Revision 7fb5409df092589b86cc9412d926879cb572b7f0 authored by Jan Kara on 10 February 2008, 06:08:38 UTC, committed by Theodore Ts'o on 10 February 2008, 06:08:38 UTC
We cannot start transaction in ext4_direct_IO() and just let it last during the whole write because dio_get_page() acquires mmap_sem which ranks above transaction start (e.g. because we have dependency chain mmap_sem->PageLock->journal_start, or because we update atime while holding mmap_sem) and thus deadlocks could happen. We solve the problem by starting a transaction separately for each ext4_get_block() call. We *could* have a problem that we allocate a block and before its data are written out the machine crashes and thus we expose stale data. But that does not happen because for hole-filling generic code falls back to buffered writes and for file extension, we add inode to orphan list and thus in case of crash, journal replay will truncate inode back to the original size. Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
1 parent 8009f9f
xor.c
/*
* 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.
*
* 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, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define BH_TRACE 0
#include <linux/module.h>
#include <linux/raid/md.h>
#include <linux/raid/xor.h>
#include <asm/xor.h>
/* 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 *template_list;
#define BENCH_SIZE (PAGE_SIZE)
static void
do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
{
int speed;
unsigned long now;
int i, count, max;
tmpl->next = template_list;
template_list = tmpl;
/*
* 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++) {
now = jiffies;
count = 0;
while (jiffies == now) {
mb(); /* prevent loop optimzation */
tmpl->do_2(BENCH_SIZE, b1, b2);
mb();
count++;
mb();
}
if (count > max)
max = count;
}
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;
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
*/
fastest = NULL;
#ifdef XOR_SELECT_TEMPLATE
fastest = XOR_SELECT_TEMPLATE(fastest);
#endif
#define xor_speed(templ) do_xor_speed((templ), b1, b2)
if (fastest) {
printk(KERN_INFO "xor: automatically using best "
"checksumming function: %s\n",
fastest->name);
xor_speed(fastest);
} else {
printk(KERN_INFO "xor: measuring software checksum speed\n");
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);
active_template = fastest;
return 0;
}
static __exit void xor_exit(void) { }
MODULE_LICENSE("GPL");
/* when built-in xor.o must initialize before drivers/md/md.o */
core_initcall(calibrate_xor_blocks);
module_exit(xor_exit);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...