inode.c

linux 内核源代码

/*
 * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/reiserfs_fs.h>
#include <linux/reiserfs_acl.h>
#include <linux/reiserfs_xattr.h>
#include <linux/exportfs.h>
#include <linux/smp_lock.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <asm/uaccess.h>
#include <asm/unaligned.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/quotaops.h>
#include <linux/swap.h>

int reiserfs_commit_write(struct file *f, struct page *page,
			  unsigned from, unsigned to);
int reiserfs_prepare_write(struct file *f, struct page *page,
			   unsigned from, unsigned to);

void reiserfs_delete_inode(struct inode *inode)
{
	/* We need blocks for transaction + (user+group) quota update (possibly delete) */
	int jbegin_count =
	    JOURNAL_PER_BALANCE_CNT * 2 +
	    2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
	struct reiserfs_transaction_handle th;
	int err;

	truncate_inode_pages(&inode->i_data, 0);

	reiserfs_write_lock(inode->i_sb);

	/* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */
	if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) {	/* also handles bad_inode case */
		reiserfs_delete_xattrs(inode);

		if (journal_begin(&th, inode->i_sb, jbegin_count))
			goto out;
		reiserfs_update_inode_transaction(inode);

		err = reiserfs_delete_object(&th, inode);

		/* Do quota update inside a transaction for journaled quotas. We must do that
		 * after delete_object so that quota updates go into the same transaction as
		 * stat data deletion */
		if (!err) 
			DQUOT_FREE_INODE(inode);

		if (journal_end(&th, inode->i_sb, jbegin_count))
			goto out;

		/* check return value from reiserfs_delete_object after
		 * ending the transaction
		 */
		if (err)
		    goto out;

		/* all items of file are deleted, so we can remove "save" link */
		remove_save_link(inode, 0 /* not truncate */ );	/* we can't do anything
								 * about an error here */
	} else {
		/* no object items are in the tree */
		;
	}
      out:
	clear_inode(inode);	/* note this must go after the journal_end to prevent deadlock */
	inode->i_blocks = 0;
	reiserfs_write_unlock(inode->i_sb);
}

static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
			  __u32 objectid, loff_t offset, int type, int length)
{
	key->version = version;

	key->on_disk_key.k_dir_id = dirid;
	key->on_disk_key.k_objectid = objectid;
	set_cpu_key_k_offset(key, offset);
	set_cpu_key_k_type(key, type);
	key->key_length = length;
}

/* take base of inode_key (it comes from inode always) (dirid, objectid) and version from an inode, set
   offset and type of key */
void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
		  int type, int length)
{
	_make_cpu_key(key, get_inode_item_key_version(inode),
		      le32_to_cpu(INODE_PKEY(inode)->k_dir_id),
		      le32_to_cpu(INODE_PKEY(inode)->k_objectid), offset, type,
		      length);
}

//
// when key is 0, do not set version and short key
//
inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
			      int version,
			      loff_t offset, int type, int length,
			      int entry_count /*or ih_free_space */ )
{
	if (key) {
		ih->ih_key.k_dir_id = cpu_to_le32(key->on_disk_key.k_dir_id);
		ih->ih_key.k_objectid =
		    cpu_to_le32(key->on_disk_key.k_objectid);
	}
	put_ih_version(ih, version);
	set_le_ih_k_offset(ih, offset);
	set_le_ih_k_type(ih, type);
	put_ih_item_len(ih, length);
	/*    set_ih_free_space (ih, 0); */
	// for directory items it is entry count, for directs and stat
	// datas - 0xffff, for indirects - 0
	put_ih_entry_count(ih, entry_count);
}

//
// FIXME: we might cache recently accessed indirect item

// Ugh.  Not too eager for that....
//  I cut the code until such time as I see a convincing argument (benchmark).
// I don't want a bloated inode struct..., and I don't like code complexity....

