ioctl.c 74.4 KB
Newer Older
C
Christoph Hellwig 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/file.h>
#include <linux/fs.h>
24
#include <linux/fsnotify.h>
C
Christoph Hellwig 已提交
25 26 27 28 29 30
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
31
#include <linux/mount.h>
C
Christoph Hellwig 已提交
32
#include <linux/mpage.h>
33
#include <linux/namei.h>
C
Christoph Hellwig 已提交
34 35 36 37 38
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/bit_spinlock.h>
39
#include <linux/security.h>
C
Christoph Hellwig 已提交
40
#include <linux/xattr.h>
41
#include <linux/vmalloc.h>
42
#include <linux/slab.h>
43
#include <linux/blkdev.h>
C
Chris Mason 已提交
44
#include "compat.h"
C
Christoph Hellwig 已提交
45 46 47 48 49 50 51
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "ioctl.h"
#include "print-tree.h"
#include "volumes.h"
52
#include "locking.h"
53
#include "inode-map.h"
54
#include "backref.h"
C
Christoph Hellwig 已提交
55

56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
{
	if (S_ISDIR(mode))
		return flags;
	else if (S_ISREG(mode))
		return flags & ~FS_DIRSYNC_FL;
	else
		return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
}

/*
 * Export inode flags to the format expected by the FS_IOC_GETFLAGS ioctl.
 */
static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
{
	unsigned int iflags = 0;

	if (flags & BTRFS_INODE_SYNC)
		iflags |= FS_SYNC_FL;
	if (flags & BTRFS_INODE_IMMUTABLE)
		iflags |= FS_IMMUTABLE_FL;
	if (flags & BTRFS_INODE_APPEND)
		iflags |= FS_APPEND_FL;
	if (flags & BTRFS_INODE_NODUMP)
		iflags |= FS_NODUMP_FL;
	if (flags & BTRFS_INODE_NOATIME)
		iflags |= FS_NOATIME_FL;
	if (flags & BTRFS_INODE_DIRSYNC)
		iflags |= FS_DIRSYNC_FL;
L
Li Zefan 已提交
86 87 88 89 90 91 92
	if (flags & BTRFS_INODE_NODATACOW)
		iflags |= FS_NOCOW_FL;

	if ((flags & BTRFS_INODE_COMPRESS) && !(flags & BTRFS_INODE_NOCOMPRESS))
		iflags |= FS_COMPR_FL;
	else if (flags & BTRFS_INODE_NOCOMPRESS)
		iflags |= FS_NOCOMP_FL;
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120

	return iflags;
}

/*
 * Update inode->i_flags based on the btrfs internal flags.
 */
void btrfs_update_iflags(struct inode *inode)
{
	struct btrfs_inode *ip = BTRFS_I(inode);

	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);

	if (ip->flags & BTRFS_INODE_SYNC)
		inode->i_flags |= S_SYNC;
	if (ip->flags & BTRFS_INODE_IMMUTABLE)
		inode->i_flags |= S_IMMUTABLE;
	if (ip->flags & BTRFS_INODE_APPEND)
		inode->i_flags |= S_APPEND;
	if (ip->flags & BTRFS_INODE_NOATIME)
		inode->i_flags |= S_NOATIME;
	if (ip->flags & BTRFS_INODE_DIRSYNC)
		inode->i_flags |= S_DIRSYNC;
}

/*
 * Inherit flags from the parent inode.
 *
121
 * Currently only the compression flags and the cow flags are inherited.
122 123 124
 */
void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
{
125 126 127 128 129 130
	unsigned int flags;

	if (!dir)
		return;

	flags = BTRFS_I(dir)->flags;
131

132 133 134 135 136 137 138 139 140 141
	if (flags & BTRFS_INODE_NOCOMPRESS) {
		BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS;
		BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
	} else if (flags & BTRFS_INODE_COMPRESS) {
		BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
		BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
	}

	if (flags & BTRFS_INODE_NODATACOW)
		BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
142 143 144 145 146 147 148 149 150 151 152 153 154 155

	btrfs_update_iflags(inode);
}

static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
{
	struct btrfs_inode *ip = BTRFS_I(file->f_path.dentry->d_inode);
	unsigned int flags = btrfs_flags_to_ioctl(ip->flags);

	if (copy_to_user(arg, &flags, sizeof(flags)))
		return -EFAULT;
	return 0;
}

156 157 158 159 160
static int check_flags(unsigned int flags)
{
	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
		      FS_NOATIME_FL | FS_NODUMP_FL | \
		      FS_SYNC_FL | FS_DIRSYNC_FL | \
L
Li Zefan 已提交
161 162
		      FS_NOCOMP_FL | FS_COMPR_FL |
		      FS_NOCOW_FL))
163 164 165 166 167 168 169 170
		return -EOPNOTSUPP;

	if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
		return -EINVAL;

	return 0;
}

171 172 173 174 175 176 177 178 179
static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct btrfs_inode *ip = BTRFS_I(inode);
	struct btrfs_root *root = ip->root;
	struct btrfs_trans_handle *trans;
	unsigned int flags, oldflags;
	int ret;

L
Li Zefan 已提交
180 181 182
	if (btrfs_root_readonly(root))
		return -EROFS;

183 184 185
	if (copy_from_user(&flags, arg, sizeof(flags)))
		return -EFAULT;

186 187 188
	ret = check_flags(flags);
	if (ret)
		return ret;
C
Christoph Hellwig 已提交
189

190
	if (!inode_owner_or_capable(inode))
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
		return -EACCES;

	mutex_lock(&inode->i_mutex);

	flags = btrfs_mask_flags(inode->i_mode, flags);
	oldflags = btrfs_flags_to_ioctl(ip->flags);
	if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
		if (!capable(CAP_LINUX_IMMUTABLE)) {
			ret = -EPERM;
			goto out_unlock;
		}
	}

	ret = mnt_want_write(file->f_path.mnt);
	if (ret)
		goto out_unlock;

	if (flags & FS_SYNC_FL)
		ip->flags |= BTRFS_INODE_SYNC;
	else
		ip->flags &= ~BTRFS_INODE_SYNC;
	if (flags & FS_IMMUTABLE_FL)
		ip->flags |= BTRFS_INODE_IMMUTABLE;
	else
		ip->flags &= ~BTRFS_INODE_IMMUTABLE;
	if (flags & FS_APPEND_FL)
		ip->flags |= BTRFS_INODE_APPEND;
	else
		ip->flags &= ~BTRFS_INODE_APPEND;
	if (flags & FS_NODUMP_FL)
		ip->flags |= BTRFS_INODE_NODUMP;
	else
		ip->flags &= ~BTRFS_INODE_NODUMP;
	if (flags & FS_NOATIME_FL)
		ip->flags |= BTRFS_INODE_NOATIME;
	else
		ip->flags &= ~BTRFS_INODE_NOATIME;
	if (flags & FS_DIRSYNC_FL)
		ip->flags |= BTRFS_INODE_DIRSYNC;
	else
		ip->flags &= ~BTRFS_INODE_DIRSYNC;
L
Li Zefan 已提交
232 233 234 235
	if (flags & FS_NOCOW_FL)
		ip->flags |= BTRFS_INODE_NODATACOW;
	else
		ip->flags &= ~BTRFS_INODE_NODATACOW;
236

237 238 239 240 241 242 243 244 245 246 247
	/*
	 * The COMPRESS flag can only be changed by users, while the NOCOMPRESS
	 * flag may be changed automatically if compression code won't make
	 * things smaller.
	 */
	if (flags & FS_NOCOMP_FL) {
		ip->flags &= ~BTRFS_INODE_COMPRESS;
		ip->flags |= BTRFS_INODE_NOCOMPRESS;
	} else if (flags & FS_COMPR_FL) {
		ip->flags |= BTRFS_INODE_COMPRESS;
		ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
L
Li Zefan 已提交
248 249
	} else {
		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
250
	}
251

