inode.c

linux 内核源代码

/*
 *  linux/fs/ext2/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 ext2_get_block() by Al Viro, 2000
 */

#include <linux/smp_lock.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/module.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"

MODULE_AUTHOR("Remy Card and others");
MODULE_DESCRIPTION("Second Extended Filesystem");
MODULE_LICENSE("GPL");

static int ext2_update_inode(struct inode * inode, int do_sync);

/*
 * Test whether an inode is a fast symlink.
 */
static inline int ext2_inode_is_fast_symlink(struct inode *inode)
{
	int ea_blocks = EXT2_I(inode)->i_file_acl ?
		(inode->i_sb->s_blocksize >> 9) : 0;

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

/*
 * Called at the last iput() if i_nlink is zero.
 */
void ext2_delete_inode (struct inode * inode)
{
	truncate_inode_pages(&inode->i_data, 0);

	if (is_bad_inode(inode))
		goto no_delete;
	EXT2_I(inode)->i_dtime	= get_seconds();
	mark_inode_dirty(inode);
	ext2_update_inode(inode, inode_needs_sync(inode));

	inode->i_size = 0;
	if (inode->i_blocks)
		ext2_truncate (inode);
	ext2_free_inode (inode);

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

/**
 *	ext2_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 ext2 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 ext2_block_to_path(struct inode *inode,
			long i_block, int offsets[4], int *boundary)
{
	int ptrs = EXT2_ADDR_PER_BLOCK(inode->i_sb);
	int ptrs_bits = EXT2_ADDR_PER_BLOCK_BITS(inode->i_sb);
	const long direct_blocks = EXT2_NDIR_BLOCKS,
		indirect_blocks = ptrs,
		double_blocks = (1 << (ptrs_bits * 2));
	int n = 0;
	int final = 0;

	if (i_block < 0) {
		ext2_warning (inode->i_sb, "ext2_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++] = EXT2_IND_BLOCK;
		offsets[n++] = i_block;
		final = ptrs;
	} else if ((i_block -= indirect_blocks) < double_blocks) {
		offsets[n++] = EXT2_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++] = EXT2_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 {
		ext2_warning (inode->i_sb, "ext2_block_to_path", "block > big");
	}
	if (boundary)
		*boundary = final - 1 - (i_block & (ptrs - 1));

	return n;
}

/**
 *	ext2_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 *ext2_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, EXT2_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;
		read_lock(&EXT2_I(inode)->i_meta_lock);
		if (!verify_chain(chain, p))
			goto changed;
		add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
		read_unlock(&EXT2_I(inode)->i_meta_lock);
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	read_unlock(&EXT2_I(inode)->i_meta_lock);
	brelse(bh);
	*err = -EAGAIN;
	goto no_block;
failure:
	*err = -EIO;
no_block:
	return p;
}

/**
 *	ext2_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 unsigned long ext2_find_near(struct inode *inode, Indirect *ind)
{
	struct ext2_inode_info *ei = EXT2_I(inode);
	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
	__le32 *p;
	unsigned long bg_start;
	unsigned long 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 refered from inode itself? OK, just put it into
	 * the same cylinder group then.
	 */
	bg_start = (ei->i_block_group * EXT2_BLOCKS_PER_GROUP(inode->i_sb)) +
		le32_to_cpu(EXT2_SB(inode->i_sb)->s_es->s_first_data_block);
	colour = (current->pid % 16) *
			(EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	return bg_start + colour;
}

/**
 *	ext2_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
 *
 *	Returns preferred place for a block (the goal).
 */

static inline int ext2_find_goal(struct inode *inode,
				 long block,
				 Indirect chain[4],
				 Indirect *partial)
{
	struct ext2_block_alloc_info *block_i;

	block_i = EXT2_I(inode)->i_block_alloc_info;

	/*
	 * try the heuristic for sequential allocation,
	 * failing that at least try to get decent locality.
	 */
	if (block_i && (block == block_i->last_alloc_logical_block + 1)
		&& (block_i->last_alloc_physical_block != 0)) {
		return block_i->last_alloc_physical_block + 1;
	}

	return ext2_find_near(inode, partial);
}

/**
 *	ext2_blks_to_allocate: Look up the block map and count the number
 *	of direct blocks need to be allocated for the given branch.
 *
 * 	@branch: chain of indirect blocks
 *	@k: number of blocks need for indirect blocks
 *	@blks: number of data blocks to be mapped.
 *	@blocks_to_boundary:  the offset in the indirect block
 *
 *	return the total number of blocks to be allocate, including the
 *	direct and indirect blocks.
 */
static int
ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
		int blocks_to_boundary)
{
	unsigned long count = 0;