/* cutting the code is fine, since it really isn't in use yet and is easy
** to add back in.  But, Vladimir has a really good idea here.  Think
** about what happens for reading a file.  For each page,
** The VFS layer calls reiserfs_readpage, who searches the tree to find
** an indirect item.  This indirect item has X number of pointers, where
** X is a big number if we've done the block allocation right.  But,
** we only use one or two of these pointers during each call to readpage,
** needlessly researching again later on.
**
** The size of the cache could be dynamic based on the size of the file.
**
** I'd also like to see us cache the location the stat data item, since
** we are needlessly researching for that frequently.
**
** --chris
*/

/* If this page has a file tail in it, and
** it was read in by get_block_create_0, the page data is valid,
** but tail is still sitting in a direct item, and we can't write to
** it.  So, look through this page, and check all the mapped buffers
** to make sure they have valid block numbers.  Any that don't need
** to be unmapped, so that block_prepare_write will correctly call
** reiserfs_get_block to convert the tail into an unformatted node
*/
static inline void fix_tail_page_for_writing(struct page *page)
{
	struct buffer_head *head, *next, *bh;

	if (page && page_has_buffers(page)) {
		head = page_buffers(page);
		bh = head;
		do {
			next = bh->b_this_page;
			if (buffer_mapped(bh) && bh->b_blocknr == 0) {
				reiserfs_unmap_buffer(bh);
			}
			bh = next;
		} while (bh != head);
	}
}

/* reiserfs_get_block does not need to allocate a block only if it has been
   done already or non-hole position has been found in the indirect item */
static inline int allocation_needed(int retval, b_blocknr_t allocated,
				    struct item_head *ih,
				    __le32 * item, int pos_in_item)
{
	if (allocated)
		return 0;
	if (retval == POSITION_FOUND && is_indirect_le_ih(ih) &&
	    get_block_num(item, pos_in_item))
		return 0;
	return 1;
}

static inline int indirect_item_found(int retval, struct item_head *ih)
{
	return (retval == POSITION_FOUND) && is_indirect_le_ih(ih);
}

static inline void set_block_dev_mapped(struct buffer_head *bh,
					b_blocknr_t block, struct inode *inode)
{
	map_bh(bh, inode->i_sb, block);
}

//
// files which were created in the earlier version can not be longer,
// than 2 gb
//
static int file_capable(struct inode *inode, sector_t block)
{
	if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 ||	// it is new file.
	    block < (1 << (31 - inode->i_sb->s_blocksize_bits)))	// old file, but 'block' is inside of 2gb
		return 1;

	return 0;
}

static int restart_transaction(struct reiserfs_transaction_handle *th,
			       struct inode *inode, struct treepath *path)
{
	struct super_block *s = th->t_super;
	int len = th->t_blocks_allocated;
	int err;

	BUG_ON(!th->t_trans_id);
	BUG_ON(!th->t_refcount);

	pathrelse(path);

	/* we cannot restart while nested */
	if (th->t_refcount > 1) {
		return 0;
	}
	reiserfs_update_sd(th, inode);
	err = journal_end(th, s, len);
	if (!err) {
		err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6);
		if (!err)
			reiserfs_update_inode_transaction(inode);
	}
	return err;
}

// it is called by get_block when create == 0. Returns block number
// for 'block'-th logical block of file. When it hits direct item it
// returns 0 (being called from bmap) or read direct item into piece
// of page (bh_result)

// Please improve the english/clarity in the comment above, as it is
// hard to understand.

static int _get_block_create_0(struct inode *inode, sector_t block,
			       struct buffer_head *bh_result, int args)
{
	INITIALIZE_PATH(path);
	struct cpu_key key;
	struct buffer_head *bh;
	struct item_head *ih, tmp_ih;
	int fs_gen;
	b_blocknr_t blocknr;
	char *p = NULL;
	int chars;
	int ret;
	int result;
	int done = 0;
	unsigned long offset;

	// prepare the key to look for the 'block'-th block of file
	make_cpu_key(&key, inode,
		     (loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
		     3);

      research:
	result = search_for_position_by_key(inode->i_sb, &key, &path);
	if (result != POSITION_FOUND) {
		pathrelse(&path);
		if (p)
			kunmap(bh_result->b_page);
		if (result == IO_ERROR)
			return -EIO;
		// We do not return -ENOENT if there is a hole but page is uptodate, because it means
		// That there is some MMAPED data associated with it that is yet to be written to disk.
		if ((args & GET_BLOCK_NO_HOLE)
		    && !PageUptodate(bh_result->b_page)) {
			return -ENOENT;
		}
		return 0;
	}
	//
	bh = get_last_bh(&path);
	ih = get_ih(&path);
	if (is_indirect_le_ih(ih)) {
		__le32 *ind_item = (__le32 *) B_I_PITEM(bh, ih);

