aha/init/calibrate.c
Venkatesh Pallipadi 8a9e1b0f56 [PATCH] Platform SMIs and their interferance with tsc based delay calibration
Issue:
Current tsc based delay_calibration can result in significant errors in
loops_per_jiffy count when the platform events like SMIs
(System Management Interrupts that are non-maskable) are present. This could
lead to potential kernel panic(). This issue is becoming more visible with 2.6
kernel (as default HZ is 1000) and on platforms with higher SMI handling
latencies. During the boot time, SMIs are mostly used by BIOS (for things
like legacy keyboard emulation).

Description:
The psuedocode for current delay calibration with tsc based delay looks like
(0) Estimate a value for loops_per_jiffy
(1) While (loops_per_jiffy estimate is accurate enough)
(2)   wait for jiffy transition (jiffy1)
(3)   Note down current tsc (tsc1)
(4)   loop until tsc becomes tsc1 + loops_per_jiffy
(5)   check whether jiffy changed since jiffy1 or not and refine
loops_per_jiffy estimate

Consider the following cases
Case 1:
If SMIs happen between (2) and (3) above, we can end up with a
loops_per_jiffy value that is too low. This results in shorted delays and
kernel can panic () during boot (Mostly at IOAPIC timer initialization
timer_irq_works() as we don't have enough timer interrupts in a specified
interval).

Case 2:
If SMIs happen between (3) and (4) above, then we can end up with a
loops_per_jiffy value that is too high. And with current i386 code, too
high lpj value (greater than 17M) can result in a overflow in
delay.c:__const_udelay() again resulting in shorter delay and panic().

Solution:
The patch below makes the calibration routine aware of asynchronous events
like SMIs. We increase the delay calibration time and also identify any
significant errors (greater than 12.5%) in the calibration and notify it to
user.

Patch below changes both i386 and x86-64 architectures to use this
new and improved calibrate_delay_direct() routine.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 09:45:08 -07:00

173 lines
4.7 KiB
C

/* calibrate.c: default delay calibration
*
* Excised from init/main.c
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <asm/timex.h>
static 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 __devinit 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 __devinit 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%
*/
#define LPS_PREC 8
void __devinit calibrate_delay(void)
{
unsigned long ticks, loopbit;
int lps_precision = LPS_PREC;
if (preset_lpj) {
loops_per_jiffy = preset_lpj;
printk("Calibrating delay loop (skipped)... "
"%lu.%02lu BogoMIPS preset\n",
loops_per_jiffy/(500000/HZ),
(loops_per_jiffy/(5000/HZ)) % 100);
} else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) {
printk("Calibrating delay using timer specific routine.. ");
printk("%lu.%02lu BogoMIPS (lpj=%lu)\n",
loops_per_jiffy/(500000/HZ),
(loops_per_jiffy/(5000/HZ)) % 100,
loops_per_jiffy);
} else {
loops_per_jiffy = (1<<12);
printk(KERN_DEBUG "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;
}
/* Round the value and print it */
printk("%lu.%02lu BogoMIPS (lpj=%lu)\n",
loops_per_jiffy/(500000/HZ),
(loops_per_jiffy/(5000/HZ)) % 100,
loops_per_jiffy);
}
}