252
	trans = btrfs_join_transaction(root);
253
	BUG_ON(IS_ERR(trans));
254 255 256 257 258 259 260 261 262

	ret = btrfs_update_inode(trans, root, inode);
	BUG_ON(ret);

	btrfs_update_iflags(inode);
	inode->i_ctime = CURRENT_TIME;
	btrfs_end_transaction(trans, root);

	mnt_drop_write(file->f_path.mnt);
263 264

	ret = 0;
265 266
 out_unlock:
	mutex_unlock(&inode->i_mutex);
267
	return ret;
268 269 270 271 272 273 274 275
}

static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
	struct inode *inode = file->f_path.dentry->d_inode;

	return put_user(inode->i_generation, arg);
}
C
Christoph Hellwig 已提交
276

277 278 279 280 281 282 283 284 285
static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
{
	struct btrfs_root *root = fdentry(file)->d_sb->s_fs_info;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_device *device;
	struct request_queue *q;
	struct fstrim_range range;
	u64 minlen = ULLONG_MAX;
	u64 num_devices = 0;
286
	u64 total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy);
287 288 289 290 291
	int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

292 293 294
	rcu_read_lock();
	list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
				dev_list) {
295 296 297 298 299 300 301 302 303
		if (!device->bdev)
			continue;
		q = bdev_get_queue(device->bdev);
		if (blk_queue_discard(q)) {
			num_devices++;
			minlen = min((u64)q->limits.discard_granularity,
				     minlen);
		}
	}
304
	rcu_read_unlock();
305

306 307 308 309
	if (!num_devices)
		return -EOPNOTSUPP;
	if (copy_from_user(&range, arg, sizeof(range)))
		return -EFAULT;
310 311
	if (range.start > total_bytes)
		return -EINVAL;
312

313
	range.len = min(range.len, total_bytes - range.start);
314 315 316 317 318 319 320 321 322 323 324
	range.minlen = max(range.minlen, minlen);
	ret = btrfs_trim_fs(root, &range);
	if (ret < 0)
		return ret;

	if (copy_to_user(arg, &range, sizeof(range)))
		return -EFAULT;

	return 0;
}

325 326
static noinline int create_subvol(struct btrfs_root *root,
				  struct dentry *dentry,
S
Sage Weil 已提交
327 328
				  char *name, int namelen,
				  u64 *async_transid)
C
Christoph Hellwig 已提交
329 330 331 332 333 334
{
	struct btrfs_trans_handle *trans;
	struct btrfs_key key;
	struct btrfs_root_item root_item;
	struct btrfs_inode_item *inode_item;
	struct extent_buffer *leaf;
335
	struct btrfs_root *new_root;
336
	struct dentry *parent = dentry->d_parent;
337
	struct inode *dir;
C
Christoph Hellwig 已提交
338 339 340 341
	int ret;
	int err;
	u64 objectid;
	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
342
	u64 index = 0;
C
Christoph Hellwig 已提交
343

344
	ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
345
	if (ret)
346
		return ret;
347 348 349

	dir = parent->d_inode;

J
Josef Bacik 已提交
350 351 352 353 354 355
	/*
	 * 1 - inode item
	 * 2 - refs
	 * 1 - root item
	 * 2 - dir items
	 */
356
	trans = btrfs_start_transaction(root, 6);
357
	if (IS_ERR(trans))
358
		return PTR_ERR(trans);
C
Christoph Hellwig 已提交
359

360 361
	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
				      0, objectid, NULL, 0, 0, 0);
362 363 364 365
	if (IS_ERR(leaf)) {
		ret = PTR_ERR(leaf);
		goto fail;
	}
C
Christoph Hellwig 已提交
366

367
	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
C
Christoph Hellwig 已提交
368 369
	btrfs_set_header_bytenr(leaf, leaf->start);
	btrfs_set_header_generation(leaf, trans->transid);
370
	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
C
Christoph Hellwig 已提交
371 372 373 374 375
	btrfs_set_header_owner(leaf, objectid);

	write_extent_buffer(leaf, root->fs_info->fsid,
			    (unsigned long)btrfs_header_fsid(leaf),
			    BTRFS_FSID_SIZE);
376 377 378
	write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
			    (unsigned long)btrfs_header_chunk_tree_uuid(leaf),
			    BTRFS_UUID_SIZE);
C
Christoph Hellwig 已提交
379 380 381 382 383 384 385
	btrfs_mark_buffer_dirty(leaf);

	inode_item = &root_item.inode;
	memset(inode_item, 0, sizeof(*inode_item));
	inode_item->generation = cpu_to_le64(1);
	inode_item->size = cpu_to_le64(3);
	inode_item->nlink = cpu_to_le32(1);
386
	inode_item->nbytes = cpu_to_le64(root->leafsize);
C
Christoph Hellwig 已提交
387 388
	inode_item->mode = cpu_to_le32(S_IFDIR | 0755);

389 390 391 392
	root_item.flags = 0;
	root_item.byte_limit = 0;
	inode_item->flags = cpu_to_le64(BTRFS_INODE_ROOT_ITEM_INIT);

C
Christoph Hellwig 已提交
393
	btrfs_set_root_bytenr(&root_item, leaf->start);
394
	btrfs_set_root_generation(&root_item, trans->transid);
C
Christoph Hellwig 已提交
395 396
	btrfs_set_root_level(&root_item, 0);
	btrfs_set_root_refs(&root_item, 1);
397
	btrfs_set_root_used(&root_item, leaf->len);
Y
Yan Zheng 已提交
398
	btrfs_set_root_last_snapshot(&root_item, 0);
C
Christoph Hellwig 已提交
399 400 401 402

	memset(&root_item.drop_progress, 0, sizeof(root_item.drop_progress));
	root_item.drop_level = 0;

403
	btrfs_tree_unlock(leaf);
C
Christoph Hellwig 已提交
404 405 406 407 408 409
	free_extent_buffer(leaf);
	leaf = NULL;

	btrfs_set_root_dirid(&root_item, new_dirid);

	key.objectid = objectid;
410
	key.offset = 0;
C
Christoph Hellwig 已提交
411 412 413 414 415 416
	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
				&root_item);
	if (ret)
		goto fail;

417 418 419 420 421 422
	key.offset = (u64)-1;
	new_root = btrfs_read_fs_root_no_name(root->fs_info, &key);
	BUG_ON(IS_ERR(new_root));

	btrfs_record_root_in_trans(trans, new_root);

423
	ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
C
Christoph Hellwig 已提交
424 425 426
	/*
	 * insert the directory item
	 */
427 428 429 430
	ret = btrfs_set_inode_index(dir, &index);
	BUG_ON(ret);

	ret = btrfs_insert_dir_item(trans, root,
431
				    name, namelen, dir, &key,
432
				    BTRFS_FT_DIR, index);
C
Christoph Hellwig 已提交
433 434
	if (ret)
		goto fail;
435

436 437 438 439
	btrfs_i_size_write(dir, dir->i_size + namelen * 2);
	ret = btrfs_update_inode(trans, root, dir);
	BUG_ON(ret);

440
	ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
441
				 objectid, root->root_key.objectid,
L
Li Zefan 已提交
442
				 btrfs_ino(dir), index, name, namelen);
443

444
	BUG_ON(ret);
C
Christoph Hellwig 已提交
445

446
	d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
C
Christoph Hellwig 已提交
447
fail:
S
Sage Weil 已提交
448 449 450 451 452 453
	if (async_transid) {
		*async_transid = trans->transid;
		err = btrfs_commit_transaction_async(trans, root, 1);
	} else {
		err = btrfs_commit_transaction(trans, root);
	}
C
Christoph Hellwig 已提交
454 455 456 457 458
	if (err && !ret)
		ret = err;
	return ret;
}