		/* FIXME: here we could cache indirect item or part of it in
		   the inode to avoid search_by_key in case of subsequent
		   access to file */
		blocknr = get_block_num(ind_item, path.pos_in_item);
		ret = 0;
		if (blocknr) {
			map_bh(bh_result, inode->i_sb, blocknr);
			if (path.pos_in_item ==
			    ((ih_item_len(ih) / UNFM_P_SIZE) - 1)) {
				set_buffer_boundary(bh_result);
			}
		} else
			// We do not return -ENOENT if there is a hole but page is uptodate, because it means
			// That there is some MMAPED data associated with it that is yet to  be written to disk.
		if ((args & GET_BLOCK_NO_HOLE)
			    && !PageUptodate(bh_result->b_page)) {
			ret = -ENOENT;
		}

		pathrelse(&path);
		if (p)
			kunmap(bh_result->b_page);
		return ret;
	}
	// requested data are in direct item(s)
	if (!(args & GET_BLOCK_READ_DIRECT)) {
		// we are called by bmap. FIXME: we can not map block of file
		// when it is stored in direct item(s)
		pathrelse(&path);
		if (p)
			kunmap(bh_result->b_page);
		return -ENOENT;
	}

	/* if we've got a direct item, and the buffer or page was uptodate,
	 ** we don't want to pull data off disk again.  skip to the
	 ** end, where we map the buffer and return
	 */
	if (buffer_uptodate(bh_result)) {
		goto finished;
	} else
		/*
		 ** grab_tail_page can trigger calls to reiserfs_get_block on up to date
		 ** pages without any buffers.  If the page is up to date, we don't want
		 ** read old data off disk.  Set the up to date bit on the buffer instead
		 ** and jump to the end
		 */
	if (!bh_result->b_page || PageUptodate(bh_result->b_page)) {
		set_buffer_uptodate(bh_result);
		goto finished;
	}
	// read file tail into part of page
	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
	fs_gen = get_generation(inode->i_sb);
	copy_item_head(&tmp_ih, ih);

	/* we only want to kmap if we are reading the tail into the page.
	 ** this is not the common case, so we don't kmap until we are
	 ** sure we need to.  But, this means the item might move if
	 ** kmap schedules
	 */
	if (!p) {
		p = (char *)kmap(bh_result->b_page);
		if (fs_changed(fs_gen, inode->i_sb)
		    && item_moved(&tmp_ih, &path)) {
			goto research;
		}
	}
	p += offset;
	memset(p, 0, inode->i_sb->s_blocksize);
	do {
		if (!is_direct_le_ih(ih)) {
			BUG();
		}
		/* make sure we don't read more bytes than actually exist in
		 ** the file.  This can happen in odd cases where i_size isn't
		 ** correct, and when direct item padding results in a few 
		 ** extra bytes at the end of the direct item
		 */
		if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size)
			break;
		if ((le_ih_k_offset(ih) - 1 + ih_item_len(ih)) > inode->i_size) {
			chars =
			    inode->i_size - (le_ih_k_offset(ih) - 1) -
			    path.pos_in_item;
			done = 1;
		} else {
			chars = ih_item_len(ih) - path.pos_in_item;
		}
		memcpy(p, B_I_PITEM(bh, ih) + path.pos_in_item, chars);

		if (done)
			break;

		p += chars;

		if (PATH_LAST_POSITION(&path) != (B_NR_ITEMS(bh) - 1))
			// we done, if read direct item is not the last item of
			// node FIXME: we could try to check right delimiting key
			// to see whether direct item continues in the right
			// neighbor or rely on i_size
			break;

		// update key to look for the next piece
		set_cpu_key_k_offset(&key, cpu_key_k_offset(&key) + chars);
		result = search_for_position_by_key(inode->i_sb, &key, &path);
		if (result != POSITION_FOUND)
			// i/o error most likely
			break;
		bh = get_last_bh(&path);
		ih = get_ih(&path);
	} while (1);

	flush_dcache_page(bh_result->b_page);
	kunmap(bh_result->b_page);

      finished:
	pathrelse(&path);

	if (result == IO_ERROR)
		return -EIO;

	/* this buffer has valid data, but isn't valid for io.  mapping it to
	 * block #0 tells the rest of reiserfs it just has a tail in it
	 */
	map_bh(bh_result, inode->i_sb, 0);
	set_buffer_uptodate(bh_result);
	return 0;
}

// this is called to create file map. So, _get_block_create_0 will not
// read direct item
static int reiserfs_bmap(struct inode *inode, sector_t block,
			 struct buffer_head *bh_result, int create)
{
	if (!file_capable(inode, block))
		return -EFBIG;

	reiserfs_write_lock(inode->i_sb);