mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-11 12:28:41 +08:00
191e56880a
Binary chop with a jiffy-resync on each step to find an upper bound is slow, so just race in a tight-ish loop to find an underestimate. If done with lots of individual steps, sometimes several hundreds of iterations would be required, which would impose a significant overhead, and make the initial estimate very low. By taking slowly increasing steps there will be less overhead. E.g. an x86_64 2.67GHz could have fitted in 613 individual small delays, but in reality should have been able to fit in a single delay 644 times longer, so underestimated by 31 steps. To reach the equivalent of 644 small delays with the accelerating scheme now requires about 130 iterations, so has <1/4th of the overhead, and can therefore be expected to underestimate by only 7 steps. As now we have a better initial estimate we can binary chop over a smaller range. With the loop overhead in the initial estimate kept low, and the step sizes moderate, we won't have under-estimated by much, so chose as tight a range as we can. Signed-off-by: Phil Carmody <ext-phil.2.carmody@nokia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Tested-by: Stephen Boyd <sboyd@codeaurora.org> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
201 lines
5.4 KiB
C
201 lines
5.4 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_fine;
|
|
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 timer_rate_min, timer_rate_max;
|
|
unsigned long good_timer_sum = 0;
|
|
unsigned long good_timer_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 (time_before_eq(jiffies, start_jiffies + 1)) {
|
|
pre_start = start;
|
|
read_current_timer(&start);
|
|
}
|
|
read_current_timer(&post_start);
|
|
|
|
pre_end = 0;
|
|
end = post_start;
|
|
while (time_before_eq(jiffies, start_jiffies + 1 +
|
|
DELAY_CALIBRATION_TICKS)) {
|
|
pre_end = end;
|
|
read_current_timer(&end);
|
|
}
|
|
read_current_timer(&post_end);
|
|
|
|
timer_rate_max = (post_end - pre_start) /
|
|
DELAY_CALIBRATION_TICKS;
|
|
timer_rate_min = (pre_end - post_start) /
|
|
DELAY_CALIBRATION_TICKS;
|
|
|
|
/*
|
|
* If the upper limit and lower limit of the timer_rate is
|
|
* >= 12.5% apart, redo calibration.
|
|
*/
|
|
if (pre_start != 0 && pre_end != 0 &&
|
|
(timer_rate_max - timer_rate_min) < (timer_rate_max >> 3)) {
|
|
good_timer_count++;
|
|
good_timer_sum += timer_rate_max;
|
|
}
|
|
}
|
|
|
|
if (good_timer_count)
|
|
return (good_timer_sum/good_timer_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
|
|
* time we refine our estimate after the first takes 1.5/HZ seconds, so try
|
|
* to start with a good estimate.
|
|
* For the boot cpu we can skip the delay calibration and assign it a value
|
|
* calculated based on the timer frequency.
|
|
* For the rest of the CPUs we cannot assume that the timer frequency is same as
|
|
* the cpu frequency, hence do the calibration for those.
|
|
*/
|
|
#define LPS_PREC 8
|
|
|
|
static unsigned long __cpuinit calibrate_delay_converge(void)
|
|
{
|
|
/* First stage - slowly accelerate to find initial bounds */
|
|
unsigned long lpj, ticks, loopadd, chop_limit;
|
|
int trials = 0, band = 0, trial_in_band = 0;
|
|
|
|
lpj = (1<<12);
|
|
|
|
/* wait for "start of" clock tick */
|
|
ticks = jiffies;
|
|
while (ticks == jiffies)
|
|
; /* nothing */
|
|
/* Go .. */
|
|
ticks = jiffies;
|
|
do {
|
|
if (++trial_in_band == (1<<band)) {
|
|
++band;
|
|
trial_in_band = 0;
|
|
}
|
|
__delay(lpj * band);
|
|
trials += band;
|
|
} while (ticks == jiffies);
|
|
/*
|
|
* We overshot, so retreat to a clear underestimate. Then estimate
|
|
* the largest likely undershoot. This defines our chop bounds.
|
|
*/
|
|
trials -= band;
|
|
loopadd = lpj * band;
|
|
lpj *= trials;
|
|
chop_limit = lpj >> (LPS_PREC + 1);
|
|
|
|
/*
|
|
* Do a binary approximation to get lpj set to
|
|
* equal one clock (up to LPS_PREC bits)
|
|
*/
|
|
while (loopadd > chop_limit) {
|
|
lpj += loopadd;
|
|
ticks = jiffies;
|
|
while (ticks == jiffies)
|
|
; /* nothing */
|
|
ticks = jiffies;
|
|
__delay(lpj);
|
|
if (jiffies != ticks) /* longer than 1 tick */
|
|
lpj -= loopadd;
|
|
loopadd >>= 1;
|
|
}
|
|
|
|
return lpj;
|
|
}
|
|
|
|
void __cpuinit calibrate_delay(void)
|
|
{
|
|
static bool printed;
|
|
|
|
if (preset_lpj) {
|
|
loops_per_jiffy = preset_lpj;
|
|
if (!printed)
|
|
pr_info("Calibrating delay loop (skipped) "
|
|
"preset value.. ");
|
|
} else if ((!printed) && lpj_fine) {
|
|
loops_per_jiffy = lpj_fine;
|
|
pr_info("Calibrating delay loop (skipped), "
|
|
"value calculated using timer frequency.. ");
|
|
} else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) {
|
|
if (!printed)
|
|
pr_info("Calibrating delay using timer "
|
|
"specific routine.. ");
|
|
} else {
|
|
if (!printed)
|
|
pr_info("Calibrating delay loop... ");
|
|
loops_per_jiffy = calibrate_delay_converge();
|
|
}
|
|
if (!printed)
|
|
pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n",
|
|
loops_per_jiffy/(500000/HZ),
|
|
(loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy);
|
|
|
|
printed = true;
|
|
}
|