From: john stultz <johnstul@us.ibm.com>

On Fri, 2003-11-21 at 11:53, Andrew Morton wrote:
> > Also, I was going to sync up w/ you today and send you my latest version
> > to reduce the number of little fix patches you have to manage, but if
> > you'd prefer I can do that after I track down the issue you're seeing.
> 
> OK, I'll do mm5 this afternoon.  I'll be out of town this weekend, then out
> of the country from Nov27->Dec14 so I'm likely to be even less than usually
> useful for some time.

Here it is then. 

This patch depends on Dominik Brodowski's "acpi-pm-timer" patch found in
mm4. It fixes a compile bug, cleans up the math, adds lost-tick
compensation and monotonic_clock, fixes a bug in the ACPI table mapping
and moves the config option under the ACPI menu. Additionally the patch
includes additional fixes found during testing in -mm3 and -mm4. 

This patch replaces the following broken out patches from -mm4:
	acpi-pm-timer-fixes.patch
	acpi-pm_timer-init-cpu_khz.patch
	timer_pm-fix-fix-fix.patch

Many thanks to Dominik for the great work, and Thomas Schlichter for the
excellent bug hunting!



 Documentation/kernel-parameters.txt     |    2 
 arch/i386/Kconfig                       |   18 -----
 arch/i386/kernel/acpi/boot.c            |   10 ++-
 arch/i386/kernel/timers/common.c        |   20 ++++++
 arch/i386/kernel/timers/timer_cyclone.c |   21 ------
 arch/i386/kernel/timers/timer_pm.c      |  105 +++++++++++++++++++++++++-------
 drivers/acpi/Kconfig                    |   18 +++++
 include/asm-i386/timer.h                |    1 
 8 files changed, 132 insertions(+), 63 deletions(-)

diff -puN arch/i386/Kconfig~acpi-pm-timer-fixes-2 arch/i386/Kconfig
--- 25/arch/i386/Kconfig~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/arch/i386/Kconfig	2003-11-21 13:04:40.000000000 -0800
@@ -411,24 +411,6 @@ config HPET_TIMER
 config HPET_EMULATE_RTC
 	def_bool HPET_TIMER && RTC=y
 
-config X86_PM_TIMER
-	bool "Power Management Timer Support"
-	depends on (!X86_VISWS && !X86_VISWS) && EXPERIMENTAL
-	default n
-	help
-	  The Power Management Timer is available on all ACPI-capable,
-	  in most cases even if ACPI is unusable or blacklisted.
-
-	  This timing source is not affected by powermanagement features
-	  like aggressive processor idling, throttling, frequency and/or
-	  voltage scaling, unlike the commonly used Time Stamp Counter
-	  (TSC) timing source.
-
-	  So, if you see messages like 'Losing too many ticks!' in the
-	  kernel logs, and/or you are using a this on a notebook which
-	  does not yet have an HPET (see above), you should say "Y"
-	  here. Otherwise, say "N".
-
 config SMP
 	bool "Symmetric multi-processing support"
 	---help---
diff -puN arch/i386/kernel/acpi/boot.c~acpi-pm-timer-fixes-2 arch/i386/kernel/acpi/boot.c
--- 25/arch/i386/kernel/acpi/boot.c~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/arch/i386/kernel/acpi/boot.c	2003-11-21 13:04:40.000000000 -0800
@@ -327,15 +327,19 @@ static int __init acpi_parse_hpet(unsign
 }
 #endif
 
-/* detect the location of the ACPI PM Timer
+/* detect the location of the ACPI PM Timer */
 #ifdef CONFIG_X86_PM_TIMER
 extern u32 pmtmr_ioport;
 
 static int __init acpi_parse_fadt(unsigned long phys, unsigned long size)
 {
-	struct fadt_descriptor_rev2 *fadt;
+	struct fadt_descriptor_rev2 *fadt =0;
 
