inode.c

linux 内核源代码

/*
 *  linux/fs/ext3/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card ([e-mail])
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Goal-directed block allocation by Stephen Tweedie
 *	([e-mail]), 1993, 1998
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller ([e-mail]), 1995
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *	([e-mail])
 *
 *  Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/ext3_jbd.h>
#include <linux/jbd.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include "xattr.h"
#include "acl.h"

static int ext3_writepage_trans_blocks(struct inode *inode);

/*
 * Test whether an inode is a fast symlink.
 */
static int ext3_inode_is_fast_symlink(struct inode *inode)
{
	int ea_blocks = EXT3_I(inode)->i_file_acl ?
		(inode->i_sb->s_blocksize >> 9) : 0;

	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}

/*
 * The ext3 forget function must perform a revoke if we are freeing data
 * which has been journaled.  Metadata (eg. indirect blocks) must be
 * revoked in all cases.
 *
 * "bh" may be NULL: a metadata block may have been freed from memory
 * but there may still be a record of it in the journal, and that record
 * still needs to be revoked.
 */
int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode,
			struct buffer_head *bh, ext3_fsblk_t blocknr)
{
	int err;

	might_sleep();

	BUFFER_TRACE(bh, "enter");

	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
		  "data mode %lx\n",
		  bh, is_metadata, inode->i_mode,
		  test_opt(inode->i_sb, DATA_FLAGS));

	/* Never use the revoke function if we are doing full data
	 * journaling: there is no need to, and a V1 superblock won't
	 * support it.  Otherwise, only skip the revoke on un-journaled
	 * data blocks. */

	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ||
	    (!is_metadata && !ext3_should_journal_data(inode))) {
		if (bh) {
			BUFFER_TRACE(bh, "call journal_forget");
			return ext3_journal_forget(handle, bh);
		}
		return 0;
	}

	/*
	 * data!=journal && (is_metadata || should_journal_data(inode))
	 */
	BUFFER_TRACE(bh, "call ext3_journal_revoke");
	err = ext3_journal_revoke(handle, blocknr, bh);
	if (err)
		ext3_abort(inode->i_sb, __FUNCTION__,
			   "error %d when attempting revoke", err);
	BUFFER_TRACE(bh, "exit");
	return err;
}

/*
 * Work out how many blocks we need to proceed with the next chunk of a
 * truncate transaction.
 */
static unsigned long blocks_for_truncate(struct inode *inode)
{
	unsigned long needed;

	needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);

	/* Give ourselves just enough room to cope with inodes in which
	 * i_blocks is corrupt: we've seen disk corruptions in the past
	 * which resulted in random data in an inode which looked enough
	 * like a regular file for ext3 to try to delete it.  Things
	 * will go a bit crazy if that happens, but at least we should
	 * try not to panic the whole kernel. */
	if (needed < 2)
		needed = 2;

	/* But we need to bound the transaction so we don't overflow the
	 * journal. */
	if (needed > EXT3_MAX_TRANS_DATA)
		needed = EXT3_MAX_TRANS_DATA;

	return EXT3_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
}

/*
 * Truncate transactions can be complex and absolutely huge.  So we need to
 * be able to restart the transaction at a conventient checkpoint to make
 * sure we don't overflow the journal.
 *
 * start_transaction gets us a new handle for a truncate transaction,
 * and extend_transaction tries to extend the existing one a bit.  If
 * extend fails, we need to propagate the failure up and restart the
 * transaction in the top-level truncate loop. --sct
 */
static handle_t *start_transaction(struct inode *inode)
{
	handle_t *result;

	result = ext3_journal_start(inode, blocks_for_truncate(inode));
	if (!IS_ERR(result))
		return result;

	ext3_std_error(inode->i_sb, PTR_ERR(result));
	return result;
}

/*
 * Try to extend this transaction for the purposes of truncation.
 *
 * Returns 0 if we managed to create more room.  If we can't create more
 * room, and the transaction must be restarted we return 1.
 */
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
	if (handle->h_buffer_credits > EXT3_RESERVE_TRANS_BLOCKS)
		return 0;
	if (!ext3_journal_extend(handle, blocks_for_truncate(inode)))
		return 0;
	return 1;
}

/*
 * Restart the transaction associated with *handle.  This does a commit,
 * so before we call here everything must be consistently dirtied against
 * this transaction.
 */
static int ext3_journal_test_restart(handle_t *handle, struct inode *inode)
{
	jbd_debug(2, "restarting handle %p\n", handle);
	return ext3_journal_restart(handle, blocks_for_truncate(inode));
}

