Christoph Lameter 2999a4b354 alpha: Replace __get_cpu_var
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

CC: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Acked-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-26 13:45:53 -04:00

236 lines
5.3 KiB
C

/*
* Definitions for measuring cputime on powerpc machines.
*
* Copyright (C) 2006 Paul Mackerras, IBM Corp.
*
* 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; either version
* 2 of the License, or (at your option) any later version.
*
* If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in
* the same units as the timebase. Otherwise we measure cpu time
* in jiffies using the generic definitions.
*/
#ifndef __POWERPC_CPUTIME_H
#define __POWERPC_CPUTIME_H
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
#include <asm-generic/cputime.h>
#ifdef __KERNEL__
static inline void setup_cputime_one_jiffy(void) { }
#endif
#else
#include <linux/types.h>
#include <linux/time.h>
#include <asm/div64.h>
#include <asm/time.h>
#include <asm/param.h>
typedef u64 __nocast cputime_t;
typedef u64 __nocast cputime64_t;
#ifdef __KERNEL__
/*
* One jiffy in timebase units computed during initialization
*/
extern cputime_t cputime_one_jiffy;
/*
* Convert cputime <-> jiffies
*/
extern u64 __cputime_jiffies_factor;
DECLARE_PER_CPU(unsigned long, cputime_last_delta);
DECLARE_PER_CPU(unsigned long, cputime_scaled_last_delta);
static inline unsigned long cputime_to_jiffies(const cputime_t ct)
{
return mulhdu((__force u64) ct, __cputime_jiffies_factor);
}
/* Estimate the scaled cputime by scaling the real cputime based on
* the last scaled to real ratio */
static inline cputime_t cputime_to_scaled(const cputime_t ct)
{
if (cpu_has_feature(CPU_FTR_SPURR) &&
__this_cpu_read(cputime_last_delta))
return (__force u64) ct *
__this_cpu_read(cputime_scaled_last_delta) /
__this_cpu_read(cputime_last_delta);
return ct;
}
static inline cputime_t jiffies_to_cputime(const unsigned long jif)
{
u64 ct;
unsigned long sec;
/* have to be a little careful about overflow */
ct = jif % HZ;
sec = jif / HZ;
if (ct) {
ct *= tb_ticks_per_sec;
do_div(ct, HZ);
}
if (sec)
ct += (cputime_t) sec * tb_ticks_per_sec;
return (__force cputime_t) ct;
}
static inline void setup_cputime_one_jiffy(void)
{
cputime_one_jiffy = jiffies_to_cputime(1);
}
static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
{
u64 ct;
u64 sec;
/* have to be a little careful about overflow */
ct = jif % HZ;
sec = jif / HZ;
if (ct) {
ct *= tb_ticks_per_sec;
do_div(ct, HZ);
}
if (sec)
ct += (u64) sec * tb_ticks_per_sec;
return (__force cputime64_t) ct;
}
static inline u64 cputime64_to_jiffies64(const cputime_t ct)
{
return mulhdu((__force u64) ct, __cputime_jiffies_factor);
}
/*
* Convert cputime <-> microseconds
*/
extern u64 __cputime_usec_factor;
static inline unsigned long cputime_to_usecs(const cputime_t ct)
{
return mulhdu((__force u64) ct, __cputime_usec_factor);
}
static inline cputime_t usecs_to_cputime(const unsigned long us)
{
u64 ct;
unsigned long sec;
/* have to be a little careful about overflow */
ct = us % 1000000;
sec = us / 1000000;
if (ct) {
ct *= tb_ticks_per_sec;
do_div(ct, 1000000);
}
if (sec)
ct += (cputime_t) sec * tb_ticks_per_sec;
return (__force cputime_t) ct;
}
#define usecs_to_cputime64(us) usecs_to_cputime(us)
/*
* Convert cputime <-> seconds
*/
extern u64 __cputime_sec_factor;
static inline unsigned long cputime_to_secs(const cputime_t ct)
{
return mulhdu((__force u64) ct, __cputime_sec_factor);
}
static inline cputime_t secs_to_cputime(const unsigned long sec)
{
return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
}
/*
* Convert cputime <-> timespec
*/
static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
{
u64 x = (__force u64) ct;
unsigned int frac;
frac = do_div(x, tb_ticks_per_sec);
p->tv_sec = x;
x = (u64) frac * 1000000000;
do_div(x, tb_ticks_per_sec);
p->tv_nsec = x;
}
static inline cputime_t timespec_to_cputime(const struct timespec *p)
{
u64 ct;
ct = (u64) p->tv_nsec * tb_ticks_per_sec;
do_div(ct, 1000000000);
return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
}
/*
* Convert cputime <-> timeval
*/
static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
{
u64 x = (__force u64) ct;
unsigned int frac;
frac = do_div(x, tb_ticks_per_sec);
p->tv_sec = x;
x = (u64) frac * 1000000;
do_div(x, tb_ticks_per_sec);
p->tv_usec = x;
}
static inline cputime_t timeval_to_cputime(const struct timeval *p)
{
u64 ct;
ct = (u64) p->tv_usec * tb_ticks_per_sec;
do_div(ct, 1000000);
return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
}
/*
* Convert cputime <-> clock_t (units of 1/USER_HZ seconds)
*/
extern u64 __cputime_clockt_factor;
static inline unsigned long cputime_to_clock_t(const cputime_t ct)
{
return mulhdu((__force u64) ct, __cputime_clockt_factor);
}
static inline cputime_t clock_t_to_cputime(const unsigned long clk)
{
u64 ct;
unsigned long sec;
/* have to be a little careful about overflow */
ct = clk % USER_HZ;
sec = clk / USER_HZ;
if (ct) {
ct *= tb_ticks_per_sec;
do_div(ct, USER_HZ);
}
if (sec)
ct += (u64) sec * tb_ticks_per_sec;
return (__force cputime_t) ct;
}
#define cputime64_to_clock_t(ct) cputime_to_clock_t((cputime_t)(ct))
static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
#endif /* __KERNEL__ */
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#endif /* __POWERPC_CPUTIME_H */