-	fadt = __va(phys);
+	fadt = (struct fadt_descriptor_rev2*) __acpi_map_table(phys,size);
+	if(!fadt) {
+		printk(KERN_WARNING PREFIX "Unable to map FADT\n");
+		return 0;
+	}
 
 	if (fadt->revision >= FADT2_REVISION_ID) {
 		/* FADT rev. 2 */
diff -puN arch/i386/kernel/timers/common.c~acpi-pm-timer-fixes-2 arch/i386/kernel/timers/common.c
--- 25/arch/i386/kernel/timers/common.c~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/arch/i386/kernel/timers/common.c	2003-11-21 13:04:40.000000000 -0800
@@ -137,3 +137,23 @@ bad_calibration:
 }
 #endif
 
+/* calculate cpu_khz */
+void __init init_cpu_khz(void)
+{
+	if (cpu_has_tsc) {
+		unsigned long tsc_quotient = calibrate_tsc();
+		if (tsc_quotient) {
+			/* report CPU clock rate in Hz.
+			 * The formula is (10^6 * 2^32) / (2^32 * 1 / (clocks/us)) =
+			 * clock/second. Our precision is about 100 ppm.
+			 */
+			{	unsigned long eax=0, edx=1000;
+				__asm__("divl %2"
+		       		:"=a" (cpu_khz), "=d" (edx)
+        	       		:"r" (tsc_quotient),
+	                	"0" (eax), "1" (edx));
+				printk("Detected %lu.%03lu MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000);
+			}
+		}
+	}
+}
diff -puN arch/i386/kernel/timers/timer_cyclone.c~acpi-pm-timer-fixes-2 arch/i386/kernel/timers/timer_cyclone.c
--- 25/arch/i386/kernel/timers/timer_cyclone.c~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/arch/i386/kernel/timers/timer_cyclone.c	2003-11-21 13:04:40.000000000 -0800
@@ -212,26 +212,7 @@ static int __init init_cyclone(char* ove
 		}
 	}
 
-	/* init cpu_khz.
-	 * XXX - This should really be done elsewhere, 
-	 * 		and in a more generic fashion. -johnstul@us.ibm.com
-	 */
-	if (cpu_has_tsc) {
-		unsigned long tsc_quotient = calibrate_tsc();
-		if (tsc_quotient) {
-			/* report CPU clock rate in Hz.
-			 * The formula is (10^6 * 2^32) / (2^32 * 1 / (clocks/us)) =
-			 * clock/second. Our precision is about 100 ppm.
-			 */
-			{	unsigned long eax=0, edx=1000;
-				__asm__("divl %2"
-		       		:"=a" (cpu_khz), "=d" (edx)
-        	       		:"r" (tsc_quotient),
-	                	"0" (eax), "1" (edx));
-				printk("Detected %lu.%03lu MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000);
-			}
-		}
-	}
+	init_cpu_khz();
 
 	/* Everything looks good! */
 	return 0;
diff -puN arch/i386/kernel/timers/timer_pm.c~acpi-pm-timer-fixes-2 arch/i386/kernel/timers/timer_pm.c
--- 25/arch/i386/kernel/timers/timer_pm.c~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/arch/i386/kernel/timers/timer_pm.c	2003-11-21 13:04:40.000000000 -0800
@@ -30,7 +30,12 @@ u32 pmtmr_ioport = 0;
 
 /* value of the Power timer at last timer interrupt */
 static u32 offset_tick;
+static u32 offset_delay;
 
+static unsigned long long monotonic_base;
+static seqlock_t monotonic_lock = SEQLOCK_UNLOCKED;
+
+#define ACPI_PM_MASK 0xFFFFFF /* limit it to 24 bits */
 
 static int init_pmtmr(char* override)
 {
@@ -45,41 +50,109 @@ static int init_pmtmr(char* override)
 
