Revision e4a0d3e720e7e508749c1439b5ba3aff56c92976 authored by Pavel Emelyanov on 18 September 2014, 15:56:17 UTC, committed by Benjamin LaHaise on 13 December 2014, 22:49:50 UTC
There are actually two issues this patch addresses. Let me start with
the one I tried to solve in the beginning.

So, in the checkpoint-restore project (criu) we try to dump tasks'
state and restore one back exactly as it was. One of the tasks' state
bits is rings set up with io_setup() call. There's (almost) no problems
in dumping them, there's a problem restoring them -- if I dump a task
with aio ring originally mapped at address A, I want to restore one
back at exactly the same address A. Unfortunately, the io_setup() does
not allow for that -- it mmaps the ring at whatever place mm finds
appropriate (it calls do_mmap_pgoff() with zero address and without
the MAP_FIXED flag).

To make restore possible I'm going to mremap() the freshly created ring
into the address A (under which it was seen before dump). The problem is
that the ring's virtual address is passed back to the user-space as the
context ID and this ID is then used as search key by all the other io_foo()
calls. Reworking this ID to be just some integer doesn't seem to work, as
this value is already used by libaio as a pointer using which this library
accesses memory for aio meta-data.

So, to make restore work we need to make sure that

a) ring is mapped at desired virtual address
b) kioctx->user_id matches this value

Having said that, the patch makes mremap() on aio region update the
kioctx's user_id and mmap_base values.

Here appears the 2nd issue I mentioned in the beginning of this mail.
If (regardless of the C/R dances I do) someone creates an io context
with io_setup(), then mremap()-s the ring and then destroys the context,
the kill_ioctx() routine will call munmap() on wrong (old) address.
This will result in a) aio ring remaining in memory and b) some other
vma get unexpectedly unmapped.

What do you think?

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
1 parent b2776bf
Raw File
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/gfp.h>
#include <linux/raid/xor.h>
#include <linux/jiffies.h>
#include <linux/preempt.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 *__initdata template_list;

#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;

	/*
	 * Note: Since the memory is not actually used for _anything_ but to
	 * test the XOR speed, we don't really want kmemcheck to warn about
	 * reading uninitialized bytes here.
	 */
	b1 = (void *) __get_free_pages(GFP_KERNEL | __GFP_NOTRACK, 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:\n");
		xor_speed(fastest);
		goto out;
	} 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

 out:
	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);
back to top