	/*
	 * Simple case, [t,d]Indirect block(s) has not allocated yet
	 * then it's clear blocks on that path have not allocated
	 */
	if (k > 0) {
		/* right now don't hanel cross boundary allocation */
		if (blks < blocks_to_boundary + 1)
			count += blks;
		else
			count += blocks_to_boundary + 1;
		return count;
	}

	count++;
	while (count < blks && count <= blocks_to_boundary
		&& le32_to_cpu(*(branch[0].p + count)) == 0) {
		count++;
	}
	return count;
}

/**
 *	ext2_alloc_blocks: multiple allocate blocks needed for a branch
 *	@indirect_blks: the number of blocks need to allocate for indirect
 *			blocks
 *
 *	@new_blocks: on return it will store the new block numbers for
 *	the indirect blocks(if needed) and the first direct block,
 *	@blks:	on return it will store the total number of allocated
 *		direct blocks
 */
static int ext2_alloc_blocks(struct inode *inode,
			ext2_fsblk_t goal, int indirect_blks, int blks,
			ext2_fsblk_t new_blocks[4], int *err)
{
	int target, i;
	unsigned long count = 0;
	int index = 0;
	ext2_fsblk_t current_block = 0;
	int ret = 0;

	/*
	 * Here we try to allocate the requested multiple blocks at once,
	 * on a best-effort basis.
	 * To build a branch, we should allocate blocks for
	 * the indirect blocks(if not allocated yet), and at least
	 * the first direct block of this branch.  That's the
	 * minimum number of blocks need to allocate(required)
	 */
	target = blks + indirect_blks;

	while (1) {
		count = target;
		/* allocating blocks for indirect blocks and direct blocks */
		current_block = ext2_new_blocks(inode,goal,&count,err);
		if (*err)
			goto failed_out;

		target -= count;
		/* allocate blocks for indirect blocks */
		while (index < indirect_blks && count) {
			new_blocks[index++] = current_block++;
			count--;
		}

		if (count > 0)
			break;
	}

	/* save the new block number for the first direct block */
	new_blocks[index] = current_block;

	/* total number of blocks allocated for direct blocks */
	ret = count;
	*err = 0;
	return ret;
failed_out:
	for (i = 0; i <index; i++)
		ext2_free_blocks(inode, new_blocks[i], 1);
	return ret;
}

/**
 *	ext2_alloc_branch - allocate and set up a chain of blocks.
 *	@inode: owner
 *	@num: depth of the chain (number of blocks to allocate)
 *	@offsets: offsets (in the blocks) to store the pointers to next.
 *	@branch: place to store the chain in.
 *
 *	This function allocates @num blocks, zeroes out all but the last one,
 *	links them into chain and (if we are synchronous) writes them to disk.
 *	In other words, it prepares a branch that can be spliced onto the
 *	inode. It stores the information about that chain in the branch[], in
 *	the same format as ext2_get_branch() would do. We are calling it after
 *	we had read the existing part of chain and partial points to the last
 *	triple of that (one with zero ->key). Upon the exit we have the same
 *	picture as after the successful ext2_get_block(), excpet that in one
 *	place chain is disconnected - *branch->p is still zero (we did not
 *	set the last link), but branch->key contains the number that should
 *	be placed into *branch->p to fill that gap.
 *
 *	If allocation fails we free all blocks we've allocated (and forget
 *	their buffer_heads) and return the error value the from failed
 *	ext2_alloc_block() (normally -ENOSPC). Otherwise we set the chain
 *	as described above and return 0.
 */

static int ext2_alloc_branch(struct inode *inode,
			int indirect_blks, int *blks, ext2_fsblk_t goal,
			int *offsets, Indirect *branch)
{
	int blocksize = inode->i_sb->s_blocksize;
	int i, n = 0;
	int err = 0;
	struct buffer_head *bh;
	int num;
	ext2_fsblk_t new_blocks[4];
	ext2_fsblk_t current_block;

	num = ext2_alloc_blocks(inode, goal, indirect_blks,
				*blks, new_blocks, &err);
	if (err)
		return err;

	branch[0].key = cpu_to_le32(new_blocks[0]);
	/*
	 * metadata blocks and data blocks are allocated.
	 */
	for (n = 1; n <= indirect_blks;  n++) {
		/*
		 * Get buffer_head for parent block, zero it out
		 * and set the pointer to new one, then send
		 * parent to disk.
		 */
		bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
		branch[n].bh = bh;
		lock_buffer(bh);
		memset(bh->b_data, 0, blocksize);
		branch[n].p = (__le32 *) bh->b_data + offsets[n];
		branch[n].key = cpu_to_le32(new_blocks[n]);
		*branch[n].p = branch[n].key;
		if ( n == indirect_blks) {
			current_block = new_blocks[n];
			/*
			 * End of chain, update the last new metablock of
			 * the chain to point to the new allocated
			 * data blocks numbers