aha/init/calibrate.c
Alok Kataria 3da757daf8 x86: use cpu_khz for loops_per_jiffy calculation
On the x86 platform we can use the value of tsc_khz computed during tsc
calibration to calculate the loops_per_jiffy value. Its very important
to keep the error in lpj values to minimum as any error in that may
result in kernel panic in check_timer. In virtualization environment, On
a highly overloaded host the guest delay calibration may sometimes
result in errors beyond the ~50% that timer_irq_works can handle,
resulting in the guest panicking.

Does some formating changes to lpj_setup code to now have a single
printk to print the bogomips value.

We do this only for the boot processor because the AP's can have
different base frequencies or the BIOS might boot a AP at a different
frequency.

Signed-off-by: Alok N Kataria <akataria@vmware.com>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Daniel Hecht <dhecht@vmware.com>
Cc: Tim Mann <mann@vmware.com>
Cc: Zach Amsden <zach@vmware.com>
Cc: Sahil Rihan <srihan@vmware.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-06-23 22:51:33 +02:00

174 lines
4.9 KiB
C

/* calibrate.c: default delay calibration
*
* Excised from init/main.c
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/jiffies.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/timex.h>
#include <linux/smp.h>
unsigned long lpj_tsc;
unsigned long preset_lpj;
static int __init lpj_setup(char *str)
{
preset_lpj = simple_strtoul(str,NULL,0);
return 1;
}
__setup("lpj=", lpj_setup);
#ifdef ARCH_HAS_READ_CURRENT_TIMER
/* This routine uses the read_current_timer() routine and gets the
* loops per jiffy directly, instead of guessing it using delay().
* Also, this code tries to handle non-maskable asynchronous events
* (like SMIs)
*/
#define DELAY_CALIBRATION_TICKS ((HZ < 100) ? 1 : (HZ/100))
#define MAX_DIRECT_CALIBRATION_RETRIES 5
static unsigned long __cpuinit calibrate_delay_direct(void)
{
unsigned long pre_start, start, post_start;
unsigned long pre_end, end, post_end;
unsigned long start_jiffies;
unsigned long tsc_rate_min, tsc_rate_max;
unsigned long good_tsc_sum = 0;
unsigned long good_tsc_count = 0;
int i;
if (read_current_timer(&pre_start) < 0 )
return 0;
/*
* A simple loop like
* while ( jiffies < start_jiffies+1)
* start = read_current_timer();
* will not do. As we don't really know whether jiffy switch
* happened first or timer_value was read first. And some asynchronous
* event can happen between these two events introducing errors in lpj.
*
* So, we do
* 1. pre_start <- When we are sure that jiffy switch hasn't happened
* 2. check jiffy switch
* 3. start <- timer value before or after jiffy switch
* 4. post_start <- When we are sure that jiffy switch has happened
*
* Note, we don't know anything about order of 2 and 3.
* Now, by looking at post_start and pre_start difference, we can
* check whether any asynchronous event happened or not
*/
for (i = 0; i < MAX_DIRECT_CALIBRATION_RETRIES; i++) {
pre_start = 0;
read_current_timer(&start);
start_jiffies = jiffies;
while (jiffies <= (start_jiffies + 1)) {
pre_start = start;
read_current_timer(&start);
}
read_current_timer(&post_start);
pre_end = 0;
end = post_start;
while (jiffies <=
(start_jiffies + 1 + DELAY_CALIBRATION_TICKS)) {
pre_end = end;
read_current_timer(&end);
}
read_current_timer(&post_end);
tsc_rate_max = (post_end - pre_start) / DELAY_CALIBRATION_TICKS;
tsc_rate_min = (pre_end - post_start) / DELAY_CALIBRATION_TICKS;
/*
* If the upper limit and lower limit of the tsc_rate is
* >= 12.5% apart, redo calibration.
*/
if (pre_start != 0 && pre_end != 0 &&
(tsc_rate_max - tsc_rate_min) < (tsc_rate_max >> 3)) {
good_tsc_count++;
good_tsc_sum += tsc_rate_max;
}
}
if (good_tsc_count)
return (good_tsc_sum/good_tsc_count);
printk(KERN_WARNING "calibrate_delay_direct() failed to get a good "
"estimate for loops_per_jiffy.\nProbably due to long platform interrupts. Consider using \"lpj=\" boot option.\n");
return 0;
}
#else
static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
#endif
/*
* This is the number of bits of precision for the loops_per_jiffy. Each
* bit takes on average 1.5/HZ seconds. This (like the original) is a little
* better than 1%
* For the boot cpu we can skip the delay calibration and assign it a value
* calculated based on the tsc frequency.
* For the rest of the CPUs we cannot assume that the tsc frequency is same as
* the cpu frequency, hence do the calibration for those.
*/
#define LPS_PREC 8
void __cpuinit calibrate_delay(void)
{
unsigned long ticks, loopbit;
int lps_precision = LPS_PREC;
if (preset_lpj) {
loops_per_jiffy = preset_lpj;
printk(KERN_INFO
"Calibrating delay loop (skipped) preset value.. ");
} else if ((smp_processor_id() == 0) && lpj_tsc) {
loops_per_jiffy = lpj_tsc;
printk(KERN_INFO
"Calibrating delay loop (skipped), "
"using tsc calculated value.. ");
} else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) {
printk(KERN_INFO
"Calibrating delay using timer specific routine.. ");
} else {
loops_per_jiffy = (1<<12);
printk(KERN_INFO "Calibrating delay loop... ");
while ((loops_per_jiffy <<= 1) != 0) {
/* wait for "start of" clock tick */
ticks = jiffies;
while (ticks == jiffies)
/* nothing */;
/* Go .. */
ticks = jiffies;
__delay(loops_per_jiffy);
ticks = jiffies - ticks;
if (ticks)
break;
}
/*
* Do a binary approximation to get loops_per_jiffy set to
* equal one clock (up to lps_precision bits)
*/
loops_per_jiffy >>= 1;
loopbit = loops_per_jiffy;
while (lps_precision-- && (loopbit >>= 1)) {
loops_per_jiffy |= loopbit;
ticks = jiffies;
while (ticks == jiffies)
/* nothing */;
ticks = jiffies;
__delay(loops_per_jiffy);
if (jiffies != ticks) /* longer than 1 tick */
loops_per_jiffy &= ~loopbit;
}
}
printk(KERN_INFO "%lu.%02lu BogoMIPS (lpj=%lu)\n",
loops_per_jiffy/(500000/HZ),
(loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy);
}