[PATCH] Time: i386 Conversion - part 3: Enable Generic Timekeeping

This converts the i386 arch to use the generic timeofday subsystem.  It
enabled the GENERIC_TIME option, disables the timer_opts code and other arch
specific timekeeping code and reworks the delay code.

While this patch enables the generic timekeeping, please note that this patch
does not provide any i386 clocksource.  Thus only the jiffies clocksource will
be available.  To get full replacements for the code being disabled here, the
timeofday-clocks-i386 patch will needed.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 1596101..db1f8b4 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -14,6 +14,10 @@
 	  486, 586, Pentiums, and various instruction-set-compatible chips by
 	  AMD, Cyrix, and others.
 
+config GENERIC_TIME
+	bool
+	default y
+
 config SEMAPHORE_SLEEPERS
 	bool
 	default y
diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index ca70d61..f238cb6 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -10,7 +10,6 @@
 		quirks.o i8237.o topology.o alternative.o i8253.o tsc.o
 
 obj-y				+= cpu/
-obj-y				+= timers/
 obj-y				+= acpi/
 obj-$(CONFIG_X86_BIOS_REBOOT)	+= reboot.o
 obj-$(CONFIG_MCA)		+= mca.o
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index 796e5fa..2a6ab86 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -82,7 +82,8 @@
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
 
-struct timer_opts *cur_timer __read_mostly = &timer_none;
+/* XXX - necessary to keep things compiling. to be removed later */
+u32 pmtmr_ioport;
 
 /*
  * This is a special lock that is owned by the CPU and holds the index
@@ -113,99 +114,19 @@
 }
 EXPORT_SYMBOL(rtc_cmos_write);
 
-/*
- * This version of gettimeofday has microsecond resolution
- * and better than microsecond precision on fast x86 machines with TSC.
- */
-void do_gettimeofday(struct timeval *tv)
-{
-	unsigned long seq;
-	unsigned long usec, sec;
-	unsigned long max_ntp_tick;
-
-	do {
-		unsigned long lost;
-
-		seq = read_seqbegin(&xtime_lock);
-
-		usec = cur_timer->get_offset();
-		lost = jiffies - wall_jiffies;
-
-		/*
-		 * If time_adjust is negative then NTP is slowing the clock
-		 * so make sure not to go into next possible interval.
-		 * Better to lose some accuracy than have time go backwards..
-		 */
-		if (unlikely(time_adjust < 0)) {
-			max_ntp_tick = (USEC_PER_SEC / HZ) - tickadj;
-			usec = min(usec, max_ntp_tick);
-
-			if (lost)
-				usec += lost * max_ntp_tick;
-		}
-		else if (unlikely(lost))
-			usec += lost * (USEC_PER_SEC / HZ);
-
-		sec = xtime.tv_sec;
-		usec += (xtime.tv_nsec / 1000);
-	} while (read_seqretry(&xtime_lock, seq));
-
-	while (usec >= 1000000) {
-		usec -= 1000000;
-		sec++;
-	}
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-}
-
-EXPORT_SYMBOL(do_gettimeofday);
-
-int do_settimeofday(struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-	/*
-	 * This is revolting. We need to set "xtime" correctly. However, the
-	 * value in this location is the value at the most recent update of
-	 * wall time.  Discover what correction gettimeofday() would have
-	 * made, and then undo it!
-	 */
-	nsec -= cur_timer->get_offset() * NSEC_PER_USEC;
-	nsec -= (jiffies - wall_jiffies) * TICK_NSEC;
-
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-	ntp_clear();
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
-	return 0;
-}
-
-EXPORT_SYMBOL(do_settimeofday);
-
 static int set_rtc_mmss(unsigned long nowtime)
 {
 	int retval;
-
-	WARN_ON(irqs_disabled());
+	unsigned long flags;
 
 	/* gets recalled with irq locally disabled */
-	spin_lock_irq(&rtc_lock);
+	/* XXX - does irqsave resolve this? -johnstul */
+	spin_lock_irqsave(&rtc_lock, flags);
 	if (efi_enabled)
 		retval = efi_set_rtc_mmss(nowtime);
 	else
 		retval = mach_set_rtc_mmss(nowtime);
-	spin_unlock_irq(&rtc_lock);
+	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	return retval;
 }
@@ -213,16 +134,6 @@
 
 int timer_ack;
 
-/* monotonic_clock(): returns # of nanoseconds passed since time_init()
- *		Note: This function is required to return accurate
- *		time even in the absence of multiple timer ticks.
- */
-unsigned long long monotonic_clock(void)
-{
-	return cur_timer->monotonic_clock();
-}
-EXPORT_SYMBOL(monotonic_clock);
-
 #if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -237,11 +148,21 @@
 #endif
 
 /*
- * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * This is the same as the above, except we _also_ save the current
+ * Time Stamp Counter value at the time of the timer interrupt, so that
+ * we later on can estimate the time of day more exactly.
  */
-static inline void do_timer_interrupt(int irq, struct pt_regs *regs)
+irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 {
+	/*
+	 * 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
+	 * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
+	 * the irq version of write_lock because as just said we have irq
+	 * locally disabled. -arca
+	 */
+	write_seqlock(&xtime_lock);
+
 #ifdef CONFIG_X86_IO_APIC
 	if (timer_ack) {
 		/*
@@ -274,27 +195,6 @@
 		irq = inb_p( 0x61 );	/* read the current state */
 		outb_p( irq|0x80, 0x61 );	/* reset the IRQ */
 	}
-}
-
-/*
- * This is the same as the above, except we _also_ save the current
- * Time Stamp Counter value at the time of the timer interrupt, so that
- * we later on can estimate the time of day more exactly.
- */
-irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
-{
-	/*
-	 * 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
-	 * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
-	 * the irq version of write_lock because as just said we have irq
-	 * locally disabled. -arca
-	 */
-	write_seqlock(&xtime_lock);
-
-	cur_timer->mark_offset();
- 
-	do_timer_interrupt(irq, regs);
 
 	write_sequnlock(&xtime_lock);
 
