inode.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

/*
 *  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/fs.h>
#include <linux/sched.h>
#include <linux/ext3_jbd.h>
#include <linux/jbd.h>
#include <linux/locks.h>
#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/quotaops.h>
#include <linux/module.h>

/*
 * SEARCH_FROM_ZERO forces each block allocation to search from the start
 * of the filesystem.  This is to force rapid reallocation of recently-freed
 * blocks.  The file fragmentation is horrendous.
 */
#undef SEARCH_FROM_ZERO

/* 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.
 */

static int ext3_forget(handle_t *handle, int is_metadata,
		       struct inode *inode, struct buffer_head *bh,
		       int blocknr)
{
	int err;

	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");
			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;
}

/* 
 * 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) 
{
	long needed;
	handle_t *result;
	
	needed = inode->i_blocks;
	if (needed > EXT3_MAX_TRANS_DATA) 
		needed = EXT3_MAX_TRANS_DATA;
	
	result = ext3_journal_start(inode, EXT3_DATA_TRANS_BLOCKS + needed);
	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)
{
	long needed;
	
	if (handle->h_buffer_credits > EXT3_RESERVE_TRANS_BLOCKS)
		return 0;
	needed = inode->i_blocks;
	if (needed > EXT3_MAX_TRANS_DATA) 
		needed = EXT3_MAX_TRANS_DATA;
	if (!ext3_journal_extend(handle, EXT3_RESERVE_TRANS_BLOCKS + needed))
		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)
{
	long needed = inode->i_blocks;
	if (needed > EXT3_MAX_TRANS_DATA) 
		needed = EXT3_MAX_TRANS_DATA;
	jbd_debug(2, "restarting handle %p\n", handle);
	return ext3_journal_restart(handle, EXT3_DATA_TRANS_BLOCKS + needed);
}

/*
 * Called at each iput()
 */
void ext3_put_inode (struct inode * inode)
{
	ext3_discard_prealloc (inode);
}

/*
 * Called at the last iput() if i_nlink is zero.
 */
void ext3_delete_inode (struct inode * inode)
{
	handle_t *handle;
	
	if (is_bad_inode(inode) ||
	    inode->i_ino == EXT3_ACL_IDX_INO ||
	    inode->i_ino == EXT3_ACL_DATA_INO)
		goto no_delete;

	lock_kernel();
	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);

		ext3_std_error(inode->i_sb, PTR_ERR(handle));
		unlock_kernel();
		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);
	inode->u.ext3_i.i_dtime	= CURRENT_TIME;

	/* 
	 * 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, inode);
	unlock_kernel();
	return;
no_delete:
	clear_inode(inode);	/* We must guarantee clearing of inode... */
}

void ext3_discard_prealloc (struct inode * inode)
{
#ifdef EXT3_PREALLOCATE
	lock_kernel();
	/* Writer: ->i_prealloc* */
	if (inode->u.ext3_i.i_prealloc_count) {
		unsigned short total = inode->u.ext3_i.i_prealloc_count;
		unsigned long block = inode->u.ext3_i.i_prealloc_block;
		inode->u.ext3_i.i_prealloc_count = 0;
		inode->u.ext3_i.i_prealloc_block = 0;
		/* Writer: end */
		ext3_free_blocks (inode, block, total);
	}
	unlock_kernel();
#endif
}

static int ext3_alloc_block (handle_t *handle,
			struct inode * inode, unsigned long goal, int *err)
{
#ifdef EXT3FS_DEBUG
	static unsigned long alloc_hits = 0, alloc_attempts = 0;
#endif
	unsigned long result;

#ifdef EXT3_PREALLOCATE
	/* Writer: ->i_prealloc* */
	if (inode->u.ext3_i.i_prealloc_count &&
	    (goal == inode->u.ext3_i.i_prealloc_block ||
	     goal + 1 == inode->u.ext3_i.i_prealloc_block))
	{
		result = inode->u.ext3_i.i_prealloc_block++;
		inode->u.ext3_i.i_prealloc_count--;
		/* Writer: end */
		ext3_debug ("preallocation hit (%lu/%lu).\n",
			    ++alloc_hits, ++alloc_attempts);
	} else {
		ext3_discard_prealloc (inode);
		ext3_debug ("preallocation miss (%lu/%lu).\n",
			    alloc_hits, ++alloc_attempts);
		if (S_ISREG(inode->i_mode))
			result = ext3_new_block (inode, goal, 
				 &inode->u.ext3_i.i_prealloc_count,
				 &inode->u.ext3_i.i_prealloc_block, err);
		else
			result = ext3_new_block (inode, goal, 0, 0, err);
		/*
		 * AKPM: this is somewhat sticky.  I'm not surprised it was
		 * disabled in 2.2's ext3.  Need to integrate b_committed_data
		 * guarding with preallocation, if indeed preallocation is
		 * effective.
		 */
	}
#else
	result = ext3_new_block (handle, inode, goal, 0, 0, err);
#endif
	return result;
}


typedef struct {
	u32	*p;
	u32	key;
	struct buffer_head *bh;
} Indirect;

static inline void add_chain(Indirect *p, struct buffer_head *bh, u32 *v)
{
	p->key = *(p->p = v);
	p->bh = bh;
}

static inline 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
 *
 *	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 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;

	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;
	} else if ( (i_block -= direct_blocks) < indirect_blocks) {
		offsets[n++] = EXT3_IND_BLOCK;
		offsets[n++] = i_block;
	} 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);
	} 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);
	} else {
		ext3_warning (inode->i_sb, "ext3_block_to_path", "block > big");
	}
	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, inode->u.ext3_i.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, (u32*)bh->b_data + *++offsets);
		/* Reader: end */
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	*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: