path: root/fs/fs-writeback.c

/*
 * fs/fs-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains all the functions related to writing back and waiting
 * upon dirty inodes against superblocks, and writing back dirty
 * pages against inodes.  ie: data writeback.  Writeout of the
 * inode itself is not handled here.
 *
 * 10Apr2002	Andrew Morton
 *		Split out of fs/inode.c
 *		Additions for address_space-based writeback
 */

#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/tracepoint.h>
#include <linux/device.h>
#include "internal.h"

/*
 * 4MB minimal write chunk size
 */
#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))

/*
 * Passed into wb_writeback(), essentially a subset of writeback_control
 */
struct wb_writeback_work {
	long nr_pages;
	struct super_block *sb;
	unsigned long *older_than_this;
	enum writeback_sync_modes sync_mode;
	unsigned int tagged_writepages:1;
	unsigned int for_kupdate:1;
	unsigned int range_cyclic:1;
	unsigned int for_background:1;
	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
	enum wb_reason reason;		/* why was writeback initiated? */

	struct list_head list;		/* pending work list */
	struct completion *done;	/* set if the caller waits */
};

/*
 * If an inode is constantly having its pages dirtied, but then the
 * updates stop dirtytime_expire_interval seconds in the past, it's
 * possible for the worst case time between when an inode has its
 * timestamps updated and when they finally get written out to be two
 * dirtytime_expire_intervals.  We set the default to 12 hours (in
 * seconds), which means most of the time inodes will have their
 * timestamps written to disk after 12 hours, but in the worst case a
 * few inodes might not their timestamps updated for 24 hours.
 */
unsigned int dirtytime_expire_interval = 12 * 60 * 60;

/**
 * writeback_in_progress - determine whether there is writeback in progress
 * @bdi: the device's backing_dev_info structure.
 *
 * Determine whether there is writeback waiting to be handled against a
 * backing device.
 */
int writeback_in_progress(struct backing_dev_info *bdi)
{
	return test_bit(WB_writeback_running, &bdi->wb.state);
}
EXPORT_SYMBOL(writeback_in_progress);

struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
	struct super_block *sb;

	if (!inode)
		return &noop_backing_dev_info;

	sb = inode->i_sb;
#ifdef CONFIG_BLOCK
	if (sb_is_blkdev_sb(sb))
		return blk_get_backing_dev_info(I_BDEV(inode));
#endif
	return sb->s_bdi;
}
EXPORT_SYMBOL_GPL(inode_to_bdi);

static inline struct inode *wb_inode(struct list_head *head)
{
	return list_entry(head, struct inode, i_wb_list);
}

/*
 * Include the creation of the trace points after defining the
 * wb_writeback_work structure and inline functions so that the definition
 * remains local to this file.
 */
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>

EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);

static void bdi_wakeup_thread(struct backing_dev_info *bdi)
{
	spin_lock_bh(&bdi->wb_lock);
	if (test_bit(WB_registered, &bdi->wb.state))
		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
	spin_unlock_bh(&bdi->wb_lock);
}

static void bdi_queue_work(struct backing_dev_info *bdi,
			   struct wb_writeback_work *work)
{
	trace_writeback_queue(bdi, work);

	spin_lock_bh(&bdi->wb_lock);
	if (!test_bit(WB_registered, &bdi->wb.state)) {
		if (work->done)
			complete(work->done);
		goto out_unlock;
	}
	list_add_tail(&work->list, &bdi->work_list);
	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
out_unlock:
	spin_unlock_bh(&bdi->wb_lock);
}

static void
__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
		      bool range_cyclic, enum wb_reason reason)
{
	struct wb_writeback_work *work;

	/*
	 * This is WB_SYNC_NONE writeback, so if allocation fails just
	 * wakeup the thread for old dirty data writeback
	 */
	work = kzalloc(sizeof(*work), GFP_ATOMIC);
	if (!work) {
		trace_writeback_nowork(bdi);
		bdi_wakeup_thread(bdi);
		return;
	}

	work->sync_mode	= WB_SYNC_NONE;
	work->nr_pages	= nr_pages;
	work->range_cyclic = range_cyclic;
	work->reason	= reason;

	bdi_queue_work(bdi, work);
}

/**
 * bdi_start_writeback - start writeback
 * @bdi: the backing device to write from
 * @nr_pages: the number of pages to write
 * @reason: reason why some writeback work was initiated
 *
 * Description:
 *   This does WB_SYNC_NONE opportunistic writeback. The IO is only
 *   started when this function returns, we make no guarantees on
 *   completion. Caller need not hold sb s_umount semaphore.
 *
 */
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
			enum wb_reason reason)
{
	__bdi_start_writeback(bdi, nr_pages, true, reason);
}

/**
 * bdi_start_background_writeback - start background writeback
 * @bdi: the backing device to write from
 *
 * Description:
 *   This makes sure WB_SYNC_NONE background writeback happens. When
 *   this function returns, it is only guaranteed that for given BDI
 *