@@ -375,7 +275,6 @@
 
 static long clock_cmos_diff, sleep_start;
 
-static struct timer_opts *last_timer;
 static int timer_suspend(struct sys_device *dev, pm_message_t state)
 {
 	/*
@@ -384,10 +283,6 @@
 	clock_cmos_diff = -get_cmos_time();
 	clock_cmos_diff += get_seconds();
 	sleep_start = get_cmos_time();
-	last_timer = cur_timer;
-	cur_timer = &timer_none;
-	if (last_timer->suspend)
-		last_timer->suspend(state);
 	return 0;
 }
 
@@ -410,10 +305,6 @@
 	jiffies_64 += sleep_length;
 	wall_jiffies += sleep_length;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
-	if (last_timer->resume)
-		last_timer->resume();
-	cur_timer = last_timer;
-	last_timer = NULL;
 	touch_softlockup_watchdog();
 	return 0;
 }
@@ -455,9 +346,6 @@
 		printk("Using HPET for base-timer\n");
 	}
 
-	cur_timer = select_timer();
-	printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
-
 	time_init_hook();
 }
 #endif
@@ -479,8 +367,5 @@
 	set_normalized_timespec(&wall_to_monotonic,
 		-xtime.tv_sec, -xtime.tv_nsec);
 
-	cur_timer = select_timer();
-	printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
-
 	time_init_hook();
 }
diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c
index 3b64eaa..96b3074 100644
--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 
 #include <asm/tsc.h>
+#include <asm/delay.h>
 #include <asm/io.h>
 
 #include "mach_timer.h"
@@ -45,7 +46,6 @@
 
 __setup("notsc", tsc_setup);
 
-
 /*
  * code to mark and check if the TSC is unstable
  * due to cpufreq or due to unsynced TSCs
@@ -205,6 +205,7 @@
 				(unsigned long)cpu_khz % 1000);
 
 	set_cyc2ns_scale(cpu_khz);
+	use_tsc_delay();
 }
 
 #ifdef CONFIG_CPU_FREQ
diff --git a/arch/i386/lib/delay.c b/arch/i386/lib/delay.c
index c49a6ac..3c0714c 100644
--- a/arch/i386/lib/delay.c
+++ b/arch/i386/lib/delay.c
@@ -10,43 +10,92 @@
  *	we have to worry about.
  */
 
+#include <linux/module.h>
 #include <linux/config.h>
 #include <linux/sched.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+
 #include <asm/processor.h>
 #include <asm/delay.h>
 #include <asm/timer.h>
 
 #ifdef CONFIG_SMP
-#include <asm/smp.h>
+# include <asm/smp.h>
 #endif
 
-extern struct timer_opts* timer;
+/* simple loop based delay: */
+static void delay_loop(unsigned long loops)
+{
+	int d0;
+
+	__asm__ __volatile__(
+		"\tjmp 1f\n"
+		".align 16\n"
+		"1:\tjmp 2f\n"
+		".align 16\n"
+		"2:\tdecl %0\n\tjns 2b"
+		:"=&a" (d0)
+		:"0" (loops));
+}
+
+/* TSC based delay: */
+static void delay_tsc(unsigned long loops)
+{
+	unsigned long bclock, now;
+
+	rdtscl(bclock);
+	do {
+		rep_nop();
+		rdtscl(now);
+	} while ((now-bclock) < loops);
+}
+
+/*
+ * Since we calibrate only once at boot, this
+ * function should be set once at boot and not changed
+ */
+static void (*delay_fn)(unsigned long) = delay_loop;
+
+void use_tsc_delay(void)
+{
+	delay_fn = delay_tsc;
+}
+
+int read_current_timer(unsigned long *timer_val)
+{
+	if (delay_fn == delay_tsc) {
+		rdtscl(*timer_val);
+		return 0;
+	}
+	return -1;
+}
 
 void __delay(unsigned long loops)
 {
-	cur_timer->delay(loops);
+	delay_fn(loops);
 }
 
 inline void __const_udelay(unsigned long xloops)
 {
 	int d0;
+
 	xloops *= 4;
 	__asm__("mull %0"
 		:"=d" (xloops), "=&a" (d0)
-		:"1" (xloops),"0" (cpu_data[raw_smp_processor_id()].loops_per_jiffy * (HZ/4)));
-        __delay(++xloops);
+		:"1" (xloops), "0"
+		(cpu_data[raw_smp_processor_id()].loops_per_jiffy * (HZ/4)));
+
+	__delay(++xloops);
 }
 
 void __udelay(unsigned long usecs)
 {
-	__const_udelay(usecs * 0x000010c7);  /* 2**32 / 1000000 (rounded up) */
+	__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
 }
 
 void __ndelay(unsigned long nsecs)
 {
-	__const_udelay(nsecs * 0x00005);  /* 2**32 / 1000000000 (rounded up) */
+	__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
 }
 
 EXPORT_SYMBOL(__delay);