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	akpm@zip.com.au
 *		Split out of fs/inode.c
 *		Additions for address_space-based writeback
 */

#include <linux/kernel.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include "internal.h"

/**
 *	__mark_inode_dirty -	internal function
 *	@inode: inode to mark
 *	@flags: what kind of dirty (i.e. I_DIRTY_SYNC)
 *	Mark an inode as dirty. Callers should use mark_inode_dirty or
 *  	mark_inode_dirty_sync.
 *
 * Put the inode on the super block's dirty list.
 *
 * CAREFUL! We mark it dirty unconditionally, but move it onto the
 * dirty list only if it is hashed or if it refers to a blockdev.
 * If it was not hashed, it will never be added to the dirty list
 * even if it is later hashed, as it will have been marked dirty already.
 *
 * In short, make sure you hash any inodes _before_ you start marking
 * them dirty.
 *
 * This function *must* be atomic for the I_DIRTY_PAGES case -
 * set_page_dirty() is called under spinlock in several places.
 *
 * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
 * the block-special inode (/dev/hda1) itself.  And the ->dirtied_when field of
 * the kernel-internal blockdev inode represents the dirtying time of the
 * blockdev's pages.  This is why for I_DIRTY_PAGES we always use
 * page->mapping->host, so the page-dirtying time is recorded in the internal
 * blockdev inode.
 */
void __mark_inode_dirty(struct inode *inode, int flags)
{
	struct super_block *sb = inode->i_sb;

	/*
	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
	 * dirty the inode itself
	 */
	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		if (sb->s_op->dirty_inode)
			sb->s_op->dirty_inode(inode);
	}

	/*
	 * make sure that changes are seen by all cpus before we test i_state
	 * -- mikulas
	 */
	smp_mb();

	/* avoid the locking if we can */
	if ((inode->i_state & flags) == flags)
		return;

	if (unlikely(block_dump)) {
		struct dentry *dentry = NULL;
		const char *name = "?";

		if (!list_empty(&inode->i_dentry)) {
			dentry = list_entry(inode->i_dentry.next,
					    struct dentry, d_alias);
			if (dentry && dentry->d_name.name)
				name = (const char *) dentry->d_name.name;
		}

		if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev"))
			printk(KERN_DEBUG
			       "%s(%d): dirtied inode %lu (%s) on %s\n",
			       current->comm, current->pid, inode->i_ino,
			       name, inode->i_sb->s_id);
	}

	spin_lock(&inode_lock);
	if ((inode->i_state & flags) != flags) {
		const int was_dirty = inode->i_state & I_DIRTY;

		inode->i_state |= flags;

		/*
		 * If the inode is locked, just update its dirty state. 
		 * The unlocker will place the inode on the appropriate
		 * superblock list, based upon its state.
		 */
		if (inode->i_state & I_LOCK)
			goto out;

		/*
		 * Only add valid (hashed) inodes to the superblock's
		 * dirty list.  Add blockdev inodes as well.
		 */
		if (!S_ISBLK(inode->i_mode)) {
			if (hlist_unhashed(&inode->i_hash))
				goto out;
		}
		if (inode->i_state & (I_FREEING|I_CLEAR))
			goto out;

		/*
		 * If the inode was already on s_dirty or s_io, don't
		 * reposition it (that would break s_dirty time-ordering).
		 */
		if (!was_dirty) {
			inode->dirtied_when = jiffies;
			list_move(&inode->i_list, &sb->s_dirty);
		}
	}
out:
	spin_unlock(&inode_lock);
}

EXPORT_SYMBOL(__mark_inode_dirty);

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

/*
 * Write a single inode's dirty pages and inode data out to disk.
 * If `wait' is set, wait on the writeout.
 *
 * The whole writeout design is quite complex and fragile.  We want to avoid
 * starvation of particular inodes when others are being redirtied, prevent
 * livelocks, etc.
 *
 * Called under inode_lock.
 */
static int
__sync_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	unsigned dirty;
	struct address_space *mapping = inode->i_mapping;
	struct super_block *sb = inode->i_sb;
	int wait = wbc->sync_mode == WB_SYNC_ALL;
	int ret;

	BUG_ON(inode->i_state & I_LOCK);

	/* Set I_LOCK, reset I_DIRTY */
	dirty = inode->i_state & I_DIRTY;
	inode->i_state |= I_LOCK;
	inode->i_state &= ~I_DIRTY;

	spin_unlock(&inode_lock);

	ret = do_writepages(mapping, wbc);

	/* Don't write the inode if only I_DIRTY_PAGES was set */
	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		int err = write_inode(inode, wait);
		if (ret == 0)
			ret = err;
	}

	if (wait) {
		int err = filemap_fdatawait(mapping);
		if (ret == 0)
			ret = err;
	}

	spin_lock(&inode_lock);
	inode->i_state &= ~I_LOCK;
	if (!(inode->i_state & I_FREEING)) {
		if (!(inode->i_state & I_DIRTY) &&
		    mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
			/*
			 * We didn't write back all the pages.  nfs_writepages()
			 * sometimes bales out without doing anything. Redirty
			 * the inode.  It is still on sb->s_io.
			 */
			if (wbc->for_kupdate) {
				/*
				 * For the kupdate function we leave the inode
				 * at the head of sb_dirty so it will get more
				 * writeout as soon as the queue becomes
				 * uncongested.
				 */
				inode->i_state |= I_DIRTY_PAGES;
				list_move_tail(&inode->i_list, &sb->s_dirty);
			} else {
				/*
				 * Otherwise fully redirty the inode so that
				 * other inodes on this superblock will get some
				 * writeout.  Otherwise heavy writing to one
				 * file would indefinitely suspend writeout of
				 * all the other files.
				 */
				inode->i_state |= I_DIRTY_PAGES;
				inode->dirtied_when = jiffies;
				list_move(&inode->i_list, &sb->s_dirty);
			}
		} else if (inode->i_state & I_DIRTY) {
			/*
			 * Someone redirtied the inode while were writing back
			 * the pages.
			 */
			list_move(&inode->i_list, &sb->s_dirty);
		} else if (atomic_read(&inode->i_count)) {
			/*
			 * The inode is clean, inuse
			 */
			list_move(&inode->i_list, &inode_in_use);
		} else {
			/*
			 * The inode is clean, unused
			 */
			list_move(&inode->i_list, &inode_unused);
		}
	}
	wake_up_inode(inode);
	return ret;
}

/*
 * Write out an inode's dirty pages.  Called under inode_lock.  Either the
 * caller has ref on the inode (either via __iget or via syscall against an fd)
 * or the inode has I_WILL_FREE set (via generic_forget_inode)
 */
static int
__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	wait_queue_head_t *wqh;

	if (!atomic_read(&inode->i_count))
		WARN_ON</