inode.c 91.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9
/*
 * 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>
10
#include <linux/exportfs.h>
L
Linus Torvalds 已提交
11 12 13 14 15 16 17 18 19
#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>
V
Vladimir Saveliev 已提交
20
#include <linux/swap.h>
L
Linus Torvalds 已提交
21

V
Vladimir Saveliev 已提交
22 23 24 25
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);
L
Linus Torvalds 已提交
26

27
void reiserfs_delete_inode(struct inode *inode)
L
Linus Torvalds 已提交
28
{
29 30 31 32 33
	/* 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;
34
	int err;
L
Linus Torvalds 已提交
35

36 37
	truncate_inode_pages(&inode->i_data, 0);

38
	reiserfs_write_lock(inode->i_sb);
L
Linus Torvalds 已提交
39

40 41 42
	/* 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);
L
Linus Torvalds 已提交
43

44
		if (journal_begin(&th, inode->i_sb, jbegin_count))
45 46
			goto out;
		reiserfs_update_inode_transaction(inode);
L
Linus Torvalds 已提交
47

48 49
		reiserfs_discard_prealloc(&th, inode);

50
		err = reiserfs_delete_object(&th, inode);
L
Linus Torvalds 已提交
51

52 53 54
		/* 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 */
55 56
		if (!err) 
			DQUOT_FREE_INODE(inode);
57

58
		if (journal_end(&th, inode->i_sb, jbegin_count))
59
			goto out;
L
Linus Torvalds 已提交
60

61 62 63 64 65 66
		/* check return value from reiserfs_delete_object after
		 * ending the transaction
		 */
		if (err)
		    goto out;

67 68 69 70 71 72 73 74 75 76 77
		/* 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);
L
Linus Torvalds 已提交
78 79
}

80 81
static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
			  __u32 objectid, loff_t offset, int type, int length)
L
Linus Torvalds 已提交
82
{
83
	key->version = version;
L
Linus Torvalds 已提交
84

85 86 87 88 89
	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;
L
Linus Torvalds 已提交
90 91 92 93
}

/* take base of inode_key (it comes from inode always) (dirid, objectid) and version from an inode, set
   offset and type of key */
94 95
void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
		  int type, int length)
L
Linus Torvalds 已提交
96
{
97 98 99 100
	_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);
L
Linus Torvalds 已提交
101 102 103 104 105
}

//
// when key is 0, do not set version and short key
//
106 107 108 109
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 */ )
L
Linus Torvalds 已提交
110
{
111 112 113 114 115 116 117 118 119 120 121 122 123
	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);
L
Linus Torvalds 已提交
124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
}

//
// 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
*/
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
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);
	}
L
Linus Torvalds 已提交
173 174 175 176
}

/* 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 */
177 178 179
static inline int allocation_needed(int retval, b_blocknr_t allocated,
				    struct item_head *ih,
				    __le32 * item, int pos_in_item)
L
Linus Torvalds 已提交
180
{
181 182 183 184 185 186
	if (allocated)
		return 0;
	if (retval == POSITION_FOUND && is_indirect_le_ih(ih) &&
	    get_block_num(item, pos_in_item))
		return 0;
	return 1;
L
Linus Torvalds 已提交
187 188
}

189
static inline int indirect_item_found(int retval, struct item_head *ih)
L
Linus Torvalds 已提交
190
{
191
	return (retval == POSITION_FOUND) && is_indirect_le_ih(ih);
L
Linus Torvalds 已提交
192 193
}

194 195
static inline void set_block_dev_mapped(struct buffer_head *bh,
					b_blocknr_t block, struct inode *inode)
L
Linus Torvalds 已提交
196 197 198 199 200 201 202 203
{
	map_bh(bh, inode->i_sb, block);
}

//
// files which were created in the earlier version can not be longer,
// than 2 gb
//
204
static int file_capable(struct inode *inode, sector_t block)
L
Linus Torvalds 已提交
205
{
206 207 208
	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;
L
Linus Torvalds 已提交
209

210
	return 0;
L
Linus Torvalds 已提交
211 212
}

A
Adrian Bunk 已提交
213 214
static int restart_transaction(struct reiserfs_transaction_handle *th,
			       struct inode *inode, struct treepath *path)
215 216 217 218 219 220 221 222
{
	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);

223 224
	pathrelse(path);

225 226 227 228 229 230 231 232 233 234 235 236
	/* 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;
L
Linus Torvalds 已提交
237 238 239 240 241 242 243 244 245 246
}

// 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.

247
static int _get_block_create_0(struct inode *inode, sector_t block,
248
			       struct buffer_head *bh_result, int args)
L
Linus Torvalds 已提交
249
{
250 251 252 253 254
	INITIALIZE_PATH(path);
	struct cpu_key key;
	struct buffer_head *bh;
	struct item_head *ih, tmp_ih;
	int fs_gen;
255
	b_blocknr_t blocknr;
256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
	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)) {
L
Linus Torvalds 已提交
338
		set_buffer_uptodate(bh_result);
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410
		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;
L
Linus Torvalds 已提交
411

412 413 414 415 416 417 418
	/* 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;
}
L
Linus Torvalds 已提交
419 420 421

// this is called to create file map. So, _get_block_create_0 will not
// read direct item
422 423
static int reiserfs_bmap(struct inode *inode, sector_t block,
			 struct buffer_head *bh_result, int create)
L
Linus Torvalds 已提交
424
{
425 426 427 428 429 430 431 432
	if (!file_capable(inode, block))
		return -EFBIG;

	reiserfs_write_lock(inode->i_sb);
	/* do not read the direct item */
	_get_block_create_0(inode, block, bh_result, 0);
	reiserfs_write_unlock(inode->i_sb);
	return 0;
L
Linus Torvalds 已提交
433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451
}

/* special version of get_block that is only used by grab_tail_page right
** now.  It is sent to block_prepare_write, and when you try to get a
** block past the end of the file (or a block from a hole) it returns
** -ENOENT instead of a valid buffer.  block_prepare_write expects to
** be able to do i/o on the buffers returned, unless an error value
** is also returned.
** 
** So, this allows block_prepare_write to be used for reading a single block
** in a page.  Where it does not produce a valid page for holes, or past the
** end of the file.  This turns out to be exactly what we need for reading
** tails for conversion.
**
** The point of the wrapper is forcing a certain value for create, even
** though the VFS layer is calling this function with create==1.  If you 
** don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block, 
** don't use this function.
*/
452 453 454 455 456
static int reiserfs_get_block_create_0(struct inode *inode, sector_t block,
				       struct buffer_head *bh_result,
				       int create)
{
	return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE);
L
Linus Torvalds 已提交
457 458 459 460 461 462 463 464 465
}

/* This is special helper for reiserfs_get_block in case we are executing
   direct_IO request. */
static int reiserfs_get_blocks_direct_io(struct inode *inode,
					 sector_t iblock,
					 struct buffer_head *bh_result,
					 int create)
{
466 467 468
	int ret;

	bh_result->b_page = NULL;
L
Linus Torvalds 已提交
469

470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501
	/* We set the b_size before reiserfs_get_block call since it is
	   referenced in convert_tail_for_hole() that may be called from
	   reiserfs_get_block() */
	bh_result->b_size = (1 << inode->i_blkbits);

	ret = reiserfs_get_block(inode, iblock, bh_result,
				 create | GET_BLOCK_NO_DANGLE);
	if (ret)
		goto out;

	/* don't allow direct io onto tail pages */
	if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
		/* make sure future calls to the direct io funcs for this offset
		 ** in the file fail by unmapping the buffer
		 */
		clear_buffer_mapped(bh_result);
		ret = -EINVAL;
	}
	/* Possible unpacked tail. Flush the data before pages have
	   disappeared */
	if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
		int err;
		lock_kernel();
		err = reiserfs_commit_for_inode(inode);
		REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
		unlock_kernel();
		if (err < 0)
			ret = err;
	}
      out:
	return ret;
}
L
Linus Torvalds 已提交
502 503 504 505 506 507 508 509 510 511 512

/*
** helper function for when reiserfs_get_block is called for a hole
** but the file tail is still in a direct item
** bh_result is the buffer head for the hole
** tail_offset is the offset of the start of the tail in the file
**
** This calls prepare_write, which will start a new transaction
** you should not be in a transaction, or have any paths held when you
** call this.
*/
513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
static int convert_tail_for_hole(struct inode *inode,
				 struct buffer_head *bh_result,
				 loff_t tail_offset)
{
	unsigned long index;
	unsigned long tail_end;
	unsigned long tail_start;
	struct page *tail_page;
	struct page *hole_page = bh_result->b_page;
	int retval = 0;

	if ((tail_offset & (bh_result->b_size - 1)) != 1)
		return -EIO;

	/* always try to read until the end of the block */
	tail_start = tail_offset & (PAGE_CACHE_SIZE - 1);
	tail_end = (tail_start | (bh_result->b_size - 1)) + 1;

	index = tail_offset >> PAGE_CACHE_SHIFT;
	/* hole_page can be zero in case of direct_io, we are sure
	   that we cannot get here if we write with O_DIRECT into
	   tail page */
	if (!hole_page || index != hole_page->index) {
		tail_page = grab_cache_page(inode->i_mapping, index);
		retval = -ENOMEM;
		if (!tail_page) {
			goto out;
		}
	} else {
		tail_page = hole_page;
	}

	/* we don't have to make sure the conversion did not happen while
	 ** we were locking the page because anyone that could convert
547
	 ** must first take i_mutex.
548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570
	 **
	 ** We must fix the tail page for writing because it might have buffers
	 ** that are mapped, but have a block number of 0.  This indicates tail
	 ** data that has been read directly into the page, and block_prepare_write
	 ** won't trigger a get_block in this case.
	 */
	fix_tail_page_for_writing(tail_page);
	retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end);
	if (retval)
		goto unlock;

	/* tail conversion might change the data in the page */
	flush_dcache_page(tail_page);

	retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end);

      unlock:
	if (tail_page != hole_page) {
		unlock_page(tail_page);
		page_cache_release(tail_page);
	}
      out:
	return retval;
L
Linus Torvalds 已提交
571 572 573
}

static inline int _allocate_block(struct reiserfs_transaction_handle *th,
574
				  sector_t block,
575 576
				  struct inode *inode,
				  b_blocknr_t * allocated_block_nr,
577
				  struct treepath *path, int flags)
578 579 580
{
	BUG_ON(!th->t_trans_id);

L
Linus Torvalds 已提交
581
#ifdef REISERFS_PREALLOCATE
582
	if (!(flags & GET_BLOCK_NO_IMUX)) {
583 584 585
		return reiserfs_new_unf_blocknrs2(th, inode, allocated_block_nr,
						  path, block);
	}
L
Linus Torvalds 已提交
586
#endif
587 588
	return reiserfs_new_unf_blocknrs(th, inode, allocated_block_nr, path,
					 block);
L
Linus Torvalds 已提交
589 590
}

591 592
int reiserfs_get_block(struct inode *inode, sector_t block,
		       struct buffer_head *bh_result, int create)
L
Linus Torvalds 已提交
593
{
594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621
	int repeat, retval = 0;
	b_blocknr_t allocated_block_nr = 0;	// b_blocknr_t is (unsigned) 32 bit int
	INITIALIZE_PATH(path);
	int pos_in_item;
	struct cpu_key key;
	struct buffer_head *bh, *unbh = NULL;
	struct item_head *ih, tmp_ih;
	__le32 *item;
	int done;
	int fs_gen;
	struct reiserfs_transaction_handle *th = NULL;
	/* space reserved in transaction batch: 
	   . 3 balancings in direct->indirect conversion
	   . 1 block involved into reiserfs_update_sd()
	   XXX in practically impossible worst case direct2indirect()
	   can incur (much) more than 3 balancings.
	   quota update for user, group */
	int jbegin_count =
	    JOURNAL_PER_BALANCE_CNT * 3 + 1 +
	    2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
	int version;
	int dangle = 1;
	loff_t new_offset =
	    (((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1;