 	/* "verify" this timing source */
 	value1 = inl(pmtmr_ioport);
-	value1 &= 0xFFFFFF;
+	value1 &= ACPI_PM_MASK;
 	for (i=0; i < 10000; i++) {
 		value2 = inl(pmtmr_ioport);
-		value2 &= 0xFFFFFF;
+		value2 &= ACPI_PM_MASK;
 		if (value2 == value1)
 			continue;
 		if (value2 > value1)
-			return 0;
+			goto pm_good;
 		if ((value2 < value1) && ((value2) < 0xFFF))
-			return 0;
+			goto pm_good;
 		printk(KERN_INFO "PM-Timer had inconsistent results: 0x%#x, 0x%#x - aborting.\n", value1, value2);
 		return -EINVAL;
 	}
 	printk(KERN_INFO "PM-Timer had no reasonable result: 0x%#x - aborting.\n", value1);
 	return -ENODEV;
+
+pm_good:
+	init_cpu_khz();
+	return 0;
 }
 
+static inline u32 cyc2us(u32 cycles)
+{
+	/* The Power Management Timer ticks at 3.579545 ticks per microsecond.
+	 * 1 / PM_TIMER_FREQUENCY == 0.27936511 =~ 286/1024 [error: 0.024%]
+	 *
+	 * Even with HZ = 100, delta is at maximum 35796 ticks, so it can
+	 * easily be multiplied with 286 (=0x11E) without having to fear
+	 * u32 overflows.
+	 */
+	cycles *= 286;
+	return (cycles >> 10);
+}
 
 /*
  * this gets called during each timer interrupt
+ *   - Called while holding the writer xtime_lock
  */
 static void mark_offset_pmtmr(void)
 {
+	u32 lost, delta, last_offset;
+	static int first_run = 1;
+	last_offset = offset_tick;
+
+	write_seqlock(&monotonic_lock);
+
 	offset_tick = inl(pmtmr_ioport);
-	offset_tick &= 0xFFFFFF; /* limit it to 24 bits */
+	offset_tick &= ACPI_PM_MASK; /* limit it to 24 bits */
+
+	/* calculate tick interval */
+	delta = (offset_tick - last_offset) & ACPI_PM_MASK;
+
+	/* convert to usecs */
+	delta = cyc2us(delta);
+
+	/* update the monotonic base value */
+	monotonic_base += delta*NSEC_PER_USEC;
+	write_sequnlock(&monotonic_lock);
+
+	/* convert to ticks */
+	delta += offset_delay;
+	lost = delta/(USEC_PER_SEC/HZ);
+	offset_delay = delta%(USEC_PER_SEC/HZ);
+
+
+	/* compensate for lost ticks */
+	if (lost >= 2)
+		jiffies += lost - 1;
+
+	/* don't calculate delay for first run,
+	   or if we've got less then a tick */
+	if (first_run || (lost < 1)) {
+		first_run = 0;
+		offset_delay = 0;
+	}
+
 	return;
 }
 
 
 static unsigned long long monotonic_clock_pmtmr(void)
 {
-	return 0;
+	u32 last_offset, this_offset;
+	unsigned long long base, ret;
+	unsigned seq;
+
+
+	/* atomically read monotonic base & last_offset */
+	do {
+		seq = read_seqbegin(&monotonic_lock);
+		last_offset = offset_tick;
+		base = monotonic_base;
+	} while (read_seqretry(&monotonic_lock, seq));
+
+	/* Read the pmtmr */
+	this_offset =  inl(pmtmr_ioport) & ACPI_PM_MASK;
+
+	/* convert to nanoseconds */
+	ret = (this_offset - last_offset) & ACPI_PM_MASK;
+	ret = base + (cyc2us(ret)*NSEC_PER_USEC);
+	return ret;
 }
 
-
 /*
  * copied from delay_pit
  */
@@ -99,6 +172,7 @@ static void delay_pmtmr(unsigned long lo
 
