/*
 * 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/module.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/tracepoint.h>
#include "internal.h"

/*
 * 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;

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

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

/*
 * We don't actually have pdflush, but this one is exported though /proc...
 */
int nr_pdflush_threads;

/**
 * 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(BDI_writeback_running, &bdi->state);
}

static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;

	if (strcmp(sb->s_type->name, "bdev") == 0)
		return inode->i_mapping->backing_dev_info;

	return sb->s_bdi;
}

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

/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
{
	if (bdi->wb.task) {
		wake_up_process(bdi->wb.task);
	} else {
		/*
		 * The bdi thread isn't there, wake up the forker thread which
		 * will create and run it.
		 */
		wake_up_process(default_backing_dev_info.wb.task);
	}
}

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);
	list_add_tail(&work->list, &bdi->work_list);
	if (!bdi->wb.task)
		trace_writeback_nothread(bdi, work);
	bdi_wakeup_flusher(bdi);
	spin_unlock_bh(&bdi->wb_lock);
}

static void
__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
		      bool range_cyclic)
{
	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) {
		if (bdi->wb.task) {
			trace_writeback_nowork(bdi);
			wake_up_process(bdi->wb.task);
		}
		return;
	}

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

	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
 *
 * 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)
{
	__bdi_start_writeback(bdi, nr_pages, true);
}

/**
 * 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
 *   some IO is happening if we are over background dirty threshold.
 *   Caller need not hold sb s_umount semaphore.
 */
void bdi_start_background_writeback(struct backing_dev_info *bdi)
{
	/*
	 * We just wake up the flusher thread. It will perform background
	 * writeback as soon as there is no other work to do.
	 */
	trace_writeback_wake_background(bdi);
	spin_lock_bh(&bdi->wb_lock);
	bdi_wakeup_flusher(bdi);
	spin_unlock_bh(&bdi->wb_lock);
}

/*
 * Remove the inode from the writeback list it is on.
 */
void inode_wb_list_del(struct inode *inode)
{
	struct backing_dev_info *bdi = inode_to_bdi(inode);

	spin_lock(&bdi->wb.list_lock);
	list_del_init(&inode->i_wb_list);
	spin_unlock(&bdi->wb.list_lock);
}

/*
 * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
 * furthest end of its superblock's dirty-inode list.
 *
 * Before stamping the inode's ->dirtied_when, we check to see whether it is
 * already the most-recently-dirtied inode on the b_dirty list.  If that is
 * the case then the inode must have been redirtied while it was being written
 * out and we don't reset its dirtied_when.
 */
static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
{
	assert_spin_locked(&wb->list_lock);
	if (!list_empty(&wb->b_dirty)) {
		struct inode *tail;

		tail = wb_inode(wb->b_dirty.next);
		if (time_before(inode->dirtied_when, tail->dirtied_when))
			inode->dirtied_when = jiffies;
	}
	list_move(&inode->i_wb_list, &wb->b_dirty);
}

/*
 * requeue inode for re-scanning after bdi->b_io list is exhausted.
 */
static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
{
	assert_spin_locked(&wb->list_lock);
	list_move(&inode->i_wb_list, &wb->b_more_io);
}

static void inode_sync_complete(struct inode *inode)
{
	/*
	 * Prevent speculative execution through
	 * spin_unlock(&wb->list_lock);
	 */

	smp_mb();
	wake_up_bit(&inode->i_state, __I_SYNC);
}

static bool inode_dirtied_after(struct inode *inode, unsigned long t)
{
	bool ret = time_after(inode->dirtied_when, t);
#ifndef CONFIG_64BIT
	/*
	 * For inodes being constantly redirtied, dirtied_when can get stuck.
	 * It _appears_ to be in the future, but is actually in distant past.
	 * This test is necessary to prevent such wrapped-around relative times
	 * from permanently stopping the whole bdi writeback.
	 */
	ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
	return ret;
}

/*
 * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
 */
static int move_expired_inodes(struct list_head *delaying_queue,
			       struct list_head *dispatch_queue,
			       unsigned long *older_than_this)
{
	LIST_HEAD(tmp);
	struct list_head *pos, *node;
	struct super_block *sb = NULL;
	struct inode *inode;
	int do_sb_sort = 0;
	int moved = 0;

	while (!list_empty(delaying_queue)) {
		inode = wb_inode(delaying_queue->prev);
		if (older_than_this &&
		    inode_dirtied_after(inode, *older_than_this))
			break;
		if (sb && sb != inode->i_sb)
			do_sb_sort = 1;
		sb = inode->i_sb;
		list_move(&inode->i_wb_list, &tmp);
		moved++;
	}

	/* just one sb in list, splice to dispatch_queue and we're done */
	if (!do_sb_sort) {
		list_splice(&tmp, dispatch_queue);
		goto out;
	}

	/* Move inodes from one superblock together */
	while (!list_empty(&tmp)) {
		sb = wb_inode(tmp.prev)->i_sb;
		list_for_each_prev_safe(pos, node, &tmp) {
			inode = wb_inode(pos);
			if (inode->i_sb == sb)
				list_move(&inode->i_wb_list, dispatch_queue);
		}
	}
out:
	return moved;
}

/*
 * Queue all expired dirty inodes for io, eldest first.
 * Before
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    gf         edc     BA
 * After
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    g          fBAedc
 *                                           |
 *                                           +--> dequeue for IO
 */
static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
	int moved;
	assert_spin_locked(&wb->list_lock);
	list_splice_init(&wb->b_more_io, &wb->b_io);
	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
	trace_writeback_queue_io(wb, older_than_this, moved);
}

static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
		return inode->i_sb->s_op->write_inode(inode, wbc);
	return 0;
}

/*
 * Wait for writeback on an inode to complete.
 */
static void inode_wait_for_writeback(struct inode *inode,
				     struct bdi_writeback *wb)
{
	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
	wait_queue_head_t *wqh;

	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
	while (inode->i_state & I_SYNC) {
		spin_unlock(&inode->i_lock);
		spin_unlock(&wb->list_lock);
		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
		spin_lock(&wb->list_lock);
		spin_lock(&inode->i_lock);
	}
}

/*
 * Write out an inode's dirty pages.  Called under wb->list_lock and