume that we've booted from SRM if we haven't booted from MILO.
 	   Detect the later by looking for "MILO" in the system serial nr.  */
 	alpha_using_srm = strncmp((const char *)hwrpb->ssn, "MILO", 4) != 0;
 #endif
+#ifndef alpha_using_qemu
+	/* Similarly, look for QEMU.  */
+	alpha_using_qemu = strstr((const char *)hwrpb->ssn, "QEMU") != 0;
+#endif
 
 	/* If we are using SRM, we want to allow callbacks
 	   as early as possible, so do this NOW, and then
@@ -1207,6 +1218,7 @@ show_cpuinfo(struct seq_file *f, void *slot)
 	char *systype_name;
 	char *sysvariation_name;
 	int nr_processors;
+	unsigned long timer_freq;
 
 	cpu_index = (unsigned) (cpu->type - 1);
 	cpu_name = "Unknown";
@@ -1218,6 +1230,12 @@ show_cpuinfo(struct seq_file *f, void *slot)
 
 	nr_processors = get_nr_processors(cpu, hwrpb->nr_processors);
 
+#if CONFIG_HZ == 1024 || CONFIG_HZ == 1200
+	timer_freq = (100UL * hwrpb->intr_freq) / 4096;
+#else
+	timer_freq = 100UL * CONFIG_HZ;
+#endif
+
 	seq_printf(f, "cpu\t\t\t: Alpha\n"
 		      "cpu model\t\t: %s\n"
 		      "cpu variation\t\t: %ld\n"
@@ -1243,8 +1261,7 @@ show_cpuinfo(struct seq_file *f, void *slot)
 		       (char*)hwrpb->ssn,
 		       est_cycle_freq ? : hwrpb->cycle_freq,
 		       est_cycle_freq ? "est." : "",
-		       hwrpb->intr_freq / 4096,
-		       (100 * hwrpb->intr_freq / 4096) % 100,
+		       timer_freq / 100, timer_freq % 100,
 		       hwrpb->pagesize,
 		       hwrpb->pa_bits,
 		       hwrpb->max_asn,
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 9dbbcb3b914..99ac36d5de4 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -138,9 +138,11 @@ smp_callin(void)
 
 	/* Get our local ticker going. */
 	smp_setup_percpu_timer(cpuid);
+	init_clockevent();
 
 	/* Call platform-specific callin, if specified */
-	if (alpha_mv.smp_callin) alpha_mv.smp_callin();
+	if (alpha_mv.smp_callin)
+		alpha_mv.smp_callin();
 
 	/* All kernel threads share the same mm context.  */
 	atomic_inc(&init_mm.mm_count);
@@ -498,35 +500,6 @@ smp_cpus_done(unsigned int max_cpus)
 	       ((bogosum + 2500) / (5000/HZ)) % 100);
 }
 
-
-void
-smp_percpu_timer_interrupt(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs;
-	int cpu = smp_processor_id();
-	unsigned long user = user_mode(regs);
-	struct cpuinfo_alpha *data = &cpu_data[cpu];
-
-	old_regs = set_irq_regs(regs);
-
-	/* Record kernel PC.  */
-	profile_tick(CPU_PROFILING);
-
-	if (!--data->prof_counter) {
-		/* We need to make like a normal interrupt -- otherwise
-		   timer interrupts ignore the global interrupt lock,
-		   which would be a Bad Thing.  */
-		irq_enter();
-
-		update_process_times(user);
-
-		data->prof_counter = data->prof_multiplier;
-
-		irq_exit();
-	}
-	set_irq_regs(old_regs);
-}
-
 int
 setup_profiling_timer(unsigned int multiplier)
 {
diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c
index 5a0af11b3a6..608f2a7fa0a 100644
--- a/arch/alpha/kernel/sys_jensen.c
+++ b/arch/alpha/kernel/sys_jensen.c
@@ -224,8 +224,6 @@ struct alpha_machine_vector jensen_mv __initmv = {
 	.machine_check		= jensen_machine_check,
 	.max_isa_dma_address	= ALPHA_MAX_ISA_DMA_ADDRESS,
 	.rtc_port		= 0x170,
-	.rtc_get_time		= common_get_rtc_time,
-	.rtc_set_time		= common_set_rtc_time,
 
