kernel_optimize_test/arch/sh/kernel/localtimer.c
Christoph Lameter c473b2c6f6 sh: Replace __get_cpu_var uses
__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)

Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:53:52 -07:00

67 lines
1.5 KiB
C

/*
* Dummy local timer
*
* Copyright (C) 2008 Paul Mundt
*
* cloned from:
*
* linux/arch/arm/mach-realview/localtimer.c
*
* Copyright (C) 2002 ARM Ltd.
* 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 version 2 as
* published by the Free Software Foundation.
*/
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/smp.h>
#include <linux/jiffies.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
#include <linux/hardirq.h>
#include <linux/irq.h>
static DEFINE_PER_CPU(struct clock_event_device, local_clockevent);
/*
* Used on SMP for either the local timer or SMP_MSG_TIMER
*/
void local_timer_interrupt(void)
{
struct clock_event_device *clk = this_cpu_ptr(&local_clockevent);
irq_enter();
clk->event_handler(clk);
irq_exit();
}
static void dummy_timer_set_mode(enum clock_event_mode mode,
struct clock_event_device *clk)
{
}
void local_timer_setup(unsigned int cpu)
{
struct clock_event_device *clk = &per_cpu(local_clockevent, cpu);
clk->name = "dummy_timer";
clk->features = CLOCK_EVT_FEAT_ONESHOT |
CLOCK_EVT_FEAT_PERIODIC |
CLOCK_EVT_FEAT_DUMMY;
clk->rating = 400;
clk->mult = 1;
clk->set_mode = dummy_timer_set_mode;
clk->broadcast = smp_timer_broadcast;
clk->cpumask = cpumask_of(cpu);
clockevents_register_device(clk);
}
void local_timer_stop(unsigned int cpu)
{
}