mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-23 04:34:11 +08:00
058e3739f6
Currently, all existing users of cnt32_to_63() are fine since the CPU architectures where it is used don't do read access reordering, and user mode preemption is disabled already. It is nevertheless a good idea to better elaborate usage requirements wrt preemption, and use an explicit memory barrier on SMP to avoid different CPUs accessing the counter value in the wrong order. On UP a simple compiler barrier is sufficient. Signed-off-by: Nicolas Pitre <nico@marvell.com> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
91 lines
3.1 KiB
C
91 lines
3.1 KiB
C
/*
|
|
* Extend a 32-bit counter to 63 bits
|
|
*
|
|
* Author: Nicolas Pitre
|
|
* Created: December 3, 2006
|
|
* Copyright: MontaVista Software, Inc.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2
|
|
* as published by the Free Software Foundation.
|
|
*/
|
|
|
|
#ifndef __LINUX_CNT32_TO_63_H__
|
|
#define __LINUX_CNT32_TO_63_H__
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/types.h>
|
|
#include <asm/byteorder.h>
|
|
#include <asm/system.h>
|
|
|
|
/* this is used only to give gcc a clue about good code generation */
|
|
union cnt32_to_63 {
|
|
struct {
|
|
#if defined(__LITTLE_ENDIAN)
|
|
u32 lo, hi;
|
|
#elif defined(__BIG_ENDIAN)
|
|
u32 hi, lo;
|
|
#endif
|
|
};
|
|
u64 val;
|
|
};
|
|
|
|
|
|
/**
|
|
* cnt32_to_63 - Expand a 32-bit counter to a 63-bit counter
|
|
* @cnt_lo: The low part of the counter
|
|
*
|
|
* Many hardware clock counters are only 32 bits wide and therefore have
|
|
* a relatively short period making wrap-arounds rather frequent. This
|
|
* is a problem when implementing sched_clock() for example, where a 64-bit
|
|
* non-wrapping monotonic value is expected to be returned.
|
|
*
|
|
* To overcome that limitation, let's extend a 32-bit counter to 63 bits
|
|
* in a completely lock free fashion. Bits 0 to 31 of the clock are provided
|
|
* by the hardware while bits 32 to 62 are stored in memory. The top bit in
|
|
* memory is used to synchronize with the hardware clock half-period. When
|
|
* the top bit of both counters (hardware and in memory) differ then the
|
|
* memory is updated with a new value, incrementing it when the hardware
|
|
* counter wraps around.
|
|
*
|
|
* Because a word store in memory is atomic then the incremented value will
|
|
* always be in synch with the top bit indicating to any potential concurrent
|
|
* reader if the value in memory is up to date or not with regards to the
|
|
* needed increment. And any race in updating the value in memory is harmless
|
|
* as the same value would simply be stored more than once.
|
|
*
|
|
* The restrictions for the algorithm to work properly are:
|
|
*
|
|
* 1) this code must be called at least once per each half period of the
|
|
* 32-bit counter;
|
|
*
|
|
* 2) this code must not be preempted for a duration longer than the
|
|
* 32-bit counter half period minus the longest period between two
|
|
* calls to this code.
|
|
*
|
|
* Those requirements ensure proper update to the state bit in memory.
|
|
* This is usually not a problem in practice, but if it is then a kernel
|
|
* timer should be scheduled to manage for this code to be executed often
|
|
* enough.
|
|
*
|
|
* Note that the top bit (bit 63) in the returned value should be considered
|
|
* as garbage. It is not cleared here because callers are likely to use a
|
|
* multiplier on the returned value which can get rid of the top bit
|
|
* implicitly by making the multiplier even, therefore saving on a runtime
|
|
* clear-bit instruction. Otherwise caller must remember to clear the top
|
|
* bit explicitly.
|
|
*/
|
|
#define cnt32_to_63(cnt_lo) \
|
|
({ \
|
|
static u32 __m_cnt_hi; \
|
|
union cnt32_to_63 __x; \
|
|
__x.hi = __m_cnt_hi; \
|
|
smp_rmb(); \
|
|
__x.lo = (cnt_lo); \
|
|
if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
|
|
__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
|
|
__x.val; \
|
|
})
|
|
|
|
#endif
|