 	.nr_irqs		= 16,
 	.device_interrupt	= jensen_device_interrupt,
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index c92e389ff21..f21d61fab67 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -22,7 +22,6 @@
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>
 #include <asm/vga.h>
-#include <asm/rtc.h>
 
 #include "proto.h"
 #include "err_impl.h"
@@ -400,57 +399,6 @@ marvel_init_rtc(void)
 	init_rtc_irq();
 }
 
-struct marvel_rtc_time {
-	struct rtc_time *time;
-	int retval;
-};
-
-#ifdef CONFIG_SMP
-static void
-smp_get_rtc_time(void *data)
-{
-	struct marvel_rtc_time *mrt = data;
-	mrt->retval = __get_rtc_time(mrt->time);
-}
-
-static void
-smp_set_rtc_time(void *data)
-{
-	struct marvel_rtc_time *mrt = data;
-	mrt->retval = __set_rtc_time(mrt->time);
-}
-#endif
-
-static unsigned int
-marvel_get_rtc_time(struct rtc_time *time)
-{
-#ifdef CONFIG_SMP
-	struct marvel_rtc_time mrt;
-
-	if (smp_processor_id() != boot_cpuid) {
-		mrt.time = time;
-		smp_call_function_single(boot_cpuid, smp_get_rtc_time, &mrt, 1);
-		return mrt.retval;
-	}
-#endif
-	return __get_rtc_time(time);
-}
-
-static int
-marvel_set_rtc_time(struct rtc_time *time)
-{
-#ifdef CONFIG_SMP
-	struct marvel_rtc_time mrt;
-
-	if (smp_processor_id() != boot_cpuid) {
-		mrt.time = time;
-		smp_call_function_single(boot_cpuid, smp_set_rtc_time, &mrt, 1);
-		return mrt.retval;
-	}
-#endif
-	return __set_rtc_time(time);
-}
-
 static void
 marvel_smp_callin(void)
 {
@@ -492,8 +440,7 @@ struct alpha_machine_vector marvel_ev7_mv __initmv = {
 	.vector_name		= "MARVEL/EV7",
 	DO_EV7_MMU,
 	.rtc_port		= 0x70,
-	.rtc_get_time		= marvel_get_rtc_time,
-	.rtc_set_time		= marvel_set_rtc_time,
+	.rtc_boot_cpu_only	= 1,
 	DO_MARVEL_IO,
 	.machine_check		= marvel_machine_check,
 	.max_isa_dma_address	= ALPHA_MAX_ISA_DMA_ADDRESS,
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index ea339503655..ee39cee8064 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -3,13 +3,7 @@
  *
  *  Copyright (C) 1991, 1992, 1995, 1999, 2000  Linus Torvalds
  *
- * This file contains the PC-specific time handling details:
- * reading the RTC at bootup, etc..
- * 1994-07-02    Alan Modra
- *	fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
- * 1995-03-26    Markus Kuhn
- *      fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
- *      precision CMOS clock update
+ * This file contains the clocksource time handling.
  * 1997-09-10	Updated NTP code according to technical memorandum Jan '96
  *		"A Kernel Model for Precision Timekeeping" by Dave Mills
  * 1997-01-09    Adrian Sun
@@ -21,9 +15,6 @@
  * 1999-04-16	Thorsten Kranzkowski (dl8bcu@gmx.net)
  *	fixed algorithm in do_gettimeofday() for calculating the precise time
  *	from processor cycle counter (now taking lost_ticks into account)
- * 2000-08-13	Jan-Benedict Glaw <jbglaw@lug-owl.de>
- * 	Fixed time_init to be aware of epoches != 1900. This prevents
- * 	booting up in 2048 for me;) Code is stolen from rtc.c.
  * 2003-06-03	R. Scott Bailey <scott.bailey@eds.com>
  *	Tighten sanity in time_init from 1% (10,000 PPM) to 250 PPM
  */
@@ -46,40 +37,19 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/hwrpb.h>
-#include <asm/rtc.h>
 
 #include <linux/mc146818rtc.h>
 #include <linux/time.h>
 #include <linux/timex.h>
 #include <linux/clocksource.h>
+#include <linux/clockchips.h>
 
 #include "proto.h"
 #include "irq_impl.h"
 
-static int set_rtc_mmss(unsigned long);
-
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
 