S
Sage Weil 已提交
459
static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
L
Li Zefan 已提交
460 461
			   char *name, int namelen, u64 *async_transid,
			   bool readonly)
C
Christoph Hellwig 已提交
462
{
463
	struct inode *inode;
C
Christoph Hellwig 已提交
464 465
	struct btrfs_pending_snapshot *pending_snapshot;
	struct btrfs_trans_handle *trans;
466
	int ret;
C
Christoph Hellwig 已提交
467 468 469 470

	if (!root->ref_cows)
		return -EINVAL;

471
	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
472 473 474 475
	if (!pending_snapshot)
		return -ENOMEM;

	btrfs_init_block_rsv(&pending_snapshot->block_rsv);
476
	pending_snapshot->dentry = dentry;
C
Christoph Hellwig 已提交
477
	pending_snapshot->root = root;
L
Li Zefan 已提交
478
	pending_snapshot->readonly = readonly;
479 480 481 482 483 484 485 486 487 488

	trans = btrfs_start_transaction(root->fs_info->extent_root, 5);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto fail;
	}

	ret = btrfs_snap_reserve_metadata(trans, pending_snapshot);
	BUG_ON(ret);

489
	spin_lock(&root->fs_info->trans_lock);
C
Christoph Hellwig 已提交
490 491
	list_add(&pending_snapshot->list,
		 &trans->transaction->pending_snapshots);
492
	spin_unlock(&root->fs_info->trans_lock);
S
Sage Weil 已提交
493 494 495 496 497 498 499 500
	if (async_transid) {
		*async_transid = trans->transid;
		ret = btrfs_commit_transaction_async(trans,
				     root->fs_info->extent_root, 1);
	} else {
		ret = btrfs_commit_transaction(trans,
					       root->fs_info->extent_root);
	}
501
	BUG_ON(ret);
502 503 504 505 506

	ret = pending_snapshot->error;
	if (ret)
		goto fail;

507 508 509
	ret = btrfs_orphan_cleanup(pending_snapshot->snap);
	if (ret)
		goto fail;
C
Christoph Hellwig 已提交
510

511
	inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
512 513 514 515 516 517 518 519
	if (IS_ERR(inode)) {
		ret = PTR_ERR(inode);
		goto fail;
	}
	BUG_ON(!inode);
	d_instantiate(dentry, inode);
	ret = 0;
fail:
520
	kfree(pending_snapshot);
C
Christoph Hellwig 已提交
521 522 523
	return ret;
}

524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
/*  copy of check_sticky in fs/namei.c()
* It's inline, so penalty for filesystems that don't use sticky bit is
* minimal.
*/
static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode)
{
	uid_t fsuid = current_fsuid();

	if (!(dir->i_mode & S_ISVTX))
		return 0;
	if (inode->i_uid == fsuid)
		return 0;
	if (dir->i_uid == fsuid)
		return 0;
	return !capable(CAP_FOWNER);
}

/*  copy of may_delete in fs/namei.c()
 *	Check whether we can remove a link victim from directory dir, check
 *  whether the type of victim is right.
 *  1. We can't do it if dir is read-only (done in permission())
 *  2. We should have write and exec permissions on dir
 *  3. We can't remove anything from append-only dir
 *  4. We can't do anything with immutable dir (done in permission())
 *  5. If the sticky bit on dir is set we should either
 *	a. be owner of dir, or
 *	b. be owner of victim, or
 *	c. have CAP_FOWNER capability
 *  6. If the victim is append-only or immutable we can't do antyhing with
 *     links pointing to it.
 *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
 *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
 *  9. We can't remove a root or mountpoint.
 * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
 *     nfs_async_unlink().
 */

static int btrfs_may_delete(struct inode *dir,struct dentry *victim,int isdir)
{
	int error;

	if (!victim->d_inode)
		return -ENOENT;

	BUG_ON(victim->d_parent->d_inode != dir);
	audit_inode_child(victim, dir);