	/* bad.... */
	reiserfs_write_lock(inode->i_sb);
	version = get_inode_item_key_version(inode);
L
Linus Torvalds 已提交
622

623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662
	if (!file_capable(inode, block)) {
		reiserfs_write_unlock(inode->i_sb);
		return -EFBIG;
	}

	/* if !create, we aren't changing the FS, so we don't need to
	 ** log anything, so we don't need to start a transaction
	 */
	if (!(create & GET_BLOCK_CREATE)) {
		int ret;
		/* find number of block-th logical block of the file */
		ret = _get_block_create_0(inode, block, bh_result,
					  create | GET_BLOCK_READ_DIRECT);
		reiserfs_write_unlock(inode->i_sb);
		return ret;
	}
	/*
	 * if we're already in a transaction, make sure to close
	 * any new transactions we start in this func
	 */
	if ((create & GET_BLOCK_NO_DANGLE) ||
	    reiserfs_transaction_running(inode->i_sb))
		dangle = 0;

	/* If file is of such a size, that it might have a tail and tails are enabled
	 ** we should mark it as possibly needing tail packing on close
	 */
	if ((have_large_tails(inode->i_sb)
	     && inode->i_size < i_block_size(inode) * 4)
	    || (have_small_tails(inode->i_sb)
		&& inode->i_size < i_block_size(inode)))
		REISERFS_I(inode)->i_flags |= i_pack_on_close_mask;

	/* set the key of the first byte in the 'block'-th block of file */
	make_cpu_key(&key, inode, new_offset, TYPE_ANY, 3 /*key length */ );
	if ((new_offset + inode->i_sb->s_blocksize - 1) > inode->i_size) {
	      start_trans:
		th = reiserfs_persistent_transaction(inode->i_sb, jbegin_count);
		if (!th) {
			retval = -ENOMEM;
L
Linus Torvalds 已提交
663 664
			goto failure;
		}
665 666 667
		reiserfs_update_inode_transaction(inode);
	}
      research:
L
Linus Torvalds 已提交
668

669
	retval = search_for_position_by_key(inode->i_sb, &key, &path);
L
Linus Torvalds 已提交
670
	if (retval == IO_ERROR) {
671 672 673 674 675 676 677
		retval = -EIO;
		goto failure;
	}

	bh = get_last_bh(&path);
	ih = get_ih(&path);
	item = get_item(&path);
L
Linus Torvalds 已提交
678 679
	pos_in_item = path.pos_in_item;

680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844
	fs_gen = get_generation(inode->i_sb);
	copy_item_head(&tmp_ih, ih);

	if (allocation_needed
	    (retval, allocated_block_nr, ih, item, pos_in_item)) {
		/* we have to allocate block for the unformatted node */
		if (!th) {
			pathrelse(&path);
			goto start_trans;
		}

		repeat =
		    _allocate_block(th, block, inode, &allocated_block_nr,
				    &path, create);

		if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) {
			/* restart the transaction to give the journal a chance to free
			 ** some blocks.  releases the path, so we have to go back to
			 ** research if we succeed on the second try
			 */
			SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1;
			retval = restart_transaction(th, inode, &path);
			if (retval)
				goto failure;
			repeat =
			    _allocate_block(th, block, inode,
					    &allocated_block_nr, NULL, create);

			if (repeat != NO_DISK_SPACE && repeat != QUOTA_EXCEEDED) {
				goto research;
			}
			if (repeat == QUOTA_EXCEEDED)
				retval = -EDQUOT;
			else
				retval = -ENOSPC;
			goto failure;
		}

		if (fs_changed(fs_gen, inode->i_sb)
		    && item_moved(&tmp_ih, &path)) {
			goto research;
		}
	}

	if (indirect_item_found(retval, ih)) {
		b_blocknr_t unfm_ptr;
		/* 'block'-th block is in the file already (there is
		   corresponding cell in some indirect item). But it may be
		   zero unformatted node pointer (hole) */
		unfm_ptr = get_block_num(item, pos_in_item);
		if (unfm_ptr == 0) {
			/* use allocated block to plug the hole */
			reiserfs_prepare_for_journal(inode->i_sb, bh, 1);
			if (fs_changed(fs_gen, inode->i_sb)
			    && item_moved(&tmp_ih, &path)) {
				reiserfs_restore_prepared_buffer(inode->i_sb,
								 bh);
				goto research;
			}
			set_buffer_new(bh_result);
			if (buffer_dirty(bh_result)
			    && reiserfs_data_ordered(inode->i_sb))
				reiserfs_add_ordered_list(inode, bh_result);
			put_block_num(item, pos_in_item, allocated_block_nr);
			unfm_ptr = allocated_block_nr;
			journal_mark_dirty(th, inode->i_sb, bh);
			reiserfs_update_sd(th, inode);
		}
		set_block_dev_mapped(bh_result, unfm_ptr, inode);
		pathrelse(&path);
		retval = 0;
		if (!dangle && th)
			retval = reiserfs_end_persistent_transaction(th);

		reiserfs_write_unlock(inode->i_sb);

		/* the item was found, so new blocks were not added to the file
		 ** there is no need to make sure the inode is updated with this 
		 ** transaction
		 */
		return retval;
	}

	if (!th) {
		pathrelse(&path);
		goto start_trans;
	}

	/* desired position is not found or is in the direct item. We have
	   to append file with holes up to 'block'-th block converting
	   direct items to indirect one if necessary */
	done = 0;
	do {
		if (is_statdata_le_ih(ih)) {
			__le32 unp = 0;
			struct cpu_key tmp_key;

			/* indirect item has to be inserted */
			make_le_item_head(&tmp_ih, &key, version, 1,
					  TYPE_INDIRECT, UNFM_P_SIZE,
					  0 /* free_space */ );

			if (cpu_key_k_offset(&key) == 1) {
				/* we are going to add 'block'-th block to the file. Use
				   allocated block for that */
				unp = cpu_to_le32(allocated_block_nr);
				set_block_dev_mapped(bh_result,
						     allocated_block_nr, inode);
				set_buffer_new(bh_result);
				done = 1;
			}
			tmp_key = key;	// ;)
			set_cpu_key_k_offset(&tmp_key, 1);
			PATH_LAST_POSITION(&path)++;

			retval =
			    reiserfs_insert_item(th, &path, &tmp_key, &tmp_ih,
						 inode, (char *)&unp);
			if (retval) {
				reiserfs_free_block(th, inode,
						    allocated_block_nr, 1);
				goto failure;	// retval == -ENOSPC, -EDQUOT or -EIO or -EEXIST
			}
			//mark_tail_converted (inode);
		} else if (is_direct_le_ih(ih)) {
			/* direct item has to be converted */
			loff_t tail_offset;

			tail_offset =
			    ((le_ih_k_offset(ih) -
			      1) & ~(inode->i_sb->s_blocksize - 1)) + 1;
			if (tail_offset == cpu_key_k_offset(&key)) {
				/* direct item we just found fits into block we have
				   to map. Convert it into unformatted node: use
				   bh_result for the conversion */
				set_block_dev_mapped(bh_result,
						     allocated_block_nr, inode);
				unbh = bh_result;
				done = 1;
			} else {
				/* we have to padd file tail stored in direct item(s)
				   up to block size and convert it to unformatted
				   node. FIXME: this should also get into page cache */

				pathrelse(&path);
				/*
				 * ugly, but we can only end the transaction if
				 * we aren't nested
				 */
				BUG_ON(!th->t_refcount);
				if (th->t_refcount == 1) {
					retval =
					    reiserfs_end_persistent_transaction
					    (th);
					th = NULL;
					if (retval)
						goto failure;
				}

				retval =
				    convert_tail_for_hole(inode, bh_result,
							  tail_offset);
				if (retval) {
					if (retval != -ENOSPC)
						reiserfs_warning(inode->i_sb,
J
Jeff Mahoney 已提交
845 846 847
							 "clm-6004",
							 "convert tail failed "
							 "inode %lu, error %d",
848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926
								 inode->i_ino,
								 retval);
					if (allocated_block_nr) {
						/* the bitmap, the super, and the stat data == 3 */
						if (!th)
							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

927 928
			RFALSE(cpu_key_k_offset(&tmp_key) > cpu_key_k_offset(&key),
			       "green-805: invalid offset");
929 930 931 932 933 934 935 936 937
			blocks_needed =
			    1 +
			    ((cpu_key_k_offset(&key) -
			      cpu_key_k_offset(&tmp_key)) >> inode->i_sb->
			     s_blocksize_bits);

			if (blocks_needed == 1) {
				un = &unf_single;
			} else {
938
				un = kzalloc(min(blocks_needed, max_to_insert) * UNFM_P_SIZE, GFP_ATOMIC);	// We need to avoid scheduling.
939 940 941 942
				if (!un) {
					un = &unf_single;
					blocks_needed = 1;
					max_to_insert = 0;
943
				}
944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982
			}
			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;
			}
		}
L
Linus Torvalds 已提交
983

984 985
		if (done == 1)
			break;
L
Linus Torvalds 已提交
986

987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003
		/* 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)) {
			retval = restart_transaction(th, inode, &path);
			if (retval)
				goto failure;
		}
		/* inserting indirect pointers for a hole can take a 
		 ** long time.  reschedule if needed
		 */
		cond_resched();
L
Linus Torvalds 已提交
1004

1005 1006 1007 1008 1009 1010
		retval = search_for_position_by_key(inode->i_sb, &key, &path);
		if (retval == IO_ERROR) {
			retval = -EIO;
			goto failure;
		}
		if (retval == POSITION_FOUND) {
J
Jeff Mahoney 已提交
1011
			reiserfs_warning(inode->i_sb, "vs-825",
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
					 "%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 || (retval && !th->t_trans_id))) {
		int err;
		if (th->t_trans_id)
			reiserfs_update_sd(th, inode);
		err = reiserfs_end_persistent_transaction(th);
		if (err)
			retval = err;
	}

	reiserfs_write_unlock(inode->i_sb);
	reiserfs_check_path(&path);
	return retval;
L
Linus Torvalds 已提交
1041 1042 1043 1044
}

static int
reiserfs_readpages(struct file *file, struct address_space *mapping,
1045
		   struct list_head *pages, unsigned nr_pages)
L
Linus Torvalds 已提交
1046
{
1047
	return mpage_readpages(mapping, pages, nr_pages, reiserfs_get_block);
L
Linus Torvalds 已提交
1048 1049 1050 1051 1052 1053 1054
}

/* 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)
{
1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
	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;
L
Linus Torvalds 已提交
1074 1075 1076
}

static inline loff_t to_real_used_space(struct inode *inode, ulong blocks,
1077
					int sd_size)
L
Linus Torvalds 已提交
1078
{
1079 1080 1081 1082 1083 1084
	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);
L
Linus Torvalds 已提交
1085 1086 1087 1088 1089
}

/* Compute number of blocks used by file in ReiserFS counting */
static inline ulong to_fake_used_blocks(struct inode *inode, int sd_size)
{
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
	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;
L
Linus Torvalds 已提交
1105 1106 1107 1108 1109 1110 1111 1112 1113 1114
}

//
// 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
1115
static void init_inode(struct inode *inode, struct treepath *path)
L
Linus Torvalds 已提交
1116
{
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132
	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));

	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;
1133
	mutex_init(&(REISERFS_I(inode)->i_mmap));
1134 1135
	reiserfs_init_acl_access(inode);
	reiserfs_init_acl_default(inode);
1136
	reiserfs_init_xattr_rwsem(inode);
1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168

	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;
		}
L
Linus Torvalds 已提交
1169

1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207
		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);
L
Linus Torvalds 已提交
1208

1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
		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));
	}
}
L
Linus Torvalds 已提交
1241 1242

// update new stat data with inode fields
1243
static void inode2sd(void *sd, struct inode *inode, loff_t size)
L
Linus Torvalds 已提交
1244
{
1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263
	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);
L
Linus Torvalds 已提交
1264 1265 1266
}

// used to copy inode's fields to old stat data
1267
static void inode2sd_v1(void *sd, struct inode *inode, loff_t size)
L
Linus Torvalds 已提交
1268
{
1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283
	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);