-#define TICK_SIZE (tick_nsec / 1000)
-
-/*
- * Shift amount by which scaled_ticks_per_cycle is scaled.  Shifting
- * by 48 gives us 16 bits for HZ while keeping the accuracy good even
- * for large CPU clock rates.
- */
-#define FIX_SHIFT	48
-
-/* lump static variables together for more efficient access: */
-static struct {
-	/* cycle counter last time it got invoked */
-	__u32 last_time;
-	/* ticks/cycle * 2^48 */
-	unsigned long scaled_ticks_per_cycle;
-	/* partial unused tick */
-	unsigned long partial_tick;
-} state;
-
 unsigned long est_cycle_freq;
 
 #ifdef CONFIG_IRQ_WORK
@@ -108,109 +78,156 @@ static inline __u32 rpcc(void)
 	return __builtin_alpha_rpcc();
 }
 
-int update_persistent_clock(struct timespec now)
-{
-	return set_rtc_mmss(now.tv_sec);
-}
 
-void read_persistent_clock(struct timespec *ts)
+
+/*
+ * The RTC as a clock_event_device primitive.
+ */
+
+static DEFINE_PER_CPU(struct clock_event_device, cpu_ce);
+
+irqreturn_t
+rtc_timer_interrupt(int irq, void *dev)
 {
-	unsigned int year, mon, day, hour, min, sec, epoch;
-
-	sec = CMOS_READ(RTC_SECONDS);
-	min = CMOS_READ(RTC_MINUTES);
-	hour = CMOS_READ(RTC_HOURS);
-	day = CMOS_READ(RTC_DAY_OF_MONTH);
-	mon = CMOS_READ(RTC_MONTH);
-	year = CMOS_READ(RTC_YEAR);
-
-	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		sec = bcd2bin(sec);
-		min = bcd2bin(min);
-		hour = bcd2bin(hour);
-		day = bcd2bin(day);
-		mon = bcd2bin(mon);
-		year = bcd2bin(year);
-	}
+	int cpu = smp_processor_id();
+	struct clock_event_device *ce = &per_cpu(cpu_ce, cpu);
 
-	/* PC-like is standard; used for year >= 70 */
-	epoch = 1900;
-	if (year < 20)
-		epoch = 2000;
-	else if (year >= 20 && year < 48)
-		/* NT epoch */
-		epoch = 1980;
-	else if (year >= 48 && year < 70)
-		/* Digital UNIX epoch */
-		epoch = 1952;
+	/* Don't run the hook for UNUSED or SHUTDOWN.  */
+	if (likely(ce->mode == CLOCK_EVT_MODE_PERIODIC))
+		ce->event_handler(ce);
 
-	printk(KERN_INFO "Using epoch = %d\n", epoch);
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
+	}
 
-	if ((year += epoch) < 1970)
-		year += 100;
+	return IRQ_HANDLED;
+}
 
-	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
-	ts->tv_nsec = 0;
+static void
+rtc_ce_set_mode(enum clock_event_mode mode, struct clock_event_device *ce)
+{
+	/* The mode member of CE is updated in generic code.
+	   Since we only support periodic events, nothing to do.  */
+}
+
+static int
+rtc_ce_set_next_event(unsigned long evt, struct clock_event_device *ce)
+{
+	/* This hook is for oneshot mode, which we don't support.  */
+	return -EINVAL;
 }
 
+static void __init
+init_rtc_clockevent(void)
+{
+	int cpu = smp_processor_id();
+	struct clock_event_device *ce = &per_cpu(cpu_ce, cpu);
+
+	*ce = (struct clock_event_device){
+		.name = "rtc",
+		.features = CLOCK_EVT_FEAT_PERIODIC,
+		.rating = 100,
+		.cpumask = cpumask_of(cpu),
+		.set_mode = rtc_ce_set_mode,
+		.set_next_event = rtc_ce_set_next_event,
+	};
 
+	clockevents_config_and_register(ce, CONFIG_HZ, 0, 0);
+}
 
+
 /*
- * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "xtime_update()" routine every clocktick
+ * The QEMU clock as a clocksource primitive.
  */
-irqreturn_t timer_interrupt(int irq, void *dev)
+
+static cycle_t
+qemu_cs_read(struct clocksource *cs)
 {
-	unsigned long delta;
-	__u32 now;
-	long nticks;
+	return qemu_get_vmtime();
+}
 
