Revision 72853e2991a2702ae93aaf889ac7db743a415dd3 authored by Mel Gorman on 09 September 2010, 23:38:16 UTC, committed by Linus Torvalds on 10 September 2010, 01:57:25 UTC
When allocating a page, the system uses NR_FREE_PAGES counters to determine if watermarks would remain intact after the allocation was made. This check is made without interrupts disabled or the zone lock held and so is race-prone by nature. Unfortunately, when pages are being freed in batch, the counters are updated before the pages are added on the list. During this window, the counters are misleading as the pages do not exist yet. When under significant pressure on systems with large numbers of CPUs, it's possible for processes to make progress even though they should have been stalled. This is particularly problematic if a number of the processes are using GFP_ATOMIC as the min watermark can be accidentally breached and in extreme cases, the system can livelock. This patch updates the counters after the pages have been added to the list. This makes the allocator more cautious with respect to preserving the watermarks and mitigates livelock possibilities. [akpm@linux-foundation.org: avoid modifying incoming args] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Christoph Lameter <cl@linux.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5ee28a4
div64.c
/*
* Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
*
* Based on former do_div() implementation from asm-parisc/div64.h:
* Copyright (C) 1999 Hewlett-Packard Co
* Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com>
*
*
* Generic C version of 64bit/32bit division and modulo, with
* 64bit result and 32bit remainder.
*
* The fast case for (n>>32 == 0) is handled inline by do_div().
*
* Code generated for this function might be very inefficient
* for some CPUs. __div64_32() can be overridden by linking arch-specific
* assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
*/
#include <linux/module.h>
#include <linux/math64.h>
/* Not needed on 64bit architectures */
#if BITS_PER_LONG == 32
uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
{
uint64_t rem = *n;
uint64_t b = base;
uint64_t res, d = 1;
uint32_t high = rem >> 32;
/* Reduce the thing a bit first */
res = 0;
if (high >= base) {
high /= base;
res = (uint64_t) high << 32;
rem -= (uint64_t) (high*base) << 32;
}
while ((int64_t)b > 0 && b < rem) {
b = b+b;
d = d+d;
}
do {
if (rem >= b) {
rem -= b;
res += d;
}
b >>= 1;
d >>= 1;
} while (d);
*n = res;
return rem;
}
EXPORT_SYMBOL(__div64_32);
#ifndef div_s64_rem
s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
{
u64 quotient;
if (dividend < 0) {
quotient = div_u64_rem(-dividend, abs(divisor), (u32 *)remainder);
*remainder = -*remainder;
if (divisor > 0)
quotient = -quotient;
} else {
quotient = div_u64_rem(dividend, abs(divisor), (u32 *)remainder);
if (divisor < 0)
quotient = -quotient;
}
return quotient;
}
EXPORT_SYMBOL(div_s64_rem);
#endif
/* 64bit divisor, dividend and result. dynamic precision */
#ifndef div64_u64
u64 div64_u64(u64 dividend, u64 divisor)
{
u32 high, d;
high = divisor >> 32;
if (high) {
unsigned int shift = fls(high);
d = divisor >> shift;
dividend >>= shift;
} else
d = divisor;
return div_u64(dividend, d);
}
EXPORT_SYMBOL(div64_u64);
#endif
#endif /* BITS_PER_LONG == 32 */
/*
* Iterative div/mod for use when dividend is not expected to be much
* bigger than divisor.
*/
u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
{
return __iter_div_u64_rem(dividend, divisor, remainder);
}
EXPORT_SYMBOL(iter_div_u64_rem);
Computing file changes ...
