/*
 * mm/page-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 *
 * Contains functions related to writing back dirty pages at the
 * address_space level.
 *
 * 10Apr2002	Andrew Morton
 *		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_SYNC 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;

/*
 * 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;

/*
 * dirty_background_bytes starts at 0 (disabled) so that it is a function of
 * dirty_background_ratio * the amount of dirtyable memory
 */
unsigned long dirty_background_bytes;

/*
 * free highmem will not be subtracted from the total free memory
 * for calculating free ratios if vm_highmem_is_dirtyable is true
 */
int vm_highmem_is_dirtyable;

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

/*
 * vm_dirty_bytes starts at 0 (disabled) so that it is a function of
 * vm_dirty_ratio * the amount of dirtyable memory
 */
unsigned long vm_dirty_bytes;

/*
 * 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);

/*
 * Scale the writeback cache size proportional to the relative writeout speeds.
 *
 * We do this by keeping a floating proportion between BDIs, based on page
 * writeback completions [end_page_writeback()]. Those devices that write out
 * pages fastest will get the larger share, while the slower will get a smaller
 * share.
 *
 * We use page writeout completions because we are interested in getting rid of
 * dirty pages. Having them written out is the primary goal.
 *
 * We introduce a concept of time, a period over which we measure these events,
 * because demand can/will vary over time. The length of this period itself is
 * measured in page writeback completions.
 *
 */
static struct prop_descriptor vm_completions;
static struct prop_descriptor vm_dirties;

/*
 * couple the period to the dirty_ratio:
 *
 *   period/2 ~ roundup_pow_of_two(dirty limit)
 */
static int calc_period_shift(void)
{
	unsigned long dirty_total;

	if (vm_dirty_bytes)
		dirty_total = vm_dirty_bytes / PAGE_SIZE;
	else
		dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
				100;
	return 2 + ilog2(dirty_total - 1);
}

/*
 * update the period when the dirty threshold changes.
 */
static void update_completion_period(void)
{
	int shift = calc_period_shift();
	prop_change_shift(&vm_completions, shift);
	prop_change_shift(&vm_dirties, shift);
}

int dirty_background_ratio_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int ret;

	ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
	if (ret == 0 && write)
		dirty_background_bytes = 0;
	return ret;
}

int dirty_background_bytes_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int ret;

	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
	if (ret == 0 && write)
		dirty_background_ratio = 0;
	return ret;
}

int dirty_ratio_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int old_ratio = vm_dirty_ratio;
	int ret;

	ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
	if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
		update_completion_period();
		vm_dirty_bytes = 0;
	}
	return ret;
}


int dirty_bytes_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos)