inode.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,950 行 · 第 1/5 页

			    th = reiserfs_persistent_transaction(inode->i_sb,3);
			if (th)
			    reiserfs_free_block (th,inode,allocated_block_nr,1);
		    }
		    goto failure ;
		}
		goto research ;
	    }
	    retval = direct2indirect (th, inode, &path, unbh, tail_offset);
	    if (retval) {
		reiserfs_unmap_buffer(unbh);
		reiserfs_free_block (th, inode, allocated_block_nr, 1);
		goto failure;
	    }
	    /* it is important the set_buffer_uptodate is done after
	    ** the direct2indirect.  The buffer might contain valid
	    ** data newer than the data on disk (read by readpage, changed,
	    ** and then sent here by writepage).  direct2indirect needs
	    ** to know if unbh was already up to date, so it can decide
	    ** if the data in unbh needs to be replaced with data from
	    ** the disk
	    */
	    set_buffer_uptodate (unbh);

	    /* unbh->b_page == NULL in case of DIRECT_IO request, this means
	       buffer will disappear shortly, so it should not be added to
	     */
	    if ( unbh->b_page ) {
		/* we've converted the tail, so we must
		** flush unbh before the transaction commits
		*/
		reiserfs_add_tail_list(inode, unbh) ;

		/* mark it dirty now to prevent commit_write from adding
		** this buffer to the inode's dirty buffer list
		*/
		/*
		 * AKPM: changed __mark_buffer_dirty to mark_buffer_dirty().
		 * It's still atomic, but it sets the page dirty too,
		 * which makes it eligible for writeback at any time by the
		 * VM (which was also the case with __mark_buffer_dirty())
		 */
		mark_buffer_dirty(unbh) ;
	    }
	} else {
	    /* append indirect item with holes if needed, when appending
	       pointer to 'block'-th block use block, which is already
	       allocated */
	    struct cpu_key tmp_key;
	    unp_t unf_single=0; // We use this in case we need to allocate only
				// one block which is a fastpath
	    unp_t *un;
	    __u64 max_to_insert=MAX_ITEM_LEN(inode->i_sb->s_blocksize)/UNFM_P_SIZE;
	    __u64 blocks_needed;

	    RFALSE( pos_in_item != ih_item_len(ih) / UNFM_P_SIZE,
		    "vs-804: invalid position for append");
	    /* indirect item has to be appended, set up key of that position */
	    make_cpu_key (&tmp_key, inode,
			  le_key_k_offset (version, &(ih->ih_key)) + op_bytes_number (ih, inode->i_sb->s_blocksize),
			  //pos_in_item * inode->i_sb->s_blocksize,
			  TYPE_INDIRECT, 3);// key type is unimportant

	    blocks_needed = 1 + ((cpu_key_k_offset (&key) - cpu_key_k_offset (&tmp_key)) >> inode->i_sb->s_blocksize_bits);
	    RFALSE( blocks_needed < 0, "green-805: invalid offset");

	    if ( blocks_needed == 1 ) {
		un = &unf_single;
	    } else {
		un=kmalloc( min(blocks_needed,max_to_insert)*UNFM_P_SIZE,
			    GFP_ATOMIC); // We need to avoid scheduling.
		if ( !un) {
		    un = &unf_single;
		    blocks_needed = 1;
		    max_to_insert = 0;
		} else
		    memset(un, 0, UNFM_P_SIZE * min(blocks_needed,max_to_insert));
	    }
	    if ( blocks_needed <= max_to_insert) {
		/* we are going to add target block to the file. Use allocated
		   block for that */
		un[blocks_needed-1] = cpu_to_le32 (allocated_block_nr);
		set_block_dev_mapped (bh_result, allocated_block_nr, inode);
		set_buffer_new(bh_result);
		done = 1;
	    } else {
		/* paste hole to the indirect item */
		/* If kmalloc failed, max_to_insert becomes zero and it means we
		   only have space for one block */
		blocks_needed=max_to_insert?max_to_insert:1;
	    }
	    retval = reiserfs_paste_into_item (th, &path, &tmp_key, inode, (char *)un, UNFM_P_SIZE * blocks_needed);

	    if (blocks_needed != 1)
		kfree(un);

	    if (retval) {
		reiserfs_free_block (th, inode, allocated_block_nr, 1);
		goto failure;
	    }
	    if (!done) {
		/* We need to mark new file size in case this function will be
		   interrupted/aborted later on. And we may do this only for
		   holes. */
		inode->i_size += inode->i_sb->s_blocksize * blocks_needed;
	    }
	}

	if (done == 1)
	    break;

	/* this loop could log more blocks than we had originally asked
	** for.  So, we have to allow the transaction to end if it is
	** too big or too full.  Update the inode so things are 
	** consistent if we crash before the function returns
	**
	** release the path so that anybody waiting on the path before
	** ending their transaction will be able to continue.
	*/
	if (journal_transaction_should_end(th, th->t_blocks_allocated)) {
	  restart_transaction(th, inode, &path) ;
	}
	/* inserting indirect pointers for a hole can take a 
	** long time.  reschedule if needed
	*/
	cond_resched();

	retval = search_for_position_by_key (inode->i_sb, &key, &path);
	if (retval == IO_ERROR) {
	    retval = -EIO;
	    goto failure;
	}
	if (retval == POSITION_FOUND) {
	    reiserfs_warning (inode->i_sb, "vs-825: reiserfs_get_block: "
			      "%K should not be found", &key);
	    retval = -EEXIST;
	    if (allocated_block_nr)
	        reiserfs_free_block (th, inode, allocated_block_nr, 1);
	    pathrelse(&path) ;
	    goto failure;
	}
	bh = get_last_bh (&path);
	ih = get_ih (&path);
	item = get_item (&path);
	pos_in_item = path.pos_in_item;
    } while (1);


    retval = 0;

 failure:
    if (th && !dangle) {
      reiserfs_update_sd(th, inode) ;
      reiserfs_end_persistent_transaction(th);
    }
    reiserfs_write_unlock(inode->i_sb);
    reiserfs_check_path(&path) ;
    return retval;
}

static int
reiserfs_readpages(struct file *file, struct address_space *mapping,
		struct list_head *pages, unsigned nr_pages)
{
    return mpage_readpages(mapping, pages, nr_pages, reiserfs_get_block);
}

/* Compute real number of used bytes by file
 * Following three functions can go away when we'll have enough space in stat item
 */
static int real_space_diff(struct inode *inode, int sd_size)
{
    int bytes;
    loff_t blocksize = inode->i_sb->s_blocksize ;

    if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode))
        return sd_size ;

    /* End of file is also in full block with indirect reference, so round
    ** up to the next block.
    **
    ** there is just no way to know if the tail is actually packed
    ** on the file, so we have to assume it isn't.  When we pack the
    ** tail, we add 4 bytes to pretend there really is an unformatted
    ** node pointer
    */
    bytes = ((inode->i_size + (blocksize-1)) >> inode->i_sb->s_blocksize_bits) * UNFM_P_SIZE + sd_size;
    return bytes ;
}

static inline loff_t to_real_used_space(struct inode *inode, ulong blocks,
                                        int sd_size)
{
    if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode)) {
        return inode->i_size + (loff_t)(real_space_diff(inode, sd_size)) ;
    }
    return ((loff_t)real_space_diff(inode, sd_size)) + (((loff_t)blocks) << 9);
}

/* Compute number of blocks used by file in ReiserFS counting */
static inline ulong to_fake_used_blocks(struct inode *inode, int sd_size)
{
    loff_t bytes = inode_get_bytes(inode) ;
    loff_t real_space = real_space_diff(inode, sd_size) ;

    /* keeps fsck and non-quota versions of reiserfs happy */
    if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode)) {
        bytes += (loff_t)511 ;
    }

    /* files from before the quota patch might i_blocks such that
    ** bytes < real_space.  Deal with that here to prevent it from
    ** going negative.
    */
    if (bytes < real_space)
        return 0 ;
    return (bytes - real_space) >> 9;
}

//
// BAD: new directories have stat data of new type and all other items
// of old type. Version stored in the inode says about body items, so
// in update_stat_data we can not rely on inode, but have to check
// item version directly
//

// called by read_locked_inode
static void init_inode (struct inode * inode, struct path * path)
{
    struct buffer_head * bh;
    struct item_head * ih;
    __u32 rdev;
    //int version = ITEM_VERSION_1;

    bh = PATH_PLAST_BUFFER (path);
    ih = PATH_PITEM_HEAD (path);


    copy_key (INODE_PKEY (inode), &(ih->ih_key));
    inode->i_blksize = reiserfs_default_io_size;

    INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list ));
    REISERFS_I(inode)->i_flags = 0;
    REISERFS_I(inode)->i_prealloc_block = 0;
    REISERFS_I(inode)->i_prealloc_count = 0;
    REISERFS_I(inode)->i_trans_id = 0;
    REISERFS_I(inode)->i_jl = NULL;
    REISERFS_I(inode)->i_acl_access = NULL;
    REISERFS_I(inode)->i_acl_default = NULL;
    init_rwsem (&REISERFS_I(inode)->xattr_sem);

    if (stat_data_v1 (ih)) {
	struct stat_data_v1 * sd = (struct stat_data_v1 *)B_I_PITEM (bh, ih);
	unsigned long blocks;

	set_inode_item_key_version (inode, KEY_FORMAT_3_5);
        set_inode_sd_version (inode, STAT_DATA_V1);
	inode->i_mode  = sd_v1_mode(sd);
	inode->i_nlink = sd_v1_nlink(sd);
	inode->i_uid   = sd_v1_uid(sd);
	inode->i_gid   = sd_v1_gid(sd);
	inode->i_size  = sd_v1_size(sd);
	inode->i_atime.tv_sec = sd_v1_atime(sd);
	inode->i_mtime.tv_sec = sd_v1_mtime(sd);
	inode->i_ctime.tv_sec = sd_v1_ctime(sd);
	inode->i_atime.tv_nsec = 0;
	inode->i_ctime.tv_nsec = 0;
	inode->i_mtime.tv_nsec = 0;

	inode->i_blocks = sd_v1_blocks(sd);
	inode->i_generation = le32_to_cpu (INODE_PKEY (inode)->k_dir_id);
	blocks = (inode->i_size + 511) >> 9;
	blocks = _ROUND_UP (blocks, inode->i_sb->s_blocksize >> 9);
	if (inode->i_blocks > blocks) {
	    // there was a bug in <=3.5.23 when i_blocks could take negative
	    // values. Starting from 3.5.17 this value could even be stored in
	    // stat data. For such files we set i_blocks based on file
	    // size. Just 2 notes: this can be wrong for sparce files. On-disk value will be
	    // only updated if file's inode will ever change
	    inode->i_blocks = blocks;
	}

        rdev = sd_v1_rdev(sd);
	REISERFS_I(inode)->i_first_direct_byte = sd_v1_first_direct_byte(sd);
	/* an early bug in the quota code can give us an odd number for the
	** block count.  This is incorrect, fix it here.
	*/
	if (inode->i_blocks & 1) {
	    inode->i_blocks++ ;
	}
	inode_set_bytes(inode, to_real_used_space(inode, inode->i_blocks,
	                                          SD_V1_SIZE));
	/* nopack is initially zero for v1 objects. For v2 objects,
	   nopack is initialised from sd_attrs */
	REISERFS_I(inode)->i_flags &= ~i_nopack_mask;
    } else {
	// new stat data found, but object may have old items
	// (directories and symlinks)
	struct stat_data * sd = (struct stat_data *)B_I_PITEM (bh, ih);

	inode->i_mode   = sd_v2_mode(sd);
	inode->i_nlink  = sd_v2_nlink(sd);
	inode->i_uid    = sd_v2_uid(sd);
	inode->i_size   = sd_v2_size(sd);
	inode->i_gid    = sd_v2_gid(sd);
	inode->i_mtime.tv_sec  = sd_v2_mtime(sd);
	inode->i_atime.tv_sec = sd_v2_atime(sd);
	inode->i_ctime.tv_sec  = sd_v2_ctime(sd);
	inode->i_ctime.tv_nsec = 0;
	inode->i_mtime.tv_nsec = 0;
	inode->i_atime.tv_nsec = 0;
	inode->i_blocks = sd_v2_blocks(sd);
        rdev            = sd_v2_rdev(sd);
	if( S_ISCHR( inode -> i_mode ) || S_ISBLK( inode -> i_mode ) )
	    inode->i_generation = le32_to_cpu (INODE_PKEY (inode)->k_dir_id);
	else
            inode->i_generation = sd_v2_generation(sd);

