87be28aaf1
Now that the ->read_tsc() paravirt hook is gone, rdtscll() is just a wrapper around native_read_tsc(). Unwrap it. Signed-off-by: Andy Lutomirski <luto@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Huang Rui <ray.huang@amd.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Len Brown <lenb@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: kvm ML <kvm@vger.kernel.org> Link: http://lkml.kernel.org/r/d2449ae62c1b1fb90195bcfb19ef4a35883a04dc.1434501121.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
140 lines
2.8 KiB
C
140 lines
2.8 KiB
C
/*
|
|
* Precise Delay Loops for i386
|
|
*
|
|
* Copyright (C) 1993 Linus Torvalds
|
|
* Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
|
|
* Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com>
|
|
*
|
|
* The __delay function must _NOT_ be inlined as its execution time
|
|
* depends wildly on alignment on many x86 processors. The additional
|
|
* jump magic is needed to get the timing stable on all the CPU's
|
|
* we have to worry about.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/timex.h>
|
|
#include <linux/preempt.h>
|
|
#include <linux/delay.h>
|
|
|
|
#include <asm/processor.h>
|
|
#include <asm/delay.h>
|
|
#include <asm/timer.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)
|
|
);
|
|
}
|
|
|
|
/* TSC based delay: */
|
|
static void delay_tsc(unsigned long __loops)
|
|
{
|
|
u32 bclock, now, loops = __loops;
|
|
int cpu;
|
|
|
|
preempt_disable();
|
|
cpu = smp_processor_id();
|
|
rdtsc_barrier();
|
|
rdtscl(bclock);
|
|
for (;;) {
|
|
rdtsc_barrier();
|
|
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();
|
|
rdtsc_barrier();
|
|
rdtscl(bclock);
|
|
}
|
|
}
|
|
preempt_enable();
|
|
}
|
|
|
|
/*
|
|
* Since we calibrate only once at boot, this
|
|
* function should be set once at boot and not changed
|
|
*/
|
|
static void (*delay_fn)(unsigned long) = delay_loop;
|
|
|
|
void use_tsc_delay(void)
|
|
{
|
|
delay_fn = delay_tsc;
|
|
}
|
|
|
|
int read_current_timer(unsigned long *timer_val)
|
|
{
|
|
if (delay_fn == delay_tsc) {
|
|
*timer_val = native_read_tsc();
|
|
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"
|
|
(this_cpu_read(cpu_info.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);
|