-#ifndef CONFIG_SMP
-	/* Not SMP, do kernel PC profiling here.  */
-	profile_tick(CPU_PROFILING);
-#endif
+static struct clocksource qemu_cs = {
+	.name                   = "qemu",
+	.rating                 = 400,
+	.read                   = qemu_cs_read,
+	.mask                   = CLOCKSOURCE_MASK(64),
+	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS,
+	.max_idle_ns		= LONG_MAX
+};
 
-	/*
-	 * Calculate how many ticks have passed since the last update,
-	 * including any previous partial leftover.  Save any resulting
-	 * fraction for the next pass.
-	 */
-	now = rpcc();
-	delta = now - state.last_time;
-	state.last_time = now;
-	delta = delta * state.scaled_ticks_per_cycle + state.partial_tick;
-	state.partial_tick = delta & ((1UL << FIX_SHIFT) - 1); 
-	nticks = delta >> FIX_SHIFT;
 
-	if (nticks)
-		xtime_update(nticks);
+/*
+ * The QEMU alarm as a clock_event_device primitive.
+ */
 
-	if (test_irq_work_pending()) {
-		clear_irq_work_pending();
-		irq_work_run();
-	}
+static void
+qemu_ce_set_mode(enum clock_event_mode mode, struct clock_event_device *ce)
+{
+	/* The mode member of CE is updated for us in generic code.
+	   Just make sure that the event is disabled.  */
+	qemu_set_alarm_abs(0);
+}
 
-#ifndef CONFIG_SMP
-	while (nticks--)
-		update_process_times(user_mode(get_irq_regs()));
-#endif
+static int
+qemu_ce_set_next_event(unsigned long evt, struct clock_event_device *ce)
+{
+	qemu_set_alarm_rel(evt);
+	return 0;
+}
 
+static irqreturn_t
+qemu_timer_interrupt(int irq, void *dev)
+{
+	int cpu = smp_processor_id();
+	struct clock_event_device *ce = &per_cpu(cpu_ce, cpu);
+
+	ce->event_handler(ce);
 	return IRQ_HANDLED;
 }
 
+static void __init
+init_qemu_clockevent(void)
+{
+	int cpu = smp_processor_id();
+	struct clock_event_device *ce = &per_cpu(cpu_ce, cpu);
+
+	*ce = (struct clock_event_device){
+		.name = "qemu",
+		.features = CLOCK_EVT_FEAT_ONESHOT,
+		.rating = 400,
+		.cpumask = cpumask_of(cpu),
+		.set_mode = qemu_ce_set_mode,
+		.set_next_event = qemu_ce_set_next_event,
+	};
+
+	clockevents_config_and_register(ce, NSEC_PER_SEC, 1000, LONG_MAX);
+}
+
+
 void __init
 common_init_rtc(void)
 {
-	unsigned char x;
+	unsigned char x, sel = 0;
 
 	/* Reset periodic interrupt frequency.  */
-	x = CMOS_READ(RTC_FREQ_SELECT) & 0x3f;
-        /* Test includes known working values on various platforms
-           where 0x26 is wrong; we refuse to change those. */
-	if (x != 0x26 && x != 0x25 && x != 0x19 && x != 0x06) {
-		printk("Setting RTC_FREQ to 1024 Hz (%x)\n", x);
-		CMOS_WRITE(0x26, RTC_FREQ_SELECT);
+#if CONFIG_HZ == 1024 || CONFIG_HZ == 1200
+ 	x = CMOS_READ(RTC_FREQ_SELECT) & 0x3f;
+	/* Test includes known working values on various platforms
+	   where 0x26 is wrong; we refuse to change those. */
+ 	if (x != 0x26 && x != 0x25 && x != 0x19 && x != 0x06) {
+		sel = RTC_REF_CLCK_32KHZ + 6;
 	}
+#elif CONFIG_HZ == 256 || CONFIG_HZ == 128 || CONFIG_HZ == 64 || CONFIG_HZ == 32
+	sel = RTC_REF_CLCK_32KHZ + __builtin_ffs(32768 / CONFIG_HZ);
+#else
+# error "Unknown HZ from arch/alpha/Kconfig"
+#endif
+	if (sel) {
+		printk(KERN_INFO "Setting RTC_FREQ to %d Hz (%x)\n",
+		       CONFIG_HZ, sel);
+		CMOS_WRITE(sel, RTC_FREQ_SELECT);
+ 	}
 
