path: root/mm/page-writeback.c

/*
 * mm/page-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains functions related to writing back dirty pages at the
 * address_space level.
 *
 * 10Apr2002	akpm@zip.com.au
 *		Initial version
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/init.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/mpage.h>
#include <linux/rmap.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/buffer_head.h>
#include <linux/pagevec.h>

/*
 * The maximum number of pages to writeout in a single bdflush/kupdate
 * operation.  We do this so we don't hold I_LOCK against an inode for
 * enormous amounts of time, which would block a userspace task which has
 * been forced to throttle against that inode.  Also, the code reevaluates
 * the dirty each time it has written this many pages.
 */
#define MAX_WRITEBACK_PAGES	1024

/*
 * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
 * will look to see if it needs to force writeback or throttling.
 */
static long ratelimit_pages = 32;

static int dirty_exceeded __cacheline_aligned_in_smp;	/* Dirty mem may be over limit */

/*
 * When balance_dirty_pages decides that the caller needs to perform some
 * non-background writeback, this is how many pages it will attempt to write.
 * It should be somewhat larger than RATELIMIT_PAGES to ensure that reasonably
 * large amounts of I/O are submitted.
 */
static inline long sync_writeback_pages(void)
{
	return ratelimit_pages + ratelimit_pages / 2;
}

/* The following parameters are exported via /proc/sys/vm */

/*
 * Start background writeback (via pdflush) at this percentage
 */
int dirty_background_ratio = 5;

/*
 * The generator of dirty data starts writeback at this percentage
 */
int vm_dirty_ratio = 10;

/*
 * The interval between `kupdate'-style writebacks, in jiffies
 */
int dirty_writeback_interval = 5 * HZ;

/*
 * The longest number of jiffies for which data is allowed to remain dirty
 */
int dirty_expire_interval = 30 * HZ;

/*
 * Flag that makes the machine dump writes/reads and block dirtyings.
 */
int block_dump;

/*
 * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
 * a full sync is triggered after this time elapses without any disk activity.
 */
int laptop_mode;

EXPORT_SYMBOL(laptop_mode);

/* End of sysctl-exported parameters */


static void background_writeout(unsigned long _min_pages);

/*
 * Work out the current dirty-memory clamping and background writeout
 * thresholds.
 *
 * The main aim here is to lower them aggressively if there is a lot of mapped
 * memory around.  To avoid stressing page reclaim with lots of unreclaimable
 * pages.  It is better to clamp down on writers than to start swapping, and
 * performing lots of scanning.
 *
 * We only allow 1/2 of the currently-unmapped memory to be dirtied.
 *
 * We don't permit the clamping level to fall below 5% - that is getting rather
 * excessive.
 *
 * We make sure that the background writeout level is below the adjusted
 * clamping level.
 */

static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
	int node;
	unsigned long x = 0;

	for_each_node_state(node, N_HIGH_MEMORY) {
		struct zone *z =
			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];

		x += zone_page_state(z, NR_FREE_PAGES)
			+ zone_page_state(z, NR_INACTIVE)
			+ zone_page_state(z, NR_ACTIVE);
	}
	/*
	 * Make sure that the number of highmem pages is never larger
	 * than the number of the total dirtyable memory. This can only
	 * occur in very strange VM situations but we want to make sure
	 * that this does not occur.
	 */
	return min(x, total);
#else
	return 0;
#endif
}

static unsigned long determine_dirtyable_memory(void)
{
	unsigned long x;

	x = global_page_state(NR_FREE_PAGES)
		+ global_page_state(NR_INACTIVE)
		+ global_page_state(NR_ACTIVE);
	x -= highmem_dirtyable_memory(x);
	return x + 1;	/* Ensure that we never return 0 */
}

static void
get_dirty_limits(long *pbackground, long *pdirty,
					struct address_space *mapping)
{
	int background_ratio;		/* Percentages */
	int dirty_ratio;
	int unmapped_ratio;
	long background;
	long dirty;
	unsigned long available_memory = determine_dirtyable_memory();
	struct task_struct *tsk;

	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
				global_page_state(NR_ANON_PAGES)) * 100) /
					available_memory;

	dirty_ratio = vm_dirty_ratio;
	if (dirty_ratio > unmapped_ratio / 2)
		dirty_ratio = unmapped_ratio / 2;

	if (dirty_ratio < 5)
		dirty_ratio = 5;

	background_ratio = dirty_background_ratio;
	if (background_ratio >= dirty_ratio)
		background_ratio = dirty_ratio / 2;

	background = (background_ratio * available_memory) / 100;
	dirty = (dirty_ratio * available_memory) / 100;
	tsk = current;
	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
		background += background / 4;
		dirty += dirty / 4;
	}
	*pbackgro