	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
		set_sd_v1_rdev(sd_v1, new_encode_dev(inode->i_rdev));
	else
		set_sd_v1_blocks(sd_v1, to_fake_used_blocks(inode, SD_V1_SIZE));
L
Linus Torvalds 已提交
1284

1285 1286 1287 1288
	// Sigh. i_first_direct_byte is back
	set_sd_v1_first_direct_byte(sd_v1,
				    REISERFS_I(inode)->i_first_direct_byte);
}
L
Linus Torvalds 已提交
1289 1290 1291 1292

/* NOTE, you must prepare the buffer head before sending it here,
** and then log it after the call
*/
1293
static void update_stat_data(struct treepath *path, struct inode *inode,
1294
			     loff_t size)
L
Linus Torvalds 已提交
1295
{
1296 1297 1298 1299 1300 1301 1302
	struct buffer_head *bh;
	struct item_head *ih;

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

	if (!is_statdata_le_ih(ih))
J
Jeff Mahoney 已提交
1303
		reiserfs_panic(inode->i_sb, "vs-13065", "key %k, found item %h",
1304 1305 1306 1307 1308 1309 1310 1311
			       INODE_PKEY(inode), ih);

	if (stat_data_v1(ih)) {
		// path points to old stat data
		inode2sd_v1(B_I_PITEM(bh, ih), inode, size);
	} else {
		inode2sd(B_I_PITEM(bh, ih), inode, size);
	}
L
Linus Torvalds 已提交
1312

1313 1314
	return;
}
L
Linus Torvalds 已提交
1315

1316 1317
void reiserfs_update_sd_size(struct reiserfs_transaction_handle *th,
			     struct inode *inode, loff_t size)
L
Linus Torvalds 已提交
1318
{
1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334
	struct cpu_key key;
	INITIALIZE_PATH(path);
	struct buffer_head *bh;
	int fs_gen;
	struct item_head *ih, tmp_ih;
	int retval;

	BUG_ON(!th->t_trans_id);

	make_cpu_key(&key, inode, SD_OFFSET, TYPE_STAT_DATA, 3);	//key type is unimportant

	for (;;) {
		int pos;
		/* look for the object's stat data */
		retval = search_item(inode->i_sb, &key, &path);
		if (retval == IO_ERROR) {
J
Jeff Mahoney 已提交
1335 1336 1337
			reiserfs_warning(inode->i_sb, "vs-13050",
					 "i/o failure occurred trying to "
					 "update %K stat data",
1338 1339 1340 1341 1342 1343 1344 1345 1346 1347
					 &key);
			return;
		}
		if (retval == ITEM_NOT_FOUND) {
			pos = PATH_LAST_POSITION(&path);
			pathrelse(&path);
			if (inode->i_nlink == 0) {
				/*reiserfs_warning (inode->i_sb, "vs-13050: reiserfs_update_sd: i_nlink == 0, stat data not found"); */
				return;
			}
J
Jeff Mahoney 已提交
1348 1349 1350
			reiserfs_warning(inode->i_sb, "vs-13060",
					 "stat data of object %k (nlink == %d) "
					 "not found (pos %d)",
1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376
					 INODE_PKEY(inode), inode->i_nlink,
					 pos);
			reiserfs_check_path(&path);
			return;
		}

		/* sigh, prepare_for_journal might schedule.  When it schedules the
		 ** FS might change.  We have to detect that, and loop back to the
		 ** search if the stat data item has moved
		 */
		bh = get_last_bh(&path);
		ih = get_ih(&path);
		copy_item_head(&tmp_ih, ih);
		fs_gen = get_generation(inode->i_sb);
		reiserfs_prepare_for_journal(inode->i_sb, bh, 1);
		if (fs_changed(fs_gen, inode->i_sb)
		    && item_moved(&tmp_ih, &path)) {
			reiserfs_restore_prepared_buffer(inode->i_sb, bh);
			continue;	/* Stat_data item has been moved after scheduling. */
		}
		break;
	}
	update_stat_data(&path, inode, size);
	journal_mark_dirty(th, th->t_super, bh);
	pathrelse(&path);
	return;
L
Linus Torvalds 已提交
1377 1378 1379 1380 1381 1382 1383 1384
}

/* reiserfs_read_locked_inode is called to read the inode off disk, and it
** does a make_bad_inode when things go wrong.  But, we need to make sure
** and clear the key in the private portion of the inode, otherwise a
** corresponding iput might try to delete whatever object the inode last
** represented.
*/
1385 1386 1387 1388
static void reiserfs_make_bad_inode(struct inode *inode)
{
	memset(INODE_PKEY(inode), 0, KEY_SIZE);
	make_bad_inode(inode);
L
Linus Torvalds 已提交
1389 1390 1391 1392 1393 1394 1395
}

//
// initially this function was derived from minix or ext2's analog and
// evolved as the prototype did
//

1396
int reiserfs_init_locked_inode(struct inode *inode, void *p)
L
Linus Torvalds 已提交
1397
{
1398 1399 1400 1401
	struct reiserfs_iget_args *args = (struct reiserfs_iget_args *)p;
	inode->i_ino = args->objectid;
	INODE_PKEY(inode)->k_dir_id = cpu_to_le32(args->dirid);
	return 0;
L
Linus Torvalds 已提交
1402 1403 1404 1405
}

/* looks for stat data in the tree, and fills up the fields of in-core
   inode stat data fields */
1406 1407
void reiserfs_read_locked_inode(struct inode *inode,
				struct reiserfs_iget_args *args)
L
Linus Torvalds 已提交
1408
{
1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
	INITIALIZE_PATH(path_to_sd);
	struct cpu_key key;
	unsigned long dirino;
	int retval;

	dirino = args->dirid;

	/* set version 1, version 2 could be used too, because stat data
	   key is the same in both versions */
	key.version = KEY_FORMAT_3_5;
	key.on_disk_key.k_dir_id = dirino;
	key.on_disk_key.k_objectid = inode->i_ino;
	key.on_disk_key.k_offset = 0;
	key.on_disk_key.k_type = 0;

	/* look for the object's stat data */
	retval = search_item(inode->i_sb, &key, &path_to_sd);
	if (retval == IO_ERROR) {
J
Jeff Mahoney 已提交
1427 1428 1429
		reiserfs_warning(inode->i_sb, "vs-13070",
				 "i/o failure occurred trying to find "
				 "stat data of %K", &key);
1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
		reiserfs_make_bad_inode(inode);
		return;
	}
	if (retval != ITEM_FOUND) {
		/* a stale NFS handle can trigger this without it being an error */
		pathrelse(&path_to_sd);
		reiserfs_make_bad_inode(inode);
		inode->i_nlink = 0;
		return;
	}

	init_inode(inode, &path_to_sd);

	/* It is possible that knfsd is trying to access inode of a file
	   that is being removed from the disk by some other thread. As we
	   update sd on unlink all that is required is to check for nlink
	   here. This bug was first found by Sizif when debugging
	   SquidNG/Butterfly, forgotten, and found again after Philippe
	   Gramoulle <philippe.gramoulle@mmania.com> reproduced it. 

	   More logical fix would require changes in fs/inode.c:iput() to
	   remove inode from hash-table _after_ fs cleaned disk stuff up and
	   in iget() to return NULL if I_FREEING inode is found in
	   hash-table. */
	/* Currently there is one place where it's ok to meet inode with
	   nlink==0: processing of open-unlinked and half-truncated files
	   during mount (fs/reiserfs/super.c:finish_unfinished()). */
	if ((inode->i_nlink == 0) &&
	    !REISERFS_SB(inode->i_sb)->s_is_unlinked_ok) {
J
Jeff Mahoney 已提交
1459
		reiserfs_warning(inode->i_sb, "vs-13075",
1460 1461 1462 1463 1464 1465 1466
				 "dead inode read from disk %K. "
				 "This is likely to be race with knfsd. Ignore",
				 &key);
		reiserfs_make_bad_inode(inode);
	}

	reiserfs_check_path(&path_to_sd);	/* init inode should be relsing */
L
Linus Torvalds 已提交
1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481

}

/**
 * reiserfs_find_actor() - "find actor" reiserfs supplies to iget5_locked().
 *
 * @inode:    inode from hash table to check
 * @opaque:   "cookie" passed to iget5_locked(). This is &reiserfs_iget_args.
 *
 * This function is called by iget5_locked() to distinguish reiserfs inodes
 * having the same inode numbers. Such inodes can only exist due to some
 * error condition. One of them should be bad. Inodes with identical
 * inode numbers (objectids) are distinguished by parent directory ids.
 *
 */
1482
int reiserfs_find_actor(struct inode *inode, void *opaque)
L
Linus Torvalds 已提交
1483
{
1484
	struct reiserfs_iget_args *args;
L
Linus Torvalds 已提交
1485

1486 1487 1488 1489
	args = opaque;
	/* args is already in CPU order */
	return (inode->i_ino == args->objectid) &&
	    (le32_to_cpu(INODE_PKEY(inode)->k_dir_id) == args->dirid);
L
Linus Torvalds 已提交
1490 1491
}

1492
struct inode *reiserfs_iget(struct super_block *s, const struct cpu_key *key)
L
Linus Torvalds 已提交
1493
{
1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
	struct inode *inode;
	struct reiserfs_iget_args args;

	args.objectid = key->on_disk_key.k_objectid;
	args.dirid = key->on_disk_key.k_dir_id;
	inode = iget5_locked(s, key->on_disk_key.k_objectid,
			     reiserfs_find_actor, reiserfs_init_locked_inode,
			     (void *)(&args));
	if (!inode)
		return ERR_PTR(-ENOMEM);

	if (inode->i_state & I_NEW) {
		reiserfs_read_locked_inode(inode, &args);
		unlock_new_inode(inode);
	}

	if (comp_short_keys(INODE_PKEY(inode), key) || is_bad_inode(inode)) {
		/* either due to i/o error or a stale NFS handle */
		iput(inode);
		inode = NULL;
	}
	return inode;
L
Linus Torvalds 已提交
1516 1517
}

C
Christoph Hellwig 已提交
1518 1519 1520
static struct dentry *reiserfs_get_dentry(struct super_block *sb,
	u32 objectid, u32 dir_id, u32 generation)

L
Linus Torvalds 已提交
1521
{
1522 1523 1524
	struct cpu_key key;
	struct inode *inode;

C
Christoph Hellwig 已提交
1525 1526
	key.on_disk_key.k_objectid = objectid;
	key.on_disk_key.k_dir_id = dir_id;
1527 1528
	reiserfs_write_lock(sb);
	inode = reiserfs_iget(sb, &key);
C
Christoph Hellwig 已提交
1529 1530
	if (inode && !IS_ERR(inode) && generation != 0 &&
	    generation != inode->i_generation) {
1531 1532 1533 1534
		iput(inode);
		inode = NULL;
	}
	reiserfs_write_unlock(sb);
1535 1536

	return d_obtain_alias(inode);
L
Linus Torvalds 已提交
1537 1538
}

C
Christoph Hellwig 已提交
1539 1540
struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553
{
	/* fhtype happens to reflect the number of u32s encoded.
	 * due to a bug in earlier code, fhtype might indicate there
	 * are more u32s then actually fitted.
	 * so if fhtype seems to be more than len, reduce fhtype.
	 * Valid types are:
	 *   2 - objectid + dir_id - legacy support
	 *   3 - objectid + dir_id + generation
	 *   4 - objectid + dir_id + objectid and dirid of parent - legacy
	 *   5 - objectid + dir_id + generation + objectid and dirid of parent
	 *   6 - as above plus generation of directory
	 * 6 does not fit in NFSv2 handles
	 */
C
Christoph Hellwig 已提交
1554 1555
	if (fh_type > fh_len) {
		if (fh_type != 6 || fh_len != 5)
J
Jeff Mahoney 已提交
1556
			reiserfs_warning(sb, "reiserfs-13077",
C
Christoph Hellwig 已提交
1557 1558 1559
				"nfsd/reiserfs, fhtype=%d, len=%d - odd",
				fh_type, fh_len);
		fh_type = 5;
1560 1561
	}