/*
 * Called at the last iput() if i_nlink is zero.
 */
void ext3_delete_inode (struct inode * inode)
{
	handle_t *handle;

	truncate_inode_pages(&inode->i_data, 0);

	if (is_bad_inode(inode))
		goto no_delete;

	handle = start_transaction(inode);
	if (IS_ERR(handle)) {
		/*
		 * If we're going to skip the normal cleanup, we still need to
		 * make sure that the in-core orphan linked list is properly
		 * cleaned up.
		 */
		ext3_orphan_del(NULL, inode);
		goto no_delete;
	}

	if (IS_SYNC(inode))
		handle->h_sync = 1;
	inode->i_size = 0;
	if (inode->i_blocks)
		ext3_truncate(inode);
	/*
	 * Kill off the orphan record which ext3_truncate created.
	 * AKPM: I think this can be inside the above `if'.
	 * Note that ext3_orphan_del() has to be able to cope with the
	 * deletion of a non-existent orphan - this is because we don't
	 * know if ext3_truncate() actually created an orphan record.
	 * (Well, we could do this if we need to, but heck - it works)
	 */
	ext3_orphan_del(handle, inode);
	EXT3_I(inode)->i_dtime	= get_seconds();

	/*
	 * One subtle ordering requirement: if anything has gone wrong
	 * (transaction abort, IO errors, whatever), then we can still
	 * do these next steps (the fs will already have been marked as
	 * having errors), but we can't free the inode if the mark_dirty
	 * fails.
	 */
	if (ext3_mark_inode_dirty(handle, inode))
		/* If that failed, just do the required in-core inode clear. */
		clear_inode(inode);
	else
		ext3_free_inode(handle, inode);
	ext3_journal_stop(handle);
	return;
no_delete:
	clear_inode(inode);	/* We must guarantee clearing of inode... */
}

typedef struct {
	__le32	*p;
	__le32	key;
	struct buffer_head *bh;
} Indirect;

static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
{
	p->key = *(p->p = v);
	p->bh = bh;
}

static int verify_chain(Indirect *from, Indirect *to)
{
	while (from <= to && from->key == *from->p)
		from++;
	return (from > to);
}

/**
 *	ext3_block_to_path - parse the block number into array of offsets
 *	@inode: inode in question (we are only interested in its superblock)
 *	@i_block: block number to be parsed
 *	@offsets: array to store the offsets in
 *      @boundary: set this non-zero if the referred-to block is likely to be
 *             followed (on disk) by an indirect block.
 *
 *	To store the locations of file's data ext3 uses a data structure common
 *	for UNIX filesystems - tree of pointers anchored in the inode, with
 *	data blocks at leaves and indirect blocks in intermediate nodes.
 *	This function translates the block number into path in that tree -
 *	return value is the path length and @offsets[n] is the offset of
 *	pointer to (n+1)th node in the nth one. If @block is out of range
 *	(negative or too large) warning is printed and zero returned.
 *
 *	Note: function doesn't find node addresses, so no IO is needed. All
 *	we need to know is the capacity of indirect blocks (taken from the
 *	inode->i_sb).
 */

/*
 * Portability note: the last comparison (check that we fit into triple
 * indirect block) is spelled differently, because otherwise on an
 * architecture with 32-bit longs and 8Kb pages we might get into trouble
 * if our filesystem had 8Kb blocks. We might use long long, but that would
 * kill us on x86. Oh, well, at least the sign propagation does not matter -
 * i_block would have to be negative in the very beginning, so we would not
 * get there at all.
 */

static int ext3_block_to_path(struct inode *inode,
			long i_block, int offsets[4], int *boundary)
{
	int ptrs = EXT3_ADDR_PER_BLOCK(inode->i_sb);
	int ptrs_bits = EXT3_ADDR_PER_BLOCK_BITS(inode->i_sb);
	const long direct_blocks = EXT3_NDIR_BLOCKS,
		indirect_blocks = ptrs,
		double_blocks = (1 << (ptrs_bits * 2));
	int n = 0;
	int final = 0;

	if (i_block < 0) {
		ext3_warning (inode->i_sb, "ext3_block_to_path", "block < 0");
	} else if (i_block < direct_blocks) {
		offsets[n++] = i_block;
		final = direct_blocks;
	} else if ( (i_block -= direct_blocks) < indirect_blocks) {
		offsets[n++] = EXT3_IND_BLOCK;
		offsets[n++] = i_block;
		final = ptrs;
	} else if ((i_block -= indirect_blocks) < double_blocks) {
		offsets[n++] = EXT3_DIND_BLOCK;
		offsets[n++] = i_block >> ptrs_bits;
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
		offsets[n++] = EXT3_TIND_BLOCK;
		offsets[n++] = i_block >> (ptrs_bits * 2);
		offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else {
		ext3_warning(inode->i_sb, "ext3_block_to_path", "block > big");
	}
	if (boundary)
		*boundary = final - 1 - (i_block & (ptrs - 1));
	return n;
}