 	/* Turn on periodic interrupts.  */
 	x = CMOS_READ(RTC_CONTROL);
@@ -233,16 +250,37 @@ common_init_rtc(void)
 	init_rtc_irq();
 }
 
-unsigned int common_get_rtc_time(struct rtc_time *time)
-{
-	return __get_rtc_time(time);
-}
+
+#ifndef CONFIG_ALPHA_WTINT
+/*
+ * The RPCC as a clocksource primitive.
+ *
+ * While we have free-running timecounters running on all CPUs, and we make
+ * a half-hearted attempt in init_rtc_rpcc_info to sync the timecounter
+ * with the wall clock, that initialization isn't kept up-to-date across
+ * different time counters in SMP mode.  Therefore we can only use this
+ * method when there's only one CPU enabled.
+ *
+ * When using the WTINT PALcall, the RPCC may shift to a lower frequency,
+ * or stop altogether, while waiting for the interrupt.  Therefore we cannot
+ * use this method when WTINT is in use.
+ */
 
-int common_set_rtc_time(struct rtc_time *time)
+static cycle_t read_rpcc(struct clocksource *cs)
 {
-	return __set_rtc_time(time);
+	return rpcc();
 }
 
+static struct clocksource clocksource_rpcc = {
+	.name                   = "rpcc",
+	.rating                 = 300,
+	.read                   = read_rpcc,
+	.mask                   = CLOCKSOURCE_MASK(32),
+	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS
+};
+#endif /* ALPHA_WTINT */
+
+
 /* Validate a computed cycle counter result against the known bounds for
    the given processor core.  There's too much brokenness in the way of
    timing hardware for any one method to work everywhere.  :-(
@@ -353,33 +391,6 @@ rpcc_after_update_in_progress(void)
 	return rpcc();
 }
 
-#ifndef CONFIG_SMP
-/* Until and unless we figure out how to get cpu cycle counters
-   in sync and keep them there, we can't use the rpcc.  */
-static cycle_t read_rpcc(struct clocksource *cs)
-{
-	cycle_t ret = (cycle_t)rpcc();
-	return ret;
-}
-
-static struct clocksource clocksource_rpcc = {
-	.name                   = "rpcc",
-	.rating                 = 300,
-	.read                   = read_rpcc,
-	.mask                   = CLOCKSOURCE_MASK(32),
-	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS
-};
-
-static inline void register_rpcc_clocksource(long cycle_freq)
-{
-	clocksource_register_hz(&clocksource_rpcc, cycle_freq);
-}
-#else /* !CONFIG_SMP */
-static inline void register_rpcc_clocksource(long cycle_freq)
-{
-}
-#endif /* !CONFIG_SMP */
-
 void __init
 time_init(void)
 {
@@ -387,6 +398,15 @@ time_init(void)
 	unsigned long cycle_freq, tolerance;
 	long diff;
 
+	if (alpha_using_qemu) {
+		clocksource_register_hz(&qemu_cs, NSEC_PER_SEC);
+		init_qemu_clockevent();
+
+		timer_irqaction.handler = qemu_timer_interrupt;
+		init_rtc_irq();
+		return;
+	}
+
 	/* Calibrate CPU clock -- attempt #1.  */
 	if (!est_cycle_freq)
 		est_cycle_freq = validate_cc_value(calibrate_cc_with_pit());
@@ -421,100 +441,25 @@ time_init(void)
 		       "and unable to estimate a proper value!\n");
 	}
 
-	/* From John Bowman <bowman@math.ualberta.ca>: allow the values
-	   to settle, as the Update-In-Progress bit going low isn't good
-	   enough on some hardware.  2ms is our guess; we haven't found 
-	   bogomips yet, but this is close on a 500Mhz box.  */
-	__delay(1000000);
-
-
-	if (HZ > (1<<16)) {
-		extern void __you_loose (void);
-		__you_loose();
-	}
-
-	register_rpcc_clocksource(cycle_freq);
-
-	state.last_time = cc1;
-	state.scaled_ticks_per_cycle
-		= ((unsigned long) HZ << FIX_SHIFT) / cycle_freq;
-	state.partial_tick = 0L;
+	/* See above for restrictions on using clocksource_rpcc.  */
+#ifndef CONFIG_ALPHA_WTINT
+	if (hwrpb->nr_processors == 1)
+		clocksource_register_hz(&clocksource_rpcc, cycle_freq);
+#endif
 