C
Christoph Hellwig 已提交
1562 1563 1564
	return reiserfs_get_dentry(sb, fid->raw[0], fid->raw[1],
		(fh_type == 3 || fh_type >= 5) ? fid->raw[2] : 0);
}
L
Linus Torvalds 已提交
1565

C
Christoph Hellwig 已提交
1566 1567 1568 1569 1570 1571 1572 1573 1574 1575
struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	if (fh_type < 4)
		return NULL;

	return reiserfs_get_dentry(sb,
		(fh_type >= 5) ? fid->raw[3] : fid->raw[2],
		(fh_type >= 5) ? fid->raw[4] : fid->raw[3],
		(fh_type == 6) ? fid->raw[5] : 0);
L
Linus Torvalds 已提交
1576 1577
}

1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606
int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp,
		       int need_parent)
{
	struct inode *inode = dentry->d_inode;
	int maxlen = *lenp;

	if (maxlen < 3)
		return 255;

	data[0] = inode->i_ino;
	data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
	data[2] = inode->i_generation;
	*lenp = 3;
	/* no room for directory info? return what we've stored so far */
	if (maxlen < 5 || !need_parent)
		return 3;

	spin_lock(&dentry->d_lock);
	inode = dentry->d_parent->d_inode;
	data[3] = inode->i_ino;
	data[4] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
	*lenp = 5;
	if (maxlen >= 6) {
		data[5] = inode->i_generation;
		*lenp = 6;
	}
	spin_unlock(&dentry->d_lock);
	return *lenp;
}
L
Linus Torvalds 已提交
1607 1608 1609 1610 1611 1612 1613 1614

/* looks for stat data, then copies fields to it, marks the buffer
   containing stat data as dirty */
/* reiserfs inodes are never really dirty, since the dirty inode call
** always logs them.  This call allows the VFS inode marking routines
** to properly mark inodes for datasync and such, but only actually
** does something when called for a synchronous update.
*/
1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635
int reiserfs_write_inode(struct inode *inode, int do_sync)
{
	struct reiserfs_transaction_handle th;
	int jbegin_count = 1;

	if (inode->i_sb->s_flags & MS_RDONLY)
		return -EROFS;
	/* memory pressure can sometimes initiate write_inode calls with sync == 1,
	 ** these cases are just when the system needs ram, not when the 
	 ** inode needs to reach disk for safety, and they can safely be
	 ** ignored because the altered inode has already been logged.
	 */
	if (do_sync && !(current->flags & PF_MEMALLOC)) {
		reiserfs_write_lock(inode->i_sb);
		if (!journal_begin(&th, inode->i_sb, jbegin_count)) {
			reiserfs_update_sd(&th, inode);
			journal_end_sync(&th, inode->i_sb, jbegin_count);
		}
		reiserfs_write_unlock(inode->i_sb);
	}
	return 0;
L
Linus Torvalds 已提交
1636 1637 1638 1639
}

/* stat data of new object is inserted already, this inserts the item
   containing "." and ".." entries */
1640 1641
static int reiserfs_new_directory(struct reiserfs_transaction_handle *th,
				  struct inode *inode,
1642
				  struct item_head *ih, struct treepath *path,
1643
				  struct inode *dir)
L
Linus Torvalds 已提交
1644
{
1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680
	struct super_block *sb = th->t_super;
	char empty_dir[EMPTY_DIR_SIZE];
	char *body = empty_dir;
	struct cpu_key key;
	int retval;

	BUG_ON(!th->t_trans_id);

	_make_cpu_key(&key, KEY_FORMAT_3_5, le32_to_cpu(ih->ih_key.k_dir_id),
		      le32_to_cpu(ih->ih_key.k_objectid), DOT_OFFSET,
		      TYPE_DIRENTRY, 3 /*key length */ );

	/* compose item head for new item. Directories consist of items of
	   old type (ITEM_VERSION_1). Do not set key (second arg is 0), it
	   is done by reiserfs_new_inode */
	if (old_format_only(sb)) {
		make_le_item_head(ih, NULL, KEY_FORMAT_3_5, DOT_OFFSET,
				  TYPE_DIRENTRY, EMPTY_DIR_SIZE_V1, 2);

		make_empty_dir_item_v1(body, ih->ih_key.k_dir_id,
				       ih->ih_key.k_objectid,
				       INODE_PKEY(dir)->k_dir_id,
				       INODE_PKEY(dir)->k_objectid);
	} else {
		make_le_item_head(ih, NULL, KEY_FORMAT_3_5, DOT_OFFSET,
				  TYPE_DIRENTRY, EMPTY_DIR_SIZE, 2);

		make_empty_dir_item(body, ih->ih_key.k_dir_id,
				    ih->ih_key.k_objectid,
				    INODE_PKEY(dir)->k_dir_id,
				    INODE_PKEY(dir)->k_objectid);
	}

	/* look for place in the tree for new item */
	retval = search_item(sb, &key, path);
	if (retval == IO_ERROR) {
J
Jeff Mahoney 已提交
1681
		reiserfs_warning(sb, "vs-13080",
1682 1683 1684 1685 1686
				 "i/o failure occurred creating new directory");
		return -EIO;
	}
	if (retval == ITEM_FOUND) {
		pathrelse(path);
J
Jeff Mahoney 已提交
1687
		reiserfs_warning(sb, "vs-13070",
1688 1689 1690 1691
				 "object with this key exists (%k)",
				 &(ih->ih_key));
		return -EEXIST;
	}
L
Linus Torvalds 已提交
1692

1693 1694 1695
	/* insert item, that is empty directory item */
	return reiserfs_insert_item(th, path, &key, ih, inode, body);
}
L
Linus Torvalds 已提交
1696 1697 1698

/* stat data of object has been inserted, this inserts the item
   containing the body of symlink */
1699 1700
static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th, struct inode *inode,	/* Inode of symlink */
				struct item_head *ih,
1701
				struct treepath *path, const char *symname,
1702
				int item_len)
L
Linus Torvalds 已提交
1703
{
1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720
	struct super_block *sb = th->t_super;
	struct cpu_key key;
	int retval;

	BUG_ON(!th->t_trans_id);

	_make_cpu_key(&key, KEY_FORMAT_3_5,
		      le32_to_cpu(ih->ih_key.k_dir_id),
		      le32_to_cpu(ih->ih_key.k_objectid),
		      1, TYPE_DIRECT, 3 /*key length */ );

	make_le_item_head(ih, NULL, KEY_FORMAT_3_5, 1, TYPE_DIRECT, item_len,
			  0 /*free_space */ );

	/* look for place in the tree for new item */
	retval = search_item(sb, &key, path);
	if (retval == IO_ERROR) {
J
Jeff Mahoney 已提交
1721
		reiserfs_warning(sb, "vs-13080",
1722 1723 1724 1725 1726
				 "i/o failure occurred creating new symlink");
		return -EIO;
	}
	if (retval == ITEM_FOUND) {
		pathrelse(path);
J
Jeff Mahoney 已提交
1727
		reiserfs_warning(sb, "vs-13080",
1728 1729 1730 1731
				 "object with this key exists (%k)",
				 &(ih->ih_key));
		return -EEXIST;
	}
L
Linus Torvalds 已提交
1732

1733 1734 1735
	/* insert item, that is body of symlink */
	return reiserfs_insert_item(th, path, &key, ih, inode, symname);
}
L
Linus Torvalds 已提交
1736 1737 1738 1739 1740 1741 1742 1743 1744 1745

/* inserts the stat data into the tree, and then calls
   reiserfs_new_directory (to insert ".", ".." item if new object is
   directory) or reiserfs_new_symlink (to insert symlink body if new
   object is symlink) or nothing (if new object is regular file) 

   NOTE! uid and gid must already be set in the inode.  If we return
   non-zero due to an error, we have to drop the quota previously allocated
   for the fresh inode.  This can only be done outside a transaction, so
   if we return non-zero, we also end the transaction.  */
1746 1747 1748 1749 1750 1751
int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
		       struct inode *dir, int mode, const char *symname,
		       /* 0 for regular, EMTRY_DIR_SIZE for dirs, 
		          strlen (symname) for symlinks) */
		       loff_t i_size, struct dentry *dentry,
		       struct inode *inode)
L
Linus Torvalds 已提交
1752
{
1753
	struct super_block *sb;
A
Al Viro 已提交
1754
	struct reiserfs_iget_args args;
1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
	INITIALIZE_PATH(path_to_key);
	struct cpu_key key;
	struct item_head ih;
	struct stat_data sd;
	int retval;
	int err;

	BUG_ON(!th->t_trans_id);

	if (DQUOT_ALLOC_INODE(inode)) {
		err = -EDQUOT;
		goto out_end_trans;
	}
1768
	if (!dir->i_nlink) {
1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781
		err = -EPERM;
		goto out_bad_inode;
	}

	sb = dir->i_sb;

	/* item head of new item */
	ih.ih_key.k_dir_id = reiserfs_choose_packing(dir);
	ih.ih_key.k_objectid = cpu_to_le32(reiserfs_get_unused_objectid(th));
	if (!ih.ih_key.k_objectid) {
		err = -ENOMEM;
		goto out_bad_inode;
	}
A
Al Viro 已提交
1782
	args.objectid = inode->i_ino = le32_to_cpu(ih.ih_key.k_objectid);
A
Al Viro 已提交
1783 1784 1785 1786 1787 1788
	if (old_format_only(sb))
		make_le_item_head(&ih, NULL, KEY_FORMAT_3_5, SD_OFFSET,
				  TYPE_STAT_DATA, SD_V1_SIZE, MAX_US_INT);
	else
		make_le_item_head(&ih, NULL, KEY_FORMAT_3_6, SD_OFFSET,
				  TYPE_STAT_DATA, SD_SIZE, MAX_US_INT);
A
Al Viro 已提交
1789 1790 1791 1792 1793 1794 1795
	memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE);
	args.dirid = le32_to_cpu(ih.ih_key.k_dir_id);
	if (insert_inode_locked4(inode, args.objectid,
			     reiserfs_find_actor, &args) < 0) {
		err = -EINVAL;
		goto out_bad_inode;
	}
1796 1797 1798 1799 1800 1801 1802 1803
	if (old_format_only(sb))
		/* not a perfect generation count, as object ids can be reused, but 
		 ** this is as good as reiserfs can do right now.
		 ** note that the private part of inode isn't filled in yet, we have
		 ** to use the directory.
		 */
		inode->i_generation = le32_to_cpu(INODE_PKEY(dir)->k_objectid);
	else
L
Linus Torvalds 已提交
1804
#if defined( USE_INODE_GENERATION_COUNTER )
1805 1806
		inode->i_generation =
		    le32_to_cpu(REISERFS_SB(sb)->s_rs->s_inode_generation);
L
Linus Torvalds 已提交
1807
#else
1808
		inode->i_generation = ++event;
L
Linus Torvalds 已提交
1809 1810
#endif

1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835
	/* fill stat data */
	inode->i_nlink = (S_ISDIR(mode) ? 2 : 1);

	/* uid and gid must already be set by the caller for quota init */

	/* symlink cannot be immutable or append only, right? */
	if (S_ISLNK(inode->i_mode))
		inode->i_flags &= ~(S_IMMUTABLE | S_APPEND);

	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
	inode->i_size = i_size;
	inode->i_blocks = 0;
	inode->i_bytes = 0;
	REISERFS_I(inode)->i_first_direct_byte = S_ISLNK(mode) ? 1 :
	    U32_MAX /*NO_BYTES_IN_DIRECT_ITEM */ ;

	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_attrs =
	    REISERFS_I(dir)->i_attrs & REISERFS_INHERIT_MASK;
	sd_attrs_to_i_attrs(REISERFS_I(inode)->i_attrs, inode);
1836
	mutex_init(&(REISERFS_I(inode)->i_mmap));
1837 1838
	reiserfs_init_acl_access(inode);
	reiserfs_init_acl_default(inode);
1839
	reiserfs_init_xattr_rwsem(inode);
1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880

