mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-28 23:24:50 +00:00
524ccdbdfb
Currently, the XOR module performs its boot time benchmark at core initcall time when it is built-in, to ensure that the RAID code can make use of it when it is built-in as well. Let's defer this to a later stage during the boot, to avoid impacting the overall boot time of the system. Instead, just pick an arbitrary implementation from the list, and use that as the preliminary default. Reviewed-by: Douglas Anderson <dianders@chromium.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
182 lines
3.9 KiB
C
182 lines
3.9 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* xor.c : Multiple Devices driver for Linux
|
|
*
|
|
* Copyright (C) 1996, 1997, 1998, 1999, 2000,
|
|
* Ingo Molnar, Matti Aarnio, Jakub Jelinek, Richard Henderson.
|
|
*
|
|
* Dispatch optimized RAID-5 checksumming functions.
|
|
*/
|
|
|
|
#define BH_TRACE 0
|
|
#include <linux/module.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/raid/xor.h>
|
|
#include <linux/jiffies.h>
|
|
#include <linux/preempt.h>
|
|
#include <asm/xor.h>
|
|
|
|
#ifndef XOR_SELECT_TEMPLATE
|
|
#define XOR_SELECT_TEMPLATE(x) (x)
|
|
#endif
|
|
|
|
/* The xor routines to use. */
|
|
static struct xor_block_template *active_template;
|
|
|
|
void
|
|
xor_blocks(unsigned int src_count, unsigned int bytes, void *dest, void **srcs)
|
|
{
|
|
unsigned long *p1, *p2, *p3, *p4;
|
|
|
|
p1 = (unsigned long *) srcs[0];
|
|
if (src_count == 1) {
|
|
active_template->do_2(bytes, dest, p1);
|
|
return;
|
|
}
|
|
|
|
p2 = (unsigned long *) srcs[1];
|
|
if (src_count == 2) {
|
|
active_template->do_3(bytes, dest, p1, p2);
|
|
return;
|
|
}
|
|
|
|
p3 = (unsigned long *) srcs[2];
|
|
if (src_count == 3) {
|
|
active_template->do_4(bytes, dest, p1, p2, p3);
|
|
return;
|
|
}
|
|
|
|
p4 = (unsigned long *) srcs[3];
|
|
active_template->do_5(bytes, dest, p1, p2, p3, p4);
|
|
}
|
|
EXPORT_SYMBOL(xor_blocks);
|
|
|
|
/* Set of all registered templates. */
|
|
static struct xor_block_template *__initdata template_list;
|
|
|
|
#ifndef MODULE
|
|
static void __init do_xor_register(struct xor_block_template *tmpl)
|
|
{
|
|
tmpl->next = template_list;
|
|
template_list = tmpl;
|
|
}
|
|
|
|
static int __init register_xor_blocks(void)
|
|
{
|
|
active_template = XOR_SELECT_TEMPLATE(NULL);
|
|
|
|
if (!active_template) {
|
|
#define xor_speed do_xor_register
|
|
// register all the templates and pick the first as the default
|
|
XOR_TRY_TEMPLATES;
|
|
#undef xor_speed
|
|
active_template = template_list;
|
|
}
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#define BENCH_SIZE (PAGE_SIZE)
|
|
|
|
static void __init
|
|
do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
|
|
{
|
|
int speed;
|
|
unsigned long now, j;
|
|
int i, count, max;
|
|
|
|
tmpl->next = template_list;
|
|
template_list = tmpl;
|
|
|
|
preempt_disable();
|
|
|
|
/*
|
|
* Count the number of XORs done during a whole jiffy, and use
|
|
* this to calculate the speed of checksumming. We use a 2-page
|
|
* allocation to have guaranteed color L1-cache layout.
|
|
*/
|
|
max = 0;
|
|
for (i = 0; i < 5; i++) {
|
|
j = jiffies;
|
|
count = 0;
|
|
while ((now = jiffies) == j)
|
|
cpu_relax();
|
|
while (time_before(jiffies, now + 1)) {
|
|
mb(); /* prevent loop optimzation */
|
|
tmpl->do_2(BENCH_SIZE, b1, b2);
|
|
mb();
|
|
count++;
|
|
mb();
|
|
}
|
|
if (count > max)
|
|
max = count;
|
|
}
|
|
|
|
preempt_enable();
|
|
|
|
speed = max * (HZ * BENCH_SIZE / 1024);
|
|
tmpl->speed = speed;
|
|
|
|
printk(KERN_INFO " %-10s: %5d.%03d MB/sec\n", tmpl->name,
|
|
speed / 1000, speed % 1000);
|
|
}
|
|
|
|
static int __init
|
|
calibrate_xor_blocks(void)
|
|
{
|
|
void *b1, *b2;
|
|
struct xor_block_template *f, *fastest;
|
|
|
|
fastest = XOR_SELECT_TEMPLATE(NULL);
|
|
|
|
if (fastest) {
|
|
printk(KERN_INFO "xor: automatically using best "
|
|
"checksumming function %-10s\n",
|
|
fastest->name);
|
|
goto out;
|
|
}
|
|
|
|
b1 = (void *) __get_free_pages(GFP_KERNEL, 2);
|
|
if (!b1) {
|
|
printk(KERN_WARNING "xor: Yikes! No memory available.\n");
|
|
return -ENOMEM;
|
|
}
|
|
b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE;
|
|
|
|
/*
|
|
* If this arch/cpu has a short-circuited selection, don't loop through
|
|
* all the possible functions, just test the best one
|
|
*/
|
|
|
|
#define xor_speed(templ) do_xor_speed((templ), b1, b2)
|
|
|
|
printk(KERN_INFO "xor: measuring software checksum speed\n");
|
|
template_list = NULL;
|
|
XOR_TRY_TEMPLATES;
|
|
fastest = template_list;
|
|
for (f = fastest; f; f = f->next)
|
|
if (f->speed > fastest->speed)
|
|
fastest = f;
|
|
|
|
printk(KERN_INFO "xor: using function: %s (%d.%03d MB/sec)\n",
|
|
fastest->name, fastest->speed / 1000, fastest->speed % 1000);
|
|
|
|
#undef xor_speed
|
|
|
|
free_pages((unsigned long)b1, 2);
|
|
out:
|
|
active_template = fastest;
|
|
return 0;
|
|
}
|
|
|
|
static __exit void xor_exit(void) { }
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
#ifndef MODULE
|
|
/* when built-in xor.o must initialize before drivers/md/md.o */
|
|
core_initcall(register_xor_blocks);
|
|
#endif
|
|
|
|
module_init(calibrate_xor_blocks);
|
|
module_exit(xor_exit);
|