Skip to main content

Browse the archive

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 
mm: page allocator: update free page counters after pages are placed on the free list
 
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
Raw File
ioremap.c 
/*
 * Re-map IO memory to kernel address space so that we can access it.
 * This is needed for high PCI addresses that aren't mapped in the
 * 640k-1MB IO memory area on PC's
 *
 * (C) Copyright 1995 1996 Linus Torvalds
 */
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/io.h>
#include <asm/cacheflush.h>
#include <asm/pgtable.h>

static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
	pte_t *pte;
	u64 pfn;

	pfn = phys_addr >> PAGE_SHIFT;
	pte = pte_alloc_kernel(pmd, addr);
	if (!pte)
		return -ENOMEM;
	do {
		BUG_ON(!pte_none(*pte));
		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	return 0;
}

static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
	pmd_t *pmd;
	unsigned long next;

	phys_addr -= addr;
	pmd = pmd_alloc(&init_mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
	pud_t *pud;
	unsigned long next;

	phys_addr -= addr;
	pud = pud_alloc(&init_mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

int ioremap_page_range(unsigned long addr,
		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long start;
	unsigned long next;
	int err;

	BUG_ON(addr >= end);

	start = addr;
	phys_addr -= addr;
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	flush_cache_vmap(start, end);

	return err;
}
back to top