	/* key to search for correct place for new stat data */
	_make_cpu_key(&key, KEY_FORMAT_3_6, le32_to_cpu(ih.ih_key.k_dir_id),
		      le32_to_cpu(ih.ih_key.k_objectid), SD_OFFSET,
		      TYPE_STAT_DATA, 3 /*key length */ );

	/* find proper place for inserting of stat data */
	retval = search_item(sb, &key, &path_to_key);
	if (retval == IO_ERROR) {
		err = -EIO;
		goto out_bad_inode;
	}
	if (retval == ITEM_FOUND) {
		pathrelse(&path_to_key);
		err = -EEXIST;
		goto out_bad_inode;
	}
	if (old_format_only(sb)) {
		if (inode->i_uid & ~0xffff || inode->i_gid & ~0xffff) {
			pathrelse(&path_to_key);
			/* i_uid or i_gid is too big to be stored in stat data v3.5 */
			err = -EINVAL;
			goto out_bad_inode;
		}
		inode2sd_v1(&sd, inode, inode->i_size);
	} else {
		inode2sd(&sd, inode, inode->i_size);
	}
	// store in in-core inode the key of stat data and version all
	// object items will have (directory items will have old offset
	// format, other new objects will consist of new items)
	if (old_format_only(sb) || S_ISDIR(mode) || S_ISLNK(mode))
		set_inode_item_key_version(inode, KEY_FORMAT_3_5);
	else
		set_inode_item_key_version(inode, KEY_FORMAT_3_6);
	if (old_format_only(sb))
		set_inode_sd_version(inode, STAT_DATA_V1);
	else
		set_inode_sd_version(inode, STAT_DATA_V2);

	/* insert the stat data into the tree */
L
Linus Torvalds 已提交
1881
#ifdef DISPLACE_NEW_PACKING_LOCALITIES
1882 1883
	if (REISERFS_I(dir)->new_packing_locality)
		th->displace_new_blocks = 1;
L
Linus Torvalds 已提交
1884
#endif
1885 1886 1887 1888 1889 1890 1891 1892
	retval =
	    reiserfs_insert_item(th, &path_to_key, &key, &ih, inode,
				 (char *)(&sd));
	if (retval) {
		err = retval;
		reiserfs_check_path(&path_to_key);
		goto out_bad_inode;
	}
L
Linus Torvalds 已提交
1893
#ifdef DISPLACE_NEW_PACKING_LOCALITIES
1894 1895
	if (!th->displace_new_blocks)
		REISERFS_I(dir)->new_packing_locality = 0;
L
Linus Torvalds 已提交
1896
#endif
1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927
	if (S_ISDIR(mode)) {
		/* insert item with "." and ".." */
		retval =
		    reiserfs_new_directory(th, inode, &ih, &path_to_key, dir);
	}

	if (S_ISLNK(mode)) {
		/* insert body of symlink */
		if (!old_format_only(sb))
			i_size = ROUND_UP(i_size);
		retval =
		    reiserfs_new_symlink(th, inode, &ih, &path_to_key, symname,
					 i_size);
	}
	if (retval) {
		err = retval;
		reiserfs_check_path(&path_to_key);
		journal_end(th, th->t_super, th->t_blocks_allocated);
		goto out_inserted_sd;
	}

	/* XXX CHECK THIS */
	if (reiserfs_posixacl(inode->i_sb)) {
		retval = reiserfs_inherit_default_acl(dir, dentry, inode);
		if (retval) {
			err = retval;
			reiserfs_check_path(&path_to_key);
			journal_end(th, th->t_super, th->t_blocks_allocated);
			goto out_inserted_sd;
		}
	} else if (inode->i_sb->s_flags & MS_POSIXACL) {
J
Jeff Mahoney 已提交
1928 1929
		reiserfs_warning(inode->i_sb, "jdm-13090",
				 "ACLs aren't enabled in the fs, "
1930 1931 1932 1933 1934 1935 1936 1937 1938
				 "but vfs thinks they are!");
	} else if (is_reiserfs_priv_object(dir)) {
		reiserfs_mark_inode_private(inode);
	}

	reiserfs_update_sd(th, inode);
	reiserfs_check_path(&path_to_key);

	return 0;
L
Linus Torvalds 已提交
1939 1940 1941 1942 1943

/* it looks like you can easily compress these two goto targets into
 * one.  Keeping it like this doesn't actually hurt anything, and they
 * are place holders for what the quota code actually needs.
 */
1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960
      out_bad_inode:
	/* Invalidate the object, nothing was inserted yet */
	INODE_PKEY(inode)->k_objectid = 0;

	/* Quota change must be inside a transaction for journaling */
	DQUOT_FREE_INODE(inode);

      out_end_trans:
	journal_end(th, th->t_super, th->t_blocks_allocated);
	/* Drop can be outside and it needs more credits so it's better to have it outside */
	DQUOT_DROP(inode);
	inode->i_flags |= S_NOQUOTA;
	make_bad_inode(inode);

      out_inserted_sd:
	inode->i_nlink = 0;
	th->t_trans_id = 0;	/* so the caller can't use this handle later */
A
Al Viro 已提交
1961
	unlock_new_inode(inode); /* OK to do even if we hadn't locked it */
1962 1963 1964 1965 1966

	/* If we were inheriting an ACL, we need to release the lock so that
	 * iput doesn't deadlock in reiserfs_delete_xattrs. The locking
	 * code really needs to be reworked, but this will take care of it
	 * for now. -jeffm */
1967
#ifdef CONFIG_REISERFS_FS_POSIX_ACL
1968
	if (REISERFS_I(dir)->i_acl_default && !IS_ERR(REISERFS_I(dir)->i_acl_default)) {
1969 1970 1971 1972
		reiserfs_write_unlock_xattrs(dir->i_sb);
		iput(inode);
		reiserfs_write_lock_xattrs(dir->i_sb);
	} else
1973
#endif
1974
		iput(inode);
1975
	return err;
L
Linus Torvalds 已提交
1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990
}

/*
** finds the tail page in the page cache,
** reads the last block in.
**
** On success, page_result is set to a locked, pinned page, and bh_result
** is set to an up to date buffer for the last block in the file.  returns 0.
**
** tail conversion is not done, so bh_result might not be valid for writing
** check buffer_mapped(bh_result) and bh_result->b_blocknr != 0 before
** trying to write the block.
**
** on failure, nonzero is returned, page_result and bh_result are untouched.
*/
1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045
static int grab_tail_page(struct inode *p_s_inode,
			  struct page **page_result,
			  struct buffer_head **bh_result)
{

	/* we want the page with the last byte in the file,
	 ** not the page that will hold the next byte for appending
	 */
	unsigned long index = (p_s_inode->i_size - 1) >> PAGE_CACHE_SHIFT;
	unsigned long pos = 0;
	unsigned long start = 0;
	unsigned long blocksize = p_s_inode->i_sb->s_blocksize;
	unsigned long offset = (p_s_inode->i_size) & (PAGE_CACHE_SIZE - 1);
	struct buffer_head *bh;
	struct buffer_head *head;
	struct page *page;
	int error;

	/* we know that we are only called with inode->i_size > 0.
	 ** we also know that a file tail can never be as big as a block
	 ** If i_size % blocksize == 0, our file is currently block aligned
	 ** and it won't need converting or zeroing after a truncate.
	 */
	if ((offset & (blocksize - 1)) == 0) {
		return -ENOENT;
	}
	page = grab_cache_page(p_s_inode->i_mapping, index);
	error = -ENOMEM;
	if (!page) {
		goto out;
	}
	/* start within the page of the last block in the file */
	start = (offset / blocksize) * blocksize;

	error = block_prepare_write(page, start, offset,
				    reiserfs_get_block_create_0);
	if (error)
		goto unlock;

	head = page_buffers(page);
	bh = head;
	do {
		if (pos >= start) {
			break;
		}
		bh = bh->b_this_page;
		pos += blocksize;
	} while (bh != head);

	if (!buffer_uptodate(bh)) {
		/* note, this should never happen, prepare_write should
		 ** be taking care of this for us.  If the buffer isn't up to date,
		 ** I've screwed up the code to find the buffer, or the code to
		 ** call prepare_write
		 */
J
Jeff Mahoney 已提交
2046 2047
		reiserfs_warning(p_s_inode->i_sb, "clm-6000",
				 "error reading block %lu on dev %s",
2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062
				 bh->b_blocknr,
				 reiserfs_bdevname(p_s_inode->i_sb));
		error = -EIO;
		goto unlock;
	}
	*bh_result = bh;
	*page_result = page;

      out:
	return error;

      unlock:
	unlock_page(page);
	page_cache_release(page);
	return error;
L
Linus Torvalds 已提交
2063 2064 2065 2066 2067 2068 2069 2070
}

/*
** vfs version of truncate file.  Must NOT be called with
** a transaction already started.
**
** some code taken from block_truncate_page
*/
2071 2072 2073 2074 2075 2076 2077 2078 2079 2080
int reiserfs_truncate_file(struct inode *p_s_inode, int update_timestamps)
{
	struct reiserfs_transaction_handle th;
	/* we want the offset for the first byte after the end of the file */
	unsigned long offset = p_s_inode->i_size & (PAGE_CACHE_SIZE - 1);
	unsigned blocksize = p_s_inode->i_sb->s_blocksize;
	unsigned length;
	struct page *page = NULL;
	int error;
	struct buffer_head *bh = NULL;
2081
	int err2;
2082 2083 2084 2085 2086 2087 2088 2089 2090

	reiserfs_write_lock(p_s_inode->i_sb);

	if (p_s_inode->i_size > 0) {
		if ((error = grab_tail_page(p_s_inode, &page, &bh))) {
			// -ENOENT means we truncated past the end of the file, 
			// and get_block_create_0 could not find a block to read in,
			// which is ok.
			if (error != -ENOENT)
J
Jeff Mahoney 已提交
2091 2092
				reiserfs_warning(p_s_inode->i_sb, "clm-6001",
						 "grab_tail_page failed %d",
2093 2094 2095 2096 2097
						 error);
			page = NULL;
			bh = NULL;
		}
	}
L
Linus Torvalds 已提交
2098

2099 2100 2101 2102 2103 2104
	/* so, if page != NULL, we have a buffer head for the offset at 
	 ** the end of the file. if the bh is mapped, and bh->b_blocknr != 0, 
	 ** then we have an unformatted node.  Otherwise, we have a direct item, 
	 ** and no zeroing is required on disk.  We zero after the truncate, 
	 ** because the truncate might pack the item anyway 
	 ** (it will unmap bh if it packs).
L
Linus Torvalds 已提交
2105
	 */
2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118
	/* it is enough to reserve space in transaction for 2 balancings:
	   one for "save" link adding and another for the first
	   cut_from_item. 1 is for update_sd */
	error = journal_begin(&th, p_s_inode->i_sb,
			      JOURNAL_PER_BALANCE_CNT * 2 + 1);
	if (error)
		goto out;
	reiserfs_update_inode_transaction(p_s_inode);
	if (update_timestamps)
		/* we are doing real truncate: if the system crashes before the last
		   transaction of truncating gets committed - on reboot the file
		   either appears truncated properly or not truncated at all */
		add_save_link(&th, p_s_inode, 1);
2119
	err2 = reiserfs_do_truncate(&th, p_s_inode, page, update_timestamps);
2120 2121 2122 2123 2124
	error =
	    journal_end(&th, p_s_inode->i_sb, JOURNAL_PER_BALANCE_CNT * 2 + 1);
	if (error)
		goto out;

2125 2126 2127 2128 2129 2130
	/* check reiserfs_do_truncate after ending the transaction */
	if (err2) {
		error = err2;
  		goto out;
	}
	
