The current implementations of __ndelay and __udelay call a hypervisor service to delay, but the hypervisor service isn't actually implemented very well, and the consensus is that Linux should handle figuring this out natively and not use a hypervisor service. By converting nanoseconds to cycles, and then spinning until the cycle counter reaches the desired cycle, we get several benefits: first, we are sensitive to the actual clock speed; second, we use less power by issuing a slow SPR read once every six cycles while we delay; and third, we properly handle the case of an interrupt by exiting at the target time rather than after some number of cycles. Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
		
			
				
	
	
		
			45 lines
		
	
	
	
		
			1.2 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			45 lines
		
	
	
	
		
			1.2 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 * Copyright 2010 Tilera Corporation. All Rights Reserved.
 | 
						|
 *
 | 
						|
 *   This program is free software; you can redistribute it and/or
 | 
						|
 *   modify it under the terms of the GNU General Public License
 | 
						|
 *   as published by the Free Software Foundation, version 2.
 | 
						|
 *
 | 
						|
 *   This program is distributed in the hope that it will be useful, but
 | 
						|
 *   WITHOUT ANY WARRANTY; without even the implied warranty of
 | 
						|
 *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
 | 
						|
 *   NON INFRINGEMENT.  See the GNU General Public License for
 | 
						|
 *   more details.
 | 
						|
 */
 | 
						|
 | 
						|
#include <linux/module.h>
 | 
						|
#include <linux/delay.h>
 | 
						|
#include <linux/thread_info.h>
 | 
						|
#include <asm/timex.h>
 | 
						|
 | 
						|
void __udelay(unsigned long usecs)
 | 
						|
{
 | 
						|
	if (usecs > ULONG_MAX / 1000) {
 | 
						|
		WARN_ON_ONCE(usecs > ULONG_MAX / 1000);
 | 
						|
		usecs = ULONG_MAX / 1000;
 | 
						|
	}
 | 
						|
	__ndelay(usecs * 1000);
 | 
						|
}
 | 
						|
EXPORT_SYMBOL(__udelay);
 | 
						|
 | 
						|
void __ndelay(unsigned long nsecs)
 | 
						|
{
 | 
						|
	cycles_t target = get_cycles();
 | 
						|
	target += ns2cycles(nsecs);
 | 
						|
	while (get_cycles() < target)
 | 
						|
		cpu_relax();
 | 
						|
}
 | 
						|
EXPORT_SYMBOL(__ndelay);
 | 
						|
 | 
						|
void __delay(unsigned long cycles)
 | 
						|
{
 | 
						|
	cycles_t target = get_cycles() + cycles;
 | 
						|
	while (get_cycles() < target)
 | 
						|
		cpu_relax();
 | 
						|
}
 | 
						|
EXPORT_SYMBOL(__delay);
 |