AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

x86: integrate delay functions.

Browse Source 
delay_32.c, delay_64.c are now equal, and are integrated into delay.c.

Signed-off-by: Glauber Costa <gcosta@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Glauber Costa 2008-07-03 12:35:41 -03:00 committed by Ingo Molnar
parent 7e58818d32
commit f0fbf0abc0
3 changed files with 6 additions and 135 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
arch/x86/lib/Makefile
View File

@ -4,7 +4,7 @@
obj-$(CONFIG_SMP) := msr-on-cpu.o
lib-y := delay_$(BITS).o
lib-y := delay.o
lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o
lib-y += memcpy_$(BITS).o

11
arch/x86/lib/delay_32.c → arch/x86/lib/delay.c
View File

@ -29,7 +29,7 @@
/* simple loop based delay: */
static void delay_loop(unsigned long loops)
{
__asm__ __volatile__(
asm volatile(
" test %0,%0 \n"
" jz 3f \n"
" jmp 1f \n"
@ -108,31 +108,30 @@ void __delay(unsigned long loops)
{
delay_fn(loops);
}
EXPORT_SYMBOL(__delay);
inline void __const_udelay(unsigned long xloops)
{
int d0;
xloops *= 4;
__asm__("mull %%edx"
asm("mull %%edx"
:"=d" (xloops), "=&a" (d0)
:"1" (xloops), "0"
(cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
__delay(++xloops);
}
EXPORT_SYMBOL(__const_udelay);
void __udelay(unsigned long usecs)
{
__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
}
EXPORT_SYMBOL(__udelay);
void __ndelay(unsigned long nsecs)
{
__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
}
EXPORT_SYMBOL(__delay);
EXPORT_SYMBOL(__const_udelay);
EXPORT_SYMBOL(__udelay);
EXPORT_SYMBOL(__ndelay);

128
arch/x86/lib/delay_64.c
View File

@ -1,128 +0,0 @@
/*
* 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/module.h>
#include <linux/sched.h>
#include <linux/timex.h>
#include <linux/preempt.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <asm/delay.h>
#include <asm/msr.h>
#ifdef CONFIG_SMP
#include <asm/smp.h>
#endif
/* simple loop based delay: */
static void delay_loop(unsigned long loops)
{
asm volatile(
" test %0,%0 \n"
" jz 3f \n"
" jmp 1f \n"
".align 16 \n"
"1: jmp 2f \n"
".align 16 \n"
"2: dec %0 \n"
" jnz 2b \n"
"3: dec %0 \n"
: /* we don't need output */
:"a" (loops)
);
}
static void delay_tsc(unsigned long loops)
{
unsigned bclock, now;
int cpu;
preempt_disable();
cpu = smp_processor_id();
rdtscl(bclock);
for (;;) {
rdtscl(now);
if ((now - bclock) >= loops)
break;
/* Allow RT tasks to run */
preempt_enable();
rep_nop();
preempt_disable();
/*
* It is possible that we moved to another CPU, and
* since TSC's are per-cpu we need to calculate
* that. The delay must guarantee that we wait "at
* least" the amount of time. Being moved to another
* CPU could make the wait longer but we just need to
* make sure we waited long enough. Rebalance the
* counter for this CPU.
*/
if (unlikely(cpu != smp_processor_id())) {
loops -= (now - bclock);
cpu = smp_processor_id();
rdtscl(bclock);
}
}
preempt_enable();
}
static void (*delay_fn)(unsigned long) = delay_loop;
void use_tsc_delay(void)
{
delay_fn = delay_tsc;
}
int __devinit read_current_timer(unsigned long *timer_value)
{
if (delay_fn == delay_tsc) {
rdtscll(*timer_value);
return 0;
}
return -1;
}
void __delay(unsigned long loops)
{
delay_fn(loops);
}
EXPORT_SYMBOL(__delay);
inline void __const_udelay(unsigned long xloops)
{
int d0;
xloops *= 4;
__asm__("mull %%edx"
:"=d" (xloops), "=&a" (d0)
:"1" (xloops), "0"
(cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
__delay(++xloops);
}
EXPORT_SYMBOL(__const_udelay);
void __udelay(unsigned long usecs)
{
__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
}
EXPORT_SYMBOL(__udelay);
void __ndelay(unsigned long nsecs)
{
__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
}
EXPORT_SYMBOL(__ndelay);