2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141
	if (update_timestamps) {
		error = remove_save_link(p_s_inode, 1 /* truncate */ );
		if (error)
			goto out;
	}

	if (page) {
		length = offset & (blocksize - 1);
		/* if we are not on a block boundary */
		if (length) {
			length = blocksize - length;
2142
			zero_user(page, offset, length);
2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175
			if (buffer_mapped(bh) && bh->b_blocknr != 0) {
				mark_buffer_dirty(bh);
			}
		}
		unlock_page(page);
		page_cache_release(page);
	}

	reiserfs_write_unlock(p_s_inode->i_sb);
	return 0;
      out:
	if (page) {
		unlock_page(page);
		page_cache_release(page);
	}
	reiserfs_write_unlock(p_s_inode->i_sb);
	return error;
}

static int map_block_for_writepage(struct inode *inode,
				   struct buffer_head *bh_result,
				   unsigned long block)
{
	struct reiserfs_transaction_handle th;
	int fs_gen;
	struct item_head tmp_ih;
	struct item_head *ih;
	struct buffer_head *bh;
	__le32 *item;
	struct cpu_key key;
	INITIALIZE_PATH(path);
	int pos_in_item;
	int jbegin_count = JOURNAL_PER_BALANCE_CNT;
2176
	loff_t byte_offset = ((loff_t)block << inode->i_sb->s_blocksize_bits)+1;
2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209
	int retval;
	int use_get_block = 0;
	int bytes_copied = 0;
	int copy_size;
	int trans_running = 0;

	/* catch places below that try to log something without starting a trans */
	th.t_trans_id = 0;

	if (!buffer_uptodate(bh_result)) {
		return -EIO;
	}

	kmap(bh_result->b_page);
      start_over:
	reiserfs_write_lock(inode->i_sb);
	make_cpu_key(&key, inode, byte_offset, TYPE_ANY, 3);

      research:
	retval = search_for_position_by_key(inode->i_sb, &key, &path);
	if (retval != POSITION_FOUND) {
		use_get_block = 1;
		goto out;
	}

	bh = get_last_bh(&path);
	ih = get_ih(&path);
	item = get_item(&path);
	pos_in_item = path.pos_in_item;

	/* we've found an unformatted node */
	if (indirect_item_found(retval, ih)) {
		if (bytes_copied > 0) {
J
Jeff Mahoney 已提交
2210 2211
			reiserfs_warning(inode->i_sb, "clm-6002",
					 "bytes_copied %d", bytes_copied);
2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267
		}
		if (!get_block_num(item, pos_in_item)) {
			/* crap, we are writing to a hole */
			use_get_block = 1;
			goto out;
		}
		set_block_dev_mapped(bh_result,
				     get_block_num(item, pos_in_item), inode);
	} else if (is_direct_le_ih(ih)) {
		char *p;
		p = page_address(bh_result->b_page);
		p += (byte_offset - 1) & (PAGE_CACHE_SIZE - 1);
		copy_size = ih_item_len(ih) - pos_in_item;

		fs_gen = get_generation(inode->i_sb);
		copy_item_head(&tmp_ih, ih);

		if (!trans_running) {
			/* vs-3050 is gone, no need to drop the path */
			retval = journal_begin(&th, inode->i_sb, jbegin_count);
			if (retval)
				goto out;
			reiserfs_update_inode_transaction(inode);
			trans_running = 1;
			if (fs_changed(fs_gen, inode->i_sb)
			    && item_moved(&tmp_ih, &path)) {
				reiserfs_restore_prepared_buffer(inode->i_sb,
								 bh);
				goto research;
			}
		}

		reiserfs_prepare_for_journal(inode->i_sb, bh, 1);

		if (fs_changed(fs_gen, inode->i_sb)
		    && item_moved(&tmp_ih, &path)) {
			reiserfs_restore_prepared_buffer(inode->i_sb, bh);
			goto research;
		}

		memcpy(B_I_PITEM(bh, ih) + pos_in_item, p + bytes_copied,
		       copy_size);

		journal_mark_dirty(&th, inode->i_sb, bh);
		bytes_copied += copy_size;
		set_block_dev_mapped(bh_result, 0, inode);

		/* are there still bytes left? */
		if (bytes_copied < bh_result->b_size &&
		    (byte_offset + bytes_copied) < inode->i_size) {
			set_cpu_key_k_offset(&key,
					     cpu_key_k_offset(&key) +
					     copy_size);
			goto research;
		}
	} else {
J
Jeff Mahoney 已提交
2268 2269
		reiserfs_warning(inode->i_sb, "clm-6003",
				 "bad item inode %lu", inode->i_ino);
2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287
		retval = -EIO;
		goto out;
	}
	retval = 0;

      out:
	pathrelse(&path);
	if (trans_running) {
		int err = journal_end(&th, inode->i_sb, jbegin_count);
		if (err)
			retval = err;
		trans_running = 0;
	}
	reiserfs_write_unlock(inode->i_sb);

	/* this is where we fill in holes in the file. */
	if (use_get_block) {
		retval = reiserfs_get_block(inode, block, bh_result,
2288
					    GET_BLOCK_CREATE | GET_BLOCK_NO_IMUX
2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309
					    | GET_BLOCK_NO_DANGLE);
		if (!retval) {
			if (!buffer_mapped(bh_result)
			    || bh_result->b_blocknr == 0) {
				/* get_block failed to find a mapped unformatted node. */
				use_get_block = 0;
				goto start_over;
			}
		}
	}
	kunmap(bh_result->b_page);

	if (!retval && buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
		/* we've copied data from the page into the direct item, so the
		 * buffer in the page is now clean, mark it to reflect that.
		 */
		lock_buffer(bh_result);
		clear_buffer_dirty(bh_result);
		unlock_buffer(bh_result);
	}
	return retval;
L
Linus Torvalds 已提交
2310 2311 2312 2313 2314 2315 2316
}

/* 
 * mason@suse.com: updated in 2.5.54 to follow the same general io 
 * start/recovery path as __block_write_full_page, along with special
 * code to handle reiserfs tails.
 */
2317 2318 2319 2320 2321 2322 2323
static int reiserfs_write_full_page(struct page *page,
				    struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned long end_index = inode->i_size >> PAGE_CACHE_SHIFT;
	int error = 0;
	unsigned long block;
2324
	sector_t last_block;
2325 2326 2327 2328 2329 2330 2331 2332 2333
	struct buffer_head *head, *bh;
	int partial = 0;
	int nr = 0;
	int checked = PageChecked(page);
	struct reiserfs_transaction_handle th;
	struct super_block *s = inode->i_sb;
	int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize;
	th.t_trans_id = 0;

2334 2335 2336 2337 2338 2339 2340
	/* no logging allowed when nonblocking or from PF_MEMALLOC */
	if (checked && (current->flags & PF_MEMALLOC)) {
		redirty_page_for_writepage(wbc, page);
		unlock_page(page);
		return 0;
	}

2341 2342 2343 2344 2345 2346 2347 2348 2349 2350
	/* The page dirty bit is cleared before writepage is called, which
	 * means we have to tell create_empty_buffers to make dirty buffers
	 * The page really should be up to date at this point, so tossing
	 * in the BH_Uptodate is just a sanity check.
	 */
	if (!page_has_buffers(page)) {
		create_empty_buffers(page, s->s_blocksize,
				     (1 << BH_Dirty) | (1 << BH_Uptodate));
	}
	head = page_buffers(page);
L
Linus Torvalds 已提交
2351

2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363
	/* last page in the file, zero out any contents past the
	 ** last byte in the file
	 */
	if (page->index >= end_index) {
		unsigned last_offset;

		last_offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
		/* no file contents in this page */
		if (page->index >= end_index + 1 || !last_offset) {
			unlock_page(page);
			return 0;
		}
2364
		zero_user_segment(page, last_offset, PAGE_CACHE_SIZE);
L
Linus Torvalds 已提交
2365
	}
2366 2367
	bh = head;
	block = page->index << (PAGE_CACHE_SHIFT - s->s_blocksize_bits);
2368
	last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;
2369 2370
	/* first map all the buffers, logging any direct items we find */
	do {
2371 2372 2373 2374 2375 2376 2377 2378 2379 2380
		if (block > last_block) {
			/*
			 * This can happen when the block size is less than
			 * the page size.  The corresponding bytes in the page
			 * were zero filled above
			 */
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
		} else if ((checked || buffer_dirty(bh)) &&
		           (!buffer_mapped(bh) || (buffer_mapped(bh)
2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399
						       && bh->b_blocknr ==
						       0))) {
			/* not mapped yet, or it points to a direct item, search
			 * the btree for the mapping info, and log any direct
			 * items found
			 */
			if ((error = map_block_for_writepage(inode, bh, block))) {
				goto fail;
			}
		}
		bh = bh->b_this_page;
		block++;
	} while (bh != head);

	/*
	 * we start the transaction after map_block_for_writepage,
	 * because it can create holes in the file (an unbounded operation).
	 * starting it here, we can make a reliable estimate for how many
	 * blocks we're going to log
L
Linus Torvalds 已提交
2400
	 */
2401 2402 2403 2404 2405 2406 2407 2408 2409
	if (checked) {
		ClearPageChecked(page);
		reiserfs_write_lock(s);
		error = journal_begin(&th, s, bh_per_page + 1);
		if (error) {
			reiserfs_write_unlock(s);
			goto fail;
		}
		reiserfs_update_inode_transaction(inode);
L
Linus Torvalds 已提交
2410
	}
2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429
	/* now go through and lock any dirty buffers on the page */
	do {
		get_bh(bh);
		if (!buffer_mapped(bh))
			continue;
		if (buffer_mapped(bh) && bh->b_blocknr == 0)
			continue;

		if (checked) {
			reiserfs_prepare_for_journal(s, bh, 1);
			journal_mark_dirty(&th, s, bh);
			continue;
		}
		/* from this point on, we know the buffer is mapped to a
		 * real block and not a direct item
		 */
		if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
			lock_buffer(bh);
		} else {
N
Nick Piggin 已提交
2430
			if (!trylock_buffer(bh)) {
2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446
				redirty_page_for_writepage(wbc, page);
				continue;
			}
		}
		if (test_clear_buffer_dirty(bh)) {
			mark_buffer_async_write(bh);
		} else {
			unlock_buffer(bh);
		}
	} while ((bh = bh->b_this_page) != head);

	if (checked) {
		error = journal_end(&th, s, bh_per_page + 1);
		reiserfs_write_unlock(s);
		if (error)
			goto fail;
L
Linus Torvalds 已提交
2447
	}
2448 2449 2450
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);
	unlock_page(page);
L
Linus Torvalds 已提交
2451

2452 2453 2454 2455
	/*
	 * since any buffer might be the only dirty buffer on the page, 
	 * the first submit_bh can bring the page out of writeback.
	 * be careful with the buffers.
L
Linus Torvalds 已提交
2456 2457
	 */
	do {
2458 2459 2460 2461 2462 2463 2464 2465
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			submit_bh(WRITE, bh);
			nr++;
		}
		put_bh(bh);
		bh = next;
	} while (bh != head);
L
Linus Torvalds 已提交
2466

2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488
	error = 0;
      done:
	if (nr == 0) {
		/*
		 * if this page only had a direct item, it is very possible for
		 * no io to be required without there being an error.  Or, 
		 * someone else could have locked them and sent them down the 
		 * pipe without locking the page
		 */
		bh = head;
		do {
			if (!buffer_uptodate(bh)) {
				partial = 1;
				break;
			}
			bh = bh->b_this_page;
		} while (bh != head);
		if (!partial)
			SetPageUptodate(page);
		end_page_writeback(page);
	}
	return error;
L
Linus Torvalds 已提交
2489

2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525
      fail:
	/* catches various errors, we need to make sure any valid dirty blocks
	 * get to the media.  The page is currently locked and not marked for 
	 * writeback
	 */
	ClearPageUptodate(page);
	bh = head;
	do {
		get_bh(bh);
		if (buffer_mapped(bh) && buffer_dirty(bh) && bh->b_blocknr) {
			lock_buffer(bh);
			mark_buffer_async_write(bh);
		} else {
			/*
			 * clear any dirty bits that might have come from getting
			 * attached to a dirty page
			 */
			clear_buffer_dirty(bh);
		}
		bh = bh->b_this_page;
	} while (bh != head);
	SetPageError(page);
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);
	unlock_page(page);
	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			clear_buffer_dirty(bh);
			submit_bh(WRITE, bh);
			nr++;
		}
		put_bh(bh);
		bh = next;
	} while (bh != head);
	goto done;
L
Linus Torvalds 已提交
2526 2527
}