 /*
  * get the offset (in microseconds) from the last call to mark_offset()
+ *	- Called holding a reader xtime_lock
  */
 static unsigned long get_offset_pmtmr(void)
 {
@@ -106,21 +180,10 @@ static unsigned long get_offset_pmtmr(vo
 
 	offset = offset_tick;
 	now = inl(pmtmr_ioport);
-	now &= 0xFFFFFF;
-	if (likely(offset < now))
-		delta = now - offset;
-	else if (offset > now)
-		delta = (0xFFFFFF - offset) + now;
+	now &= ACPI_PM_MASK;
+	delta = (now - offset)&ACPI_PM_MASK;
 
-	/* The Power Management Timer ticks at 3.579545 ticks per microsecond.
-	 * 1 / PM_TIMER_FREQUENCY == 0.27936511 =~ 286/1024 [error: 0.024%]
-	 *
-	 * Even with HZ = 100, delta is at maximum 35796 ticks, so it can
-	 * easily be multiplied with 286 (=0x11E) without having to fear
-	 * u32 overflows.
-	 */
-	delta *= 286;
-	return (unsigned long) (delta >> 10);
+	return (unsigned long) offset_delay + cyc2us(delta);
 }
 
 
diff -puN Documentation/kernel-parameters.txt~acpi-pm-timer-fixes-2 Documentation/kernel-parameters.txt
--- 25/Documentation/kernel-parameters.txt~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/Documentation/kernel-parameters.txt	2003-11-21 13:04:40.000000000 -0800
@@ -214,7 +214,7 @@ running once the system is up.
 			Forces specified timesource (if avaliable) to be used
 			when calculating gettimeofday(). If specicified timesource
 			is not avalible, it defaults to PIT. 
-			Format: { pit | tsc | cyclone | ... }
+			Format: { pit | tsc | cyclone | pmtmr }
 
 	hpet=		[IA-32,HPET] option to disable HPET and use PIT.
 			Format: disable
diff -puN drivers/acpi/Kconfig~acpi-pm-timer-fixes-2 drivers/acpi/Kconfig
--- 25/drivers/acpi/Kconfig~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/drivers/acpi/Kconfig	2003-11-21 13:04:40.000000000 -0800
@@ -263,5 +263,23 @@ config ACPI_RELAXED_AML
 	  particular, many Toshiba laptops require this for correct operation
 	  of the AC module.
 
+config X86_PM_TIMER
+	bool "Power Management Timer Support"
+	depends on X86 && ACPI
+	depends on ACPI_BOOT && EXPERIMENTAL
+	default n
+	help
+	  The Power Management Timer is available on all ACPI-capable,
+	  in most cases even if ACPI is unusable or blacklisted.
+
+	  This timing source is not affected by powermanagement features
+	  like aggressive processor idling, throttling, frequency and/or
+	  voltage scaling, unlike the commonly used Time Stamp Counter
+	  (TSC) timing source.
+
+	  So, if you see messages like 'Losing too many ticks!' in the
+	  kernel logs, and/or you are using a this on a notebook which
+	  does not yet have an HPET, you should say "Y" here.
+
 endmenu
 
diff -puN include/asm-i386/timer.h~acpi-pm-timer-fixes-2 include/asm-i386/timer.h
--- 25/include/asm-i386/timer.h~acpi-pm-timer-fixes-2	2003-11-21 13:04:40.000000000 -0800
+++ 25-akpm/include/asm-i386/timer.h	2003-11-21 13:04:40.000000000 -0800
@@ -40,6 +40,7 @@ extern struct timer_opts timer_cyclone;
 #endif
 
 extern unsigned long calibrate_tsc(void);
+extern void init_cpu_khz(void);
 #ifdef CONFIG_HPET_TIMER
 extern struct timer_opts timer_hpet;
 extern unsigned long calibrate_tsc_hpet(unsigned long *tsc_hpet_quotient_ptr);

_