[PATCH] add suspend/resume for timer

The timers lack .suspend/.resume methods.  Because of this, jiffies got a
big compensation after a S3 resume.  And then softlockup watchdog reports
an oops.  This occured with HPET enabled, but it's also possible for other
timers.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 50 insertions, 27 deletions

diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index 0ee9dee8af0..6f794a78ee1 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -383,6 +383,7 @@ void notify_arch_cmos_timer(void)
 
 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)
 {
 	/*
@@ -391,6 +392,10 @@ static int timer_suspend(struct sys_device *dev, pm_message_t state)
 	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;
 }
 
@@ -404,6 +409,7 @@ static int timer_resume(struct sys_device *dev)
 	if (is_hpet_enabled())
 		hpet_reenable();
 #endif
+	setup_pit_timer();
 	sec = get_cmos_time() + clock_cmos_diff;
 	sleep_length = (get_cmos_time() - sleep_start) * HZ;
 	write_seqlock_irqsave(&xtime_lock, flags);
@@ -412,6 +418,10 @@ static int timer_resume(struct sys_device *dev)
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 	jiffies += sleep_length;
 	wall_jiffies += sleep_length;
+	if (last_timer->resume)
+		last_timer->resume();
+	cur_timer = last_timer;
+	last_timer = NULL;
 	return 0;
 }
 
diff --git a/arch/i386/kernel/timers/timer_hpet.c b/arch/i386/kernel/timers/timer_hpet.c
index cbb3f221ced..001de97c9e4 100644
--- a/arch/i386/kernel/timers/timer_hpet.c
+++ b/arch/i386/kernel/timers/timer_hpet.c
@@ -181,6 +181,19 @@ static int __init init_hpet(char* override)
 	return 0;
 }
 
+static int hpet_resume(void)
+{
+	write_seqlock(&monotonic_lock);
+	/* Assume this is the last mark offset time */
+	rdtsc(last_tsc_low, last_tsc_high);
+
+	if (hpet_use_timer)
+		hpet_last = hpet_readl(HPET_T0_CMP) - hpet_tick;
+	else
+		hpet_last = hpet_readl(HPET_COUNTER);
+	write_sequnlock(&monotonic_lock);
+	return 0;
+}
 /************************************************************/
 
 /* tsc timer_opts struct */
@@ -190,6 +203,7 @@ static struct timer_opts timer_hpet __read_mostly = {
 	.get_offset =		get_offset_hpet,
 	.monotonic_clock =	monotonic_clock_hpet,
 	.delay = 		delay_hpet,
+	.resume	=		hpet_resume,
 };
 
 struct init_timer_opts __initdata timer_hpet_init = {
diff --git a/arch/i386/kernel/timers/timer_pit.c b/arch/i386/kernel/timers/timer_pit.c
index 06de036a820..eddb6403823 100644
--- a/arch/i386/kernel/timers/timer_pit.c
+++ b/arch/i386/kernel/timers/timer_pit.c
@@ -175,30 +175,3 @@ void setup_pit_timer(void)
 	outb(LATCH >> 8 , PIT_CH0);	/* MSB */
 	spin_unlock_irqrestore(&i8253_lock, flags);
 }
-
-static int timer_resume(struct sys_device *dev)
-{
-	setup_pit_timer();
-	return 0;
-}
-
-static struct sysdev_class timer_sysclass = {
-	set_kset_name("timer_pit"),
-	.resume	= timer_resume,
-};
-
-static struct sys_device device_timer = {
-	.id	= 0,
-	.cls	= &timer_sysclass,
-};
-
-static int __init init_timer_sysfs(void)
-{
-	int error = sysdev_class_register(&timer_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
-}
-
-device_initcall(init_timer_sysfs);
-
diff --git a/arch/i386/kernel/timers/timer_pm.c b/arch/i386/kernel/timers/timer_pm.c
index 4ef20e66349..264edaaac31 100644
--- a/arch/i386/kernel/timers/timer_pm.c
+++ b/arch/i386/kernel/timers/timer_pm.c
@@ -186,6 +186,14 @@ static void mark_offset_pmtmr(void)
 	}
 }
 
+static int pmtmr_resume(void)
+{
+	write_seqlock(&monotonic_lock);
+	/* Assume this is the last mark offset time */
+	offset_tick = read_pmtmr();
+	write_sequnlock(&monotonic_lock);
+	return 0;
+}
 
 static unsigned long long monotonic_clock_pmtmr(void)
 {
@@ -247,6 +255,7 @@ static struct timer_opts timer_pmtmr = {
 	.monotonic_clock 	= monotonic_clock_pmtmr,
 	.delay 			= delay_pmtmr,
 	.read_timer 		= read_timer_tsc,
+	.resume			= pmtmr_resume,
 };
 
 struct init_timer_opts __initdata timer_pmtmr_init = {
diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c
index 8f4e4d5bc56..6dd470cc9f7 100644
--- a/arch/i386/kernel/timers/timer_tsc.c
+++ b/arch/i386/kernel/timers/timer_tsc.c
@@ -543,6 +543,19 @@ static int __init init_tsc(char* override)
 	return -ENODEV;
 }
 
+static int tsc_resume(void)
+{
+	write_seqlock(&monotonic_lock);
+	/* Assume this is the last mark offset time */
+	rdtsc(last_tsc_low, last_tsc_high);
+#ifdef CONFIG_HPET_TIMER
+	if (is_hpet_enabled() && hpet_use_timer)
+		hpet_last = hpet_readl(HPET_COUNTER);
+#endif
+	write_sequnlock(&monotonic_lock);
+	return 0;
+}
+
 #ifndef CONFIG_X86_TSC
 /* disable flag for tsc.  Takes effect by clearing the TSC cpu flag
  * in cpu/common.c */
@@ -573,6 +586,7 @@ static struct timer_opts timer_tsc = {
 	.monotonic_clock = monotonic_clock_tsc,
 	.delay = delay_tsc,
 	.read_timer = read_timer_tsc,
+	.resume	= tsc_resume,
 };
 
 struct init_timer_opts __initdata timer_tsc_init = {
diff --git a/include/asm-i386/timer.h b/include/asm-i386/timer.h
index dcf1e07db08..aed16437479 100644
--- a/include/asm-i386/timer.h
+++ b/include/asm-i386/timer.h
@@ -1,6 +1,7 @@
 #ifndef _ASMi386_TIMER_H
 #define _ASMi386_TIMER_H
 #include <linux/init.h>
+#include <linux/pm.h>
 
 /**
  * struct timer_ops - used to define a timer source
@@ -23,6 +24,8 @@ struct timer_opts {
 	unsigned long long (*monotonic_clock)(void);
 	void (*delay)(unsigned long);
 	unsigned long (*read_timer)(void);
+	int (*suspend)(pm_message_t state);
+	int (*resume)(void);
 };
 
 struct init_timer_opts {