2528 2529 2530 2531
static int reiserfs_readpage(struct file *f, struct page *page)
{
	return block_read_full_page(page, reiserfs_get_block);
}
L
Linus Torvalds 已提交
2532

2533
static int reiserfs_writepage(struct page *page, struct writeback_control *wbc)
L
Linus Torvalds 已提交
2534
{
2535 2536 2537
	struct inode *inode = page->mapping->host;
	reiserfs_wait_on_write_block(inode->i_sb);
	return reiserfs_write_full_page(page, wbc);
L
Linus Torvalds 已提交
2538 2539
}

V
Vladimir Saveliev 已提交
2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550
static int reiserfs_write_begin(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata)
{
	struct inode *inode;
	struct page *page;
	pgoff_t index;
	int ret;
	int old_ref = 0;

2551 2552 2553 2554 2555 2556 2557 2558
 	inode = mapping->host;
	*fsdata = 0;
 	if (flags & AOP_FLAG_CONT_EXPAND &&
 	    (pos & (inode->i_sb->s_blocksize - 1)) == 0) {
 		pos ++;
		*fsdata = (void *)(unsigned long)flags;
	}

V
Vladimir Saveliev 已提交
2559
	index = pos >> PAGE_CACHE_SHIFT;
2560
	page = grab_cache_page_write_begin(mapping, index, flags);
V
Vladimir Saveliev 已提交
2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611
	if (!page)
		return -ENOMEM;
	*pagep = page;

	reiserfs_wait_on_write_block(inode->i_sb);
	fix_tail_page_for_writing(page);
	if (reiserfs_transaction_running(inode->i_sb)) {
		struct reiserfs_transaction_handle *th;
		th = (struct reiserfs_transaction_handle *)current->
		    journal_info;
		BUG_ON(!th->t_refcount);
		BUG_ON(!th->t_trans_id);
		old_ref = th->t_refcount;
		th->t_refcount++;
	}
	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				reiserfs_get_block);
	if (ret && reiserfs_transaction_running(inode->i_sb)) {
		struct reiserfs_transaction_handle *th = current->journal_info;
		/* this gets a little ugly.  If reiserfs_get_block returned an
		 * error and left a transacstion running, we've got to close it,
		 * and we've got to free handle if it was a persistent transaction.
		 *
		 * But, if we had nested into an existing transaction, we need
		 * to just drop the ref count on the handle.
		 *
		 * If old_ref == 0, the transaction is from reiserfs_get_block,
		 * and it was a persistent trans.  Otherwise, it was nested above.
		 */
		if (th->t_refcount > old_ref) {
			if (old_ref)
				th->t_refcount--;
			else {
				int err;
				reiserfs_write_lock(inode->i_sb);
				err = reiserfs_end_persistent_transaction(th);
				reiserfs_write_unlock(inode->i_sb);
				if (err)
					ret = err;
			}
		}
	}
	if (ret) {
		unlock_page(page);
		page_cache_release(page);
	}
	return ret;
}

int reiserfs_prepare_write(struct file *f, struct page *page,
			   unsigned from, unsigned to)
2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626
{
	struct inode *inode = page->mapping->host;
	int ret;
	int old_ref = 0;

	reiserfs_wait_on_write_block(inode->i_sb);
	fix_tail_page_for_writing(page);
	if (reiserfs_transaction_running(inode->i_sb)) {
		struct reiserfs_transaction_handle *th;
		th = (struct reiserfs_transaction_handle *)current->
		    journal_info;
		BUG_ON(!th->t_refcount);
		BUG_ON(!th->t_trans_id);
		old_ref = th->t_refcount;
		th->t_refcount++;
L
Linus Torvalds 已提交
2627 2628
	}

2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655
	ret = block_prepare_write(page, from, to, reiserfs_get_block);
	if (ret && reiserfs_transaction_running(inode->i_sb)) {
		struct reiserfs_transaction_handle *th = current->journal_info;
		/* this gets a little ugly.  If reiserfs_get_block returned an
		 * error and left a transacstion running, we've got to close it,
		 * and we've got to free handle if it was a persistent transaction.
		 *
		 * But, if we had nested into an existing transaction, we need
		 * to just drop the ref count on the handle.
		 *
		 * If old_ref == 0, the transaction is from reiserfs_get_block,
		 * and it was a persistent trans.  Otherwise, it was nested above.
		 */
		if (th->t_refcount > old_ref) {
			if (old_ref)
				th->t_refcount--;
			else {
				int err;
				reiserfs_write_lock(inode->i_sb);
				err = reiserfs_end_persistent_transaction(th);
				reiserfs_write_unlock(inode->i_sb);
				if (err)
					ret = err;
			}
		}
	}
	return ret;
L
Linus Torvalds 已提交
2656

2657
}
L
Linus Torvalds 已提交
2658

2659 2660 2661
static sector_t reiserfs_aop_bmap(struct address_space *as, sector_t block)
{
	return generic_block_bmap(as, block, reiserfs_bmap);
L
Linus Torvalds 已提交
2662 2663
}

V
Vladimir Saveliev 已提交
2664 2665 2666 2667 2668 2669 2670 2671 2672 2673
static int reiserfs_write_end(struct file *file, struct address_space *mapping,
			      loff_t pos, unsigned len, unsigned copied,
			      struct page *page, void *fsdata)
{
	struct inode *inode = page->mapping->host;
	int ret = 0;
	int update_sd = 0;
	struct reiserfs_transaction_handle *th;
	unsigned start;

2674 2675
	if ((unsigned long)fsdata & AOP_FLAG_CONT_EXPAND)
		pos ++;
V
Vladimir Saveliev 已提交
2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759

	reiserfs_wait_on_write_block(inode->i_sb);
	if (reiserfs_transaction_running(inode->i_sb))
		th = current->journal_info;
	else
		th = NULL;

	start = pos & (PAGE_CACHE_SIZE - 1);
	if (unlikely(copied < len)) {
		if (!PageUptodate(page))
			copied = 0;

		page_zero_new_buffers(page, start + copied, start + len);
	}
	flush_dcache_page(page);

	reiserfs_commit_page(inode, page, start, start + copied);

	/* generic_commit_write does this for us, but does not update the
	 ** transaction tracking stuff when the size changes.  So, we have
	 ** to do the i_size updates here.
	 */
	pos += copied;
	if (pos > inode->i_size) {
		struct reiserfs_transaction_handle myth;
		reiserfs_write_lock(inode->i_sb);
		/* If the file have grown beyond the border where it
		   can have a tail, unmark it as needing a tail
		   packing */
		if ((have_large_tails(inode->i_sb)
		     && inode->i_size > i_block_size(inode) * 4)
		    || (have_small_tails(inode->i_sb)
			&& inode->i_size > i_block_size(inode)))
			REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;

		ret = journal_begin(&myth, inode->i_sb, 1);
		if (ret) {
			reiserfs_write_unlock(inode->i_sb);
			goto journal_error;
		}
		reiserfs_update_inode_transaction(inode);
		inode->i_size = pos;
		/*
		 * this will just nest into our transaction.  It's important
		 * to use mark_inode_dirty so the inode gets pushed around on the
		 * dirty lists, and so that O_SYNC works as expected
		 */
		mark_inode_dirty(inode);
		reiserfs_update_sd(&myth, inode);
		update_sd = 1;
		ret = journal_end(&myth, inode->i_sb, 1);
		reiserfs_write_unlock(inode->i_sb);
		if (ret)
			goto journal_error;
	}
	if (th) {
		reiserfs_write_lock(inode->i_sb);
		if (!update_sd)
			mark_inode_dirty(inode);
		ret = reiserfs_end_persistent_transaction(th);
		reiserfs_write_unlock(inode->i_sb);
		if (ret)
			goto out;
	}

      out:
	unlock_page(page);
	page_cache_release(page);
	return ret == 0 ? copied : ret;

      journal_error:
	if (th) {
		reiserfs_write_lock(inode->i_sb);
		if (!update_sd)
			reiserfs_update_sd(th, inode);
		ret = reiserfs_end_persistent_transaction(th);
		reiserfs_write_unlock(inode->i_sb);
	}

	goto out;
}

int reiserfs_commit_write(struct file *f, struct page *page,
			  unsigned from, unsigned to)
2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771
{
	struct inode *inode = page->mapping->host;
	loff_t pos = ((loff_t) page->index << PAGE_CACHE_SHIFT) + to;
	int ret = 0;
	int update_sd = 0;
	struct reiserfs_transaction_handle *th = NULL;

	reiserfs_wait_on_write_block(inode->i_sb);
	if (reiserfs_transaction_running(inode->i_sb)) {
		th = current->journal_info;
	}
	reiserfs_commit_page(inode, page, from, to);
L
Linus Torvalds 已提交
2772

2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795
	/* generic_commit_write does this for us, but does not update the
	 ** transaction tracking stuff when the size changes.  So, we have
	 ** to do the i_size updates here.
	 */
	if (pos > inode->i_size) {
		struct reiserfs_transaction_handle myth;
		reiserfs_write_lock(inode->i_sb);
		/* If the file have grown beyond the border where it
		   can have a tail, unmark it as needing a tail
		   packing */
		if ((have_large_tails(inode->i_sb)
		     && inode->i_size > i_block_size(inode) * 4)
		    || (have_small_tails(inode->i_sb)
			&& inode->i_size > i_block_size(inode)))
			REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;

		ret = journal_begin(&myth, inode->i_sb, 1);
		if (ret) {
			reiserfs_write_unlock(inode->i_sb);
			goto journal_error;
		}
		reiserfs_update_inode_transaction(inode);
		inode->i_size = pos;
2796 2797 2798 2799 2800 2801
		/*
		 * this will just nest into our transaction.  It's important
		 * to use mark_inode_dirty so the inode gets pushed around on the
		 * dirty lists, and so that O_SYNC works as expected
		 */
		mark_inode_dirty(inode);
2802 2803 2804 2805 2806 2807 2808 2809 2810 2811
		reiserfs_update_sd(&myth, inode);
		update_sd = 1;
		ret = journal_end(&myth, inode->i_sb, 1);
		reiserfs_write_unlock(inode->i_sb);
		if (ret)
			goto journal_error;
	}
	if (th) {
		reiserfs_write_lock(inode->i_sb);
		if (!update_sd)
2812
			mark_inode_dirty(inode);
2813 2814 2815 2816 2817 2818 2819 2820
		ret = reiserfs_end_persistent_transaction(th);
		reiserfs_write_unlock(inode->i_sb);
		if (ret)
			goto out;
	}

      out:
	return ret;
L
Linus Torvalds 已提交
2821

2822 2823 2824 2825 2826 2827 2828 2829 2830 2831
      journal_error:
	if (th) {
		reiserfs_write_lock(inode->i_sb);
		if (!update_sd)
			reiserfs_update_sd(th, inode);
		ret = reiserfs_end_persistent_transaction(th);
		reiserfs_write_unlock(inode->i_sb);
	}

	return ret;
L
Linus Torvalds 已提交
2832 2833
}

2834
void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode)
L
Linus Torvalds 已提交
2835
{
2836 2837 2838
	if (reiserfs_attrs(inode->i_sb)) {
		if (sd_attrs & REISERFS_SYNC_FL)
			inode->i_flags |= S_SYNC;
L
Linus Torvalds 已提交
2839
		else
2840 2841 2842
			inode->i_flags &= ~S_SYNC;
		if (sd_attrs & REISERFS_IMMUTABLE_FL)
			inode->i_flags |= S_IMMUTABLE;
L
Linus Torvalds 已提交
2843
		else
2844 2845 2846
			inode->i_flags &= ~S_IMMUTABLE;
		if (sd_attrs & REISERFS_APPEND_FL)
			inode->i_flags |= S_APPEND;
L
Linus Torvalds 已提交
2847
		else
2848 2849 2850
			inode->i_flags &= ~S_APPEND;
		if (sd_attrs & REISERFS_NOATIME_FL)
			inode->i_flags |= S_NOATIME;
L
Linus Torvalds 已提交
2851
		else
2852 2853
			inode->i_flags &= ~S_NOATIME;
		if (sd_attrs & REISERFS_NOTAIL_FL)
L
Linus Torvalds 已提交
2854 2855 2856 2857 2858 2859
			REISERFS_I(inode)->i_flags |= i_nopack_mask;
		else
			REISERFS_I(inode)->i_flags &= ~i_nopack_mask;
	}
}