 	/* Startup the timer source. */
 	alpha_mv.init_rtc();
+	init_rtc_clockevent();
 }
 
-/*
- * In order to set the CMOS clock precisely, set_rtc_mmss has to be
- * called 500 ms after the second nowtime has started, because when
- * nowtime is written into the registers of the CMOS clock, it will
- * jump to the next second precisely 500 ms later. Check the Motorola
- * MC146818A or Dallas DS12887 data sheet for details.
- *
- * BUG: This routine does not handle hour overflow properly; it just
- *      sets the minutes. Usually you won't notice until after reboot!
- */
-
-
-static int
-set_rtc_mmss(unsigned long nowtime)
+/* Initialize the clock_event_device for secondary cpus.  */
+#ifdef CONFIG_SMP
+void __init
+init_clockevent(void)
 {
-	int retval = 0;
-	int real_seconds, real_minutes, cmos_minutes;
-	unsigned char save_control, save_freq_select;
-
-	/* irq are locally disabled here */
-	spin_lock(&rtc_lock);
-	/* Tell the clock it's being set */
-	save_control = CMOS_READ(RTC_CONTROL);
-	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
-
-	/* Stop and reset prescaler */
-	save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
-	CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
-
-	cmos_minutes = CMOS_READ(RTC_MINUTES);
-	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		cmos_minutes = bcd2bin(cmos_minutes);
-
-	/*
-	 * since we're only adjusting minutes and seconds,
-	 * don't interfere with hour overflow. This avoids
-	 * messing with unknown time zones but requires your
-	 * RTC not to be off by more than 15 minutes
-	 */
-	real_seconds = nowtime % 60;
-	real_minutes = nowtime / 60;
-	if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1) {
-		/* correct for half hour time zone */
-		real_minutes += 30;
-	}
-	real_minutes %= 60;
-
-	if (abs(real_minutes - cmos_minutes) < 30) {
-		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			real_seconds = bin2bcd(real_seconds);
-			real_minutes = bin2bcd(real_minutes);
-		}
-		CMOS_WRITE(real_seconds,RTC_SECONDS);
-		CMOS_WRITE(real_minutes,RTC_MINUTES);
-	} else {
-		printk_once(KERN_NOTICE
-		       "set_rtc_mmss: can't update from %d to %d\n",
-		       cmos_minutes, real_minutes);
- 		retval = -1;
-	}
-
-	/* The following flags have to be released exactly in this order,
-	 * otherwise the DS12887 (popular MC146818A clone with integrated
-	 * battery and quartz) will not reset the oscillator and will not
-	 * update precisely 500 ms later. You won't find this mentioned in
-	 * the Dallas Semiconductor data sheets, but who believes data
-	 * sheets anyway ...                           -- Markus Kuhn
-	 */
-	CMOS_WRITE(save_control, RTC_CONTROL);
-	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
-	spin_unlock(&rtc_lock);
-
-	return retval;
+	if (alpha_using_qemu)
+		init_qemu_clockevent();
+	else
+		init_rtc_clockevent();
 }
+#endif
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index bd0665cdc84..9c4c189eb22 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -241,6 +241,21 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 			       (const char *)(data[1] | (long)data[2] << 32), 
 			       data[0]);
 		}
+#ifdef CONFIG_ALPHA_WTINT
+		if (type == 4) {
+			/* If CALL_PAL WTINT is totally unsupported by the
+			   PALcode, e.g. MILO, "emulate" it by overwriting
+			   the insn.  */
+			unsigned int *pinsn
+			  = (unsigned int *) regs->pc - 1;
+			if (*pinsn == PAL_wtint) {
+				*pinsn = 0x47e01400; /* mov 0,$0 */
+				imb();
+				regs->r0 = 0;
+				return;
+			}
+		}
+#endif /* ALPHA_WTINT */
 		die_if_kernel((type == 1 ? "Kernel Bug" : "Instruction fault"),
 			      regs, type, NULL);
 	}