/**
 *	ext3_get_branch - read the chain of indirect blocks leading to data
 *	@inode: inode in question
 *	@depth: depth of the chain (1 - direct pointer, etc.)
 *	@offsets: offsets of pointers in inode/indirect blocks
 *	@chain: place to store the result
 *	@err: here we store the error value
 *
 *	Function fills the array of triples <key, p, bh> and returns %NULL
 *	if everything went OK or the pointer to the last filled triple
 *	(incomplete one) otherwise. Upon the return chain[i].key contains
 *	the number of (i+1)-th block in the chain (as it is stored in memory,
 *	i.e. little-endian 32-bit), chain[i].p contains the address of that
 *	number (it points into struct inode for i==0 and into the bh->b_data
 *	for i>0) and chain[i].bh points to the buffer_head of i-th indirect
 *	block for i>0 and NULL for i==0. In other words, it holds the block
 *	numbers of the chain, addresses they were taken from (and where we can
 *	verify that chain did not change) and buffer_heads hosting these
 *	numbers.
 *
 *	Function stops when it stumbles upon zero pointer (absent block)
 *		(pointer to last triple returned, *@err == 0)
 *	or when it gets an IO error reading an indirect block
 *		(ditto, *@err == -EIO)
 *	or when it notices that chain had been changed while it was reading
 *		(ditto, *@err == -EAGAIN)
 *	or when it reads all @depth-1 indirect blocks successfully and finds
 *	the whole chain, all way to the data (returns %NULL, *err == 0).
 */
static Indirect *ext3_get_branch(struct inode *inode, int depth, int *offsets,
				 Indirect chain[4], int *err)
{
	struct super_block *sb = inode->i_sb;
	Indirect *p = chain;
	struct buffer_head *bh;

	*err = 0;
	/* i_data is not going away, no lock needed */
	add_chain (chain, NULL, EXT3_I(inode)->i_data + *offsets);
	if (!p->key)
		goto no_block;
	while (--depth) {
		bh = sb_bread(sb, le32_to_cpu(p->key));
		if (!bh)
			goto failure;
		/* Reader: pointers */
		if (!verify_chain(chain, p))
			goto changed;
		add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
		/* Reader: end */
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	brelse(bh);
	*err = -EAGAIN;
	goto no_block;
failure:
	*err = -EIO;
no_block:
	return p;
}

/**
 *	ext3_find_near - find a place for allocation with sufficient locality
 *	@inode: owner
 *	@ind: descriptor of indirect block.
 *
 *	This function returns the prefered place for block allocation.
 *	It is used when heuristic for sequential allocation fails.
 *	Rules are:
 *	  + if there is a block to the left of our position - allocate near it.
 *	  + if pointer will live in indirect block - allocate near that block.
 *	  + if pointer will live in inode - allocate in the same
 *	    cylinder group.
 *
 * In the latter case we colour the starting block by the callers PID to
 * prevent it from clashing with concurrent allocations for a different inode
 * in the same block group.   The PID is used here so that functionally related
 * files will be close-by on-disk.
 *
 *	Caller must make sure that @ind is valid and will stay that way.
 */
static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
	__le32 *p;
	ext3_fsblk_t bg_start;
	ext3_grpblk_t colour;

	/* Try to find previous block */
	for (p = ind->p - 1; p >= start; p--) {
		if (*p)
			return le32_to_cpu(*p);
	}

	/* No such thing, so let's try location of indirect block */
	if (ind->bh)
		return ind->bh->b_blocknr;

	/*
	 * It is going to be referred to from the inode itself? OK, just put it
	 * into the same cylinder group then.
	 */
	bg_start = ext3_group_first_block_no(inode->i_sb, ei->i_block_group);
	colour = (current->pid % 16) *
			(EXT3_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	return bg_start + colour;
}

/**
 *	ext3_find_goal - find a prefered place for allocation.
 *	@inode: owner
 *	@block:  block we want
 *	@chain:  chain of indirect blocks
 *	@partial: pointer to the last triple within a chain
 *	@goal:	place to store the result.
 *
 *	Normally this function find the prefered place for block allocation,