2860
void i_attrs_to_sd_attrs(struct inode *inode, __u16 * sd_attrs)
L
Linus Torvalds 已提交
2861
{
2862 2863
	if (reiserfs_attrs(inode->i_sb)) {
		if (inode->i_flags & S_IMMUTABLE)
L
Linus Torvalds 已提交
2864 2865 2866
			*sd_attrs |= REISERFS_IMMUTABLE_FL;
		else
			*sd_attrs &= ~REISERFS_IMMUTABLE_FL;
2867
		if (inode->i_flags & S_SYNC)
L
Linus Torvalds 已提交
2868 2869 2870
			*sd_attrs |= REISERFS_SYNC_FL;
		else
			*sd_attrs &= ~REISERFS_SYNC_FL;
2871
		if (inode->i_flags & S_NOATIME)
L
Linus Torvalds 已提交
2872 2873 2874
			*sd_attrs |= REISERFS_NOATIME_FL;
		else
			*sd_attrs &= ~REISERFS_NOATIME_FL;
2875
		if (REISERFS_I(inode)->i_flags & i_nopack_mask)
L
Linus Torvalds 已提交
2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
			*sd_attrs |= REISERFS_NOTAIL_FL;
		else
			*sd_attrs &= ~REISERFS_NOTAIL_FL;
	}
}

/* decide if this buffer needs to stay around for data logging or ordered
** write purposes
*/
static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
{
2887 2888 2889
	int ret = 1;
	struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);

2890
	lock_buffer(bh);
2891 2892 2893 2894 2895 2896
	spin_lock(&j->j_dirty_buffers_lock);
	if (!buffer_mapped(bh)) {
		goto free_jh;
	}
	/* the page is locked, and the only places that log a data buffer
	 * also lock the page.
L
Linus Torvalds 已提交
2897
	 */
2898 2899 2900 2901 2902 2903 2904 2905
	if (reiserfs_file_data_log(inode)) {
		/*
		 * very conservative, leave the buffer pinned if
		 * anyone might need it.
		 */
		if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
			ret = 0;
		}
2906
	} else  if (buffer_dirty(bh)) {
2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931
		struct reiserfs_journal_list *jl;
		struct reiserfs_jh *jh = bh->b_private;

		/* why is this safe?
		 * reiserfs_setattr updates i_size in the on disk
		 * stat data before allowing vmtruncate to be called.
		 *
		 * If buffer was put onto the ordered list for this
		 * transaction, we know for sure either this transaction
		 * or an older one already has updated i_size on disk,
		 * and this ordered data won't be referenced in the file
		 * if we crash.
		 *
		 * if the buffer was put onto the ordered list for an older
		 * transaction, we need to leave it around
		 */
		if (jh && (jl = jh->jl)
		    && jl != SB_JOURNAL(inode->i_sb)->j_current_jl)
			ret = 0;
	}
      free_jh:
	if (ret && bh->b_private) {
		reiserfs_free_jh(bh);
	}
	spin_unlock(&j->j_dirty_buffers_lock);
2932
	unlock_buffer(bh);
2933
	return ret;
L
Linus Torvalds 已提交
2934 2935 2936
}

/* clm -- taken from fs/buffer.c:block_invalidate_page */
2937
static void reiserfs_invalidatepage(struct page *page, unsigned long offset)
L
Linus Torvalds 已提交
2938
{
2939 2940 2941 2942
	struct buffer_head *head, *bh, *next;
	struct inode *inode = page->mapping->host;
	unsigned int curr_off = 0;
	int ret = 1;
L
Linus Torvalds 已提交
2943

2944
	BUG_ON(!PageLocked(page));
L
Linus Torvalds 已提交
2945

2946 2947
	if (offset == 0)
		ClearPageChecked(page);
L
Linus Torvalds 已提交
2948

2949 2950 2951 2952 2953 2954 2955 2956
	if (!page_has_buffers(page))
		goto out;

	head = page_buffers(page);
	bh = head;
	do {
		unsigned int next_off = curr_off + bh->b_size;
		next = bh->b_this_page;
L
Linus Torvalds 已提交
2957

2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969
		/*
		 * is this block fully invalidated?
		 */
		if (offset <= curr_off) {
			if (invalidatepage_can_drop(inode, bh))
				reiserfs_unmap_buffer(bh);
			else
				ret = 0;
		}
		curr_off = next_off;
		bh = next;
	} while (bh != head);
L
Linus Torvalds 已提交
2970 2971

	/*
2972 2973 2974
	 * We release buffers only if the entire page is being invalidated.
	 * The get_block cached value has been unconditionally invalidated,
	 * so real IO is not possible anymore.
L
Linus Torvalds 已提交
2975
	 */
2976
	if (!offset && ret) {
2977
		ret = try_to_release_page(page, 0);
2978 2979
		/* maybe should BUG_ON(!ret); - neilb */
	}
2980
      out:
2981
	return;
L
Linus Torvalds 已提交
2982 2983
}

2984 2985 2986 2987 2988 2989 2990 2991
static int reiserfs_set_page_dirty(struct page *page)
{
	struct inode *inode = page->mapping->host;
	if (reiserfs_file_data_log(inode)) {
		SetPageChecked(page);
		return __set_page_dirty_nobuffers(page);
	}
	return __set_page_dirty_buffers(page);
L
Linus Torvalds 已提交
2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002
}

/*
 * Returns 1 if the page's buffers were dropped.  The page is locked.
 *
 * Takes j_dirty_buffers_lock to protect the b_assoc_buffers list_heads
 * in the buffers at page_buffers(page).
 *
 * even in -o notail mode, we can't be sure an old mount without -o notail
 * didn't create files with tails.
 */
A
Al Viro 已提交
3003
static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags)
L
Linus Torvalds 已提交
3004
{
3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029
	struct inode *inode = page->mapping->host;
	struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
	struct buffer_head *head;
	struct buffer_head *bh;
	int ret = 1;

	WARN_ON(PageChecked(page));
	spin_lock(&j->j_dirty_buffers_lock);
	head = page_buffers(page);
	bh = head;
	do {
		if (bh->b_private) {
			if (!buffer_dirty(bh) && !buffer_locked(bh)) {
				reiserfs_free_jh(bh);
			} else {
				ret = 0;
				break;
			}
		}
		bh = bh->b_this_page;
	} while (bh != head);
	if (ret)
		ret = try_to_free_buffers(page);
	spin_unlock(&j->j_dirty_buffers_lock);
	return ret;
L
Linus Torvalds 已提交
3030 3031 3032 3033 3034
}

/* We thank Mingming Cao for helping us understand in great detail what
   to do in this section of the code. */
static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
3035 3036
				  const struct iovec *iov, loff_t offset,
				  unsigned long nr_segs)
L
Linus Torvalds 已提交
3037
{
3038 3039
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
L
Linus Torvalds 已提交
3040

3041 3042 3043
	return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				  offset, nr_segs,
				  reiserfs_get_blocks_direct_io, NULL);
L
Linus Torvalds 已提交
3044 3045
}

3046 3047 3048 3049
int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	int error;
3050 3051 3052 3053 3054
	unsigned int ia_valid;

	/* must be turned off for recursive notify_change calls */
	ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);

3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066
	reiserfs_write_lock(inode->i_sb);
	if (attr->ia_valid & ATTR_SIZE) {
		/* version 2 items will be caught by the s_maxbytes check
		 ** done for us in vmtruncate
		 */
		if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5 &&
		    attr->ia_size > MAX_NON_LFS) {
			error = -EFBIG;
			goto out;
		}
		/* fill in hole pointers in the expanding truncate case. */
		if (attr->ia_size > inode->i_size) {
3067
			error = generic_cont_expand_simple(inode, attr->ia_size);
3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081
			if (REISERFS_I(inode)->i_prealloc_count > 0) {
				int err;
				struct reiserfs_transaction_handle th;
				/* we're changing at most 2 bitmaps, inode + super */
				err = journal_begin(&th, inode->i_sb, 4);
				if (!err) {
					reiserfs_discard_prealloc(&th, inode);
					err = journal_end(&th, inode->i_sb, 4);
				}
				if (err)
					error = err;
			}
			if (error)
				goto out;
3082 3083 3084 3085 3086
			/*
			 * file size is changed, ctime and mtime are
			 * to be updated
			 */
			attr->ia_valid |= (ATTR_MTIME | ATTR_CTIME);
L
Linus Torvalds 已提交
3087 3088 3089
		}
	}

3090 3091 3092
	if ((((attr->ia_valid & ATTR_UID) && (attr->ia_uid & ~0xffff)) ||
	     ((attr->ia_valid & ATTR_GID) && (attr->ia_gid & ~0xffff))) &&
	    (get_inode_sd_version(inode) == STAT_DATA_V1)) {
L
Linus Torvalds 已提交
3093
		/* stat data of format v3.5 has 16 bit uid and gid */
3094 3095 3096
		error = -EINVAL;
		goto out;
	}
L
Linus Torvalds 已提交
3097

3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138
	error = inode_change_ok(inode, attr);
	if (!error) {
		if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
		    (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
			error = reiserfs_chown_xattrs(inode, attr);

			if (!error) {
				struct reiserfs_transaction_handle th;
				int jbegin_count =
				    2 *
				    (REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb) +
				     REISERFS_QUOTA_DEL_BLOCKS(inode->i_sb)) +
				    2;

				/* (user+group)*(old+new) structure - we count quota info and , inode write (sb, inode) */
				error =
				    journal_begin(&th, inode->i_sb,
						  jbegin_count);
				if (error)
					goto out;
				error =
				    DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
				if (error) {
					journal_end(&th, inode->i_sb,
						    jbegin_count);
					goto out;
				}
				/* Update corresponding info in inode so that everything is in
				 * one transaction */
				if (attr->ia_valid & ATTR_UID)
					inode->i_uid = attr->ia_uid;
				if (attr->ia_valid & ATTR_GID)
					inode->i_gid = attr->ia_gid;
				mark_inode_dirty(inode);
				error =
				    journal_end(&th, inode->i_sb, jbegin_count);
			}
		}
		if (!error)
			error = inode_setattr(inode, attr);
	}
L
Linus Torvalds 已提交
3139

3140 3141 3142 3143
	if (!error && reiserfs_posixacl(inode->i_sb)) {
		if (attr->ia_valid & ATTR_MODE)
			error = reiserfs_acl_chmod(inode);
	}
L
Linus Torvalds 已提交
3144

3145 3146 3147
      out:
	reiserfs_write_unlock(inode->i_sb);
	return error;
L
Linus Torvalds 已提交
3148 3149
}

3150
const struct address_space_operations reiserfs_address_space_operations = {
3151 3152 3153 3154 3155 3156
	.writepage = reiserfs_writepage,
	.readpage = reiserfs_readpage,
	.readpages = reiserfs_readpages,
	.releasepage = reiserfs_releasepage,
	.invalidatepage = reiserfs_invalidatepage,
	.sync_page = block_sync_page,
V
Vladimir Saveliev 已提交
3157 3158
	.write_begin = reiserfs_write_begin,
	.write_end = reiserfs_write_end,
3159 3160 3161 3162
	.bmap = reiserfs_aop_bmap,
	.direct_IO = reiserfs_direct_IO,
	.set_page_dirty = reiserfs_set_page_dirty,
};