	if (S_ISDIR (inode->i_mode) || S_ISLNK (inode->i_mode))
	    set_inode_item_key_version (inode, KEY_FORMAT_3_5);
	else
	    set_inode_item_key_version (inode, KEY_FORMAT_3_6);
	REISERFS_I(inode)->i_first_direct_byte = 0;
	set_inode_sd_version (inode, STAT_DATA_V2);
	inode_set_bytes(inode, to_real_used_space(inode, inode->i_blocks,
	                                          SD_V2_SIZE));
	/* read persistent inode attributes from sd and initalise
	   generic inode flags from them */
	REISERFS_I(inode)->i_attrs = sd_v2_attrs( sd );
	sd_attrs_to_i_attrs( sd_v2_attrs( sd ), inode );
    }

    pathrelse (path);
    if (S_ISREG (inode->i_mode)) {
	inode->i_op = &reiserfs_file_inode_operations;
	inode->i_fop = &reiserfs_file_operations;
	inode->i_mapping->a_ops = &reiserfs_address_space_operations ;
    } else if (S_ISDIR (inode->i_mode)) {
	inode->i_op = &reiserfs_dir_inode_operations;
	inode->i_fop = &reiserfs_dir_operations;
    } else if (S_ISLNK (inode->i_mode)) {
	inode->i_op = &reiserfs_symlink_inode_operations;
	inode->i_mapping->a_ops = &reiserfs_address_space_operations;
    } else {
	inode->i_blocks = 0;
	inode->i_op = &reiserfs_special_inode_operations;
	init_special_inode(inode, inode->i_mode, new_decode_dev(rdev));
    }
}


// update new stat data with inode fields
static void inode2sd (void * sd, struct inode * inode, loff_t size)
{
    struct stat_data * sd_v2 = (struct stat_data *)sd;
    __u16 flags;

    set_sd_v2_mode(sd_v2, inode->i_mode );
    set_sd_v2_nlink(sd_v2, inode->i_nlink );
    set_sd_v2_uid(sd_v2, inode->i_uid );
    set_sd_v2_size(sd_v2, size );
    set_sd_v2_gid(sd_v2, inode->i_gid );
    set_sd_v2_mtime(sd_v2, inode->i_mtime.tv_sec );
    set_sd_v2_atime(sd_v2, inode->i_atime.tv_sec );
    set_sd_v2_ctime(sd_v2, inode->i_ctime.tv_sec );
    set_sd_v2_blocks(sd_v2, to_fake_used_blocks(inode, SD_V2_SIZE));
    if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
	set_sd_v2_rdev(sd_v2, new_encode_dev(inode->i_rdev));
    else
	set_sd_v2_generation(sd_v2, inode->i_generation);
    flags = REISERFS_I(inode)->i_attrs;
    i_attrs_to_sd_attrs( inode, &flags );
    set_sd_v2_attrs( sd_v2, flags );
}


// used to copy inode's fields to old stat data
static void inode2sd_v1 (void * sd, struct inode * inode, loff_t size)
{
    struct stat_data_v1 * sd_v1 = (struct stat_data_v1 *)sd;

    set_sd_v1_mode(sd_v1, inode->i_mode );
    set_sd_v1_uid(sd_v1, inode->i_uid );
    set_sd_v1_gid(sd_v1, inode->i_gid );
    set_sd_v1_nlink(sd_v1, inode->i_nlink );
    set_sd_v1_size(sd_v1, size );
    set_sd_v1_atime(sd_v1, inode->i_atime.tv_sec );
    set_sd_v1_ctime(sd_v1, inode->i_ctime.tv_sec );
    set_sd_v1_mtime(sd_v1, inode->i_mtime.tv_sec );