	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		return error;
	if (IS_APPEND(dir))
		return -EPERM;
	if (btrfs_check_sticky(dir, victim->d_inode)||
		IS_APPEND(victim->d_inode)||
	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
		return -EPERM;
	if (isdir) {
		if (!S_ISDIR(victim->d_inode->i_mode))
			return -ENOTDIR;
		if (IS_ROOT(victim))
			return -EBUSY;
	} else if (S_ISDIR(victim->d_inode->i_mode))
		return -EISDIR;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	if (victim->d_flags & DCACHE_NFSFS_RENAMED)
		return -EBUSY;
	return 0;
}

594 595 596 597 598 599 600 601 602 603 604 605 606 607 608
/* copy of may_create in fs/namei.c() */
static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
{
	if (child->d_inode)
		return -EEXIST;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	return inode_permission(dir, MAY_WRITE | MAY_EXEC);
}

/*
 * Create a new subvolume below @parent.  This is largely modeled after
 * sys_mkdirat and vfs_mkdir, but we only do a single component lookup
 * inside this filesystem so it's quite a bit simpler.
 */
609 610
static noinline int btrfs_mksubvol(struct path *parent,
				   char *name, int namelen,
S
Sage Weil 已提交
611
				   struct btrfs_root *snap_src,
L
Li Zefan 已提交
612
				   u64 *async_transid, bool readonly)
613
{
614
	struct inode *dir  = parent->dentry->d_inode;
615 616 617
	struct dentry *dentry;
	int error;

618
	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
619 620 621 622 623 624 625 626 627 628 629 630 631 632

	dentry = lookup_one_len(name, parent->dentry, namelen);
	error = PTR_ERR(dentry);
	if (IS_ERR(dentry))
		goto out_unlock;

	error = -EEXIST;
	if (dentry->d_inode)
		goto out_dput;

	error = mnt_want_write(parent->mnt);
	if (error)
		goto out_dput;

633
	error = btrfs_may_create(dir, dentry);
634 635 636
	if (error)
		goto out_drop_write;

637 638 639 640 641
	down_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);

	if (btrfs_root_refs(&BTRFS_I(dir)->root->root_item) == 0)
		goto out_up_read;

642
	if (snap_src) {
S
Sage Weil 已提交
643
		error = create_snapshot(snap_src, dentry,
L
Li Zefan 已提交
644
					name, namelen, async_transid, readonly);
645
	} else {
646
		error = create_subvol(BTRFS_I(dir)->root, dentry,
S
Sage Weil 已提交
647
				      name, namelen, async_transid);
648
	}
649 650 651 652
	if (!error)
		fsnotify_mkdir(dir, dentry);
out_up_read:
	up_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
653 654 655 656 657
out_drop_write:
	mnt_drop_write(parent->mnt);
out_dput:
	dput(dentry);
out_unlock:
658
	mutex_unlock(&dir->i_mutex);
659 660 661
	return error;
}

C
Chris Mason 已提交
662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
/*
 * When we're defragging a range, we don't want to kick it off again
 * if it is really just waiting for delalloc to send it down.
 * If we find a nice big extent or delalloc range for the bytes in the
 * file you want to defrag, we return 0 to let you know to skip this
 * part of the file
 */
static int check_defrag_in_cache(struct inode *inode, u64 offset, int thresh)
{
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_map *em = NULL;
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	u64 end;

	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE);
	read_unlock(&em_tree->lock);

	if (em) {
		end = extent_map_end(em);
		free_extent_map(em);
		if (end - offset > thresh)
			return 0;
	}
	/* if we already have a nice delalloc here, just stop */
	thresh /= 2;
	end = count_range_bits(io_tree, &offset, offset + thresh,
			       thresh, EXTENT_DELALLOC, 1);
	if (end >= thresh)
		return 0;
	return 1;
}

/*
 * helper function to walk through a file and find extents
 * newer than a specific transid, and smaller than thresh.
 *
 * This is used by the defragging code to find new and small
 * extents
 */
static int find_new_extents(struct btrfs_root *root,
			    struct inode *inode, u64 newer_than,
			    u64 *off, int thresh)
{
	struct btrfs_path *path;
	struct btrfs_key min_key;
	struct btrfs_key max_key;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *extent;
	int type;
	int ret;
713
	u64 ino = btrfs_ino(inode);
C
Chris Mason 已提交
714 715 716 717 718

