mirror of
https://github.com/FEX-Emu/linux.git
synced 2024-12-18 15:09:53 +00:00
79c62cf178
The attempt to avoid overflow in __delay caused varying precision on different CPUs depending on differences in the CPU speed. We should be able to do this multiplication with out overflowing provided the cpu is running at less than about 128 GHz. xloops < 20000 * 0x10c6. loops_per_jiffy * HZ <= cpu_clock_speed. So if the cpu clock speed < 2^64/(20000 * 0x10c6) = 2^64/ 51E6CC0 < 2^64/2^27 = 2^37 = 128G we will not overflow the calculation. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
54 lines
1.0 KiB
C
54 lines
1.0 KiB
C
/*
|
|
* Precise Delay Loops for x86-64
|
|
*
|
|
* Copyright (C) 1993 Linus Torvalds
|
|
* Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
|
|
*
|
|
* The __delay function must _NOT_ be inlined as its execution time
|
|
* depends wildly on alignment on many x86 processors.
|
|
*/
|
|
|
|
#include <linux/config.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/delay.h>
|
|
#include <asm/delay.h>
|
|
#include <asm/msr.h>
|
|
|
|
#ifdef CONFIG_SMP
|
|
#include <asm/smp.h>
|
|
#endif
|
|
|
|
int read_current_timer(unsigned long *timer_value)
|
|
{
|
|
rdtscll(*timer_value);
|
|
return 0;
|
|
}
|
|
|
|
void __delay(unsigned long loops)
|
|
{
|
|
unsigned bclock, now;
|
|
|
|
rdtscl(bclock);
|
|
do
|
|
{
|
|
rep_nop();
|
|
rdtscl(now);
|
|
}
|
|
while((now-bclock) < loops);
|
|
}
|
|
|
|
inline void __const_udelay(unsigned long xloops)
|
|
{
|
|
__delay((xloops * HZ * cpu_data[raw_smp_processor_id()].loops_per_jiffy) >> 32);
|
|
}
|
|
|
|
void __udelay(unsigned long usecs)
|
|
{
|
|
__const_udelay(usecs * 0x000010c6); /* 2**32 / 1000000 */
|
|
}
|
|
|
|
void __ndelay(unsigned long nsecs)
|
|
{
|
|
__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
|
|
}
|