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

719
	min_key.objectid = ino;
C
Chris Mason 已提交
720 721 722
	min_key.type = BTRFS_EXTENT_DATA_KEY;
	min_key.offset = *off;

723
	max_key.objectid = ino;
C
Chris Mason 已提交
724 725 726 727 728 729 730 731 732 733
	max_key.type = (u8)-1;
	max_key.offset = (u64)-1;

	path->keep_locks = 1;

	while(1) {
		ret = btrfs_search_forward(root, &min_key, &max_key,
					   path, 0, newer_than);
		if (ret != 0)
			goto none;
734
		if (min_key.objectid != ino)
C
Chris Mason 已提交
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
			goto none;
		if (min_key.type != BTRFS_EXTENT_DATA_KEY)
			goto none;

		leaf = path->nodes[0];
		extent = btrfs_item_ptr(leaf, path->slots[0],
					struct btrfs_file_extent_item);

		type = btrfs_file_extent_type(leaf, extent);
		if (type == BTRFS_FILE_EXTENT_REG &&
		    btrfs_file_extent_num_bytes(leaf, extent) < thresh &&
		    check_defrag_in_cache(inode, min_key.offset, thresh)) {
			*off = min_key.offset;
			btrfs_free_path(path);
			return 0;
		}

		if (min_key.offset == (u64)-1)
			goto none;

		min_key.offset++;
		btrfs_release_path(path);
	}
none:
	btrfs_free_path(path);
	return -ENOENT;
}

763
static int should_defrag_range(struct inode *inode, u64 start, u64 len,
C
Chris Mason 已提交
764 765
			       int thresh, u64 *last_len, u64 *skip,
			       u64 *defrag_end)
766 767 768 769 770 771 772
{
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_map *em = NULL;
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	int ret = 1;

	/*
773
	 * make sure that once we start defragging an extent, we keep on
774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794
	 * defragging it
	 */
	if (start < *defrag_end)
		return 1;

	*skip = 0;

	/*
	 * hopefully we have this extent in the tree already, try without
	 * the full extent lock
	 */
	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, start, len);
	read_unlock(&em_tree->lock);

	if (!em) {
		/* get the big lock and read metadata off disk */
		lock_extent(io_tree, start, start + len - 1, GFP_NOFS);
		em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
		unlock_extent(io_tree, start, start + len - 1, GFP_NOFS);

795
		if (IS_ERR(em))
796 797 798 799 800 801 802 803 804 805
			return 0;
	}

	/* this will cover holes, and inline extents */
	if (em->block_start >= EXTENT_MAP_LAST_BYTE)
		ret = 0;

	/*
	 * we hit a real extent, if it is big don't bother defragging it again
	 */
C
Chris Mason 已提交
806
	if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh)
807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828
		ret = 0;

	/*
	 * last_len ends up being a counter of how many bytes we've defragged.
	 * every time we choose not to defrag an extent, we reset *last_len
	 * so that the next tiny extent will force a defrag.
	 *
	 * The end result of this is that tiny extents before a single big
	 * extent will force at least part of that big extent to be defragged.
	 */
	if (ret) {
		*defrag_end = extent_map_end(em);
	} else {
		*last_len = 0;
		*skip = extent_map_end(em);
		*defrag_end = 0;
	}

	free_extent_map(em);
	return ret;
}

C
Chris Mason 已提交
829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844
/*
 * it doesn't do much good to defrag one or two pages
 * at a time.  This pulls in a nice chunk of pages
 * to COW and defrag.
 *
 * It also makes sure the delalloc code has enough
 * dirty data to avoid making new small extents as part
 * of the defrag
 *
 * It's a good idea to start RA on this range
 * before calling this.
 */
static int cluster_pages_for_defrag(struct inode *inode,
				    struct page **pages,
				    unsigned long start_index,
				    int num_pages)
C
Christoph Hellwig 已提交
845
{
C
Chris Mason 已提交
846 847 848 849 850 851 852
	unsigned long file_end;
	u64 isize = i_size_read(inode);
	u64 page_start;
	u64 page_end;
	int ret;
	int i;
	int i_done;
853
	struct btrfs_ordered_extent *ordered;
C
Chris Mason 已提交
854
	struct extent_state *cached_state = NULL;
855
	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
C
Chris Mason 已提交
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871

	if (isize == 0)
		return 0;
	file_end = (isize - 1) >> PAGE_CACHE_SHIFT;

	ret = btrfs_delalloc_reserve_space(inode,
					   num_pages << PAGE_CACHE_SHIFT);
	if (ret)
		return ret;
again:
	ret = 0;
	i_done = 0;

	/* step one, lock all the pages */
	for (i = 0; i < num_pages; i++) {
		struct page *page;
872
		page = find_or_create_page(inode->i_mapping,
873
					    start_index + i, mask);
C
Chris Mason 已提交
874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942
		if (!page)
			break;

		if (!PageUptodate(page)) {
			btrfs_readpage(NULL, page);
			lock_page(page);
			if (!PageUptodate(page)) {
				unlock_page(page);
				page_cache_release(page);
				ret = -EIO;
				break;
			}
		}
		isize = i_size_read(inode);
		file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
		if (!isize || page->index > file_end ||
		    page->mapping != inode->i_mapping) {
			/* whoops, we blew past eof, skip this page */
			unlock_page(page);
			page_cache_release(page);
			break;
		}
		pages[i] = page;
		i_done++;
	}
	if (!i_done || ret)
		goto out;

	if (!(inode->i_sb->s_flags & MS_ACTIVE))
		goto out;

	/*
	 * so now we have a nice long stream of locked
	 * and up to date pages, lets wait on them
	 */
	for (i = 0; i < i_done; i++)
		wait_on_page_writeback(pages[i]);

	page_start = page_offset(pages[0]);
	page_end = page_offset(pages[i_done - 1]) + PAGE_CACHE_SIZE;

	lock_extent_bits(&BTRFS_I(inode)->io_tree,
			 page_start, page_end - 1, 0, &cached_state,
			 GFP_NOFS);
	ordered = btrfs_lookup_first_ordered_extent(inode, page_end - 1);
	if (ordered &&
	    ordered->file_offset + ordered->len > page_start &&
	    ordered->file_offset < page_end) {
		btrfs_put_ordered_extent(ordered);
		unlock_extent_cached(&BTRFS_I(inode)->io_tree,
				     page_start, page_end - 1,
				     &cached_state, GFP_NOFS);
		for (i = 0; i < i_done; i++) {
			unlock_page(pages[i]);
			page_cache_release(pages[i]);
		}
		btrfs_wait_ordered_range(inode, page_start,
					 page_end - page_start);
		goto again;
	}
	if (ordered)
		btrfs_put_ordered_extent(ordered);

	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
			  page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
			  EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
			  GFP_NOFS);

	if (i_done != num_pages) {
943 944 945
		spin_lock(&BTRFS_I(inode)->lock);
		BTRFS_I(inode)->outstanding_extents++;
		spin_unlock(&BTRFS_I(inode)->lock);
C
Chris Mason 已提交
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
		btrfs_delalloc_release_space(inode,
				     (num_pages - i_done) << PAGE_CACHE_SHIFT);
	}


	btrfs_set_extent_delalloc(inode, page_start, page_end - 1,
				  &cached_state);

	unlock_extent_cached(&BTRFS_I(inode)->io_tree,
			     page_start, page_end - 1, &cached_state,
			     GFP_NOFS);

	for (i = 0; i < i_done; i++) {
		clear_page_dirty_for_io(pages[i]);
		ClearPageChecked(pages[i]);
		set_page_extent_mapped(pages[i]);
		set_page_dirty(pages[i]);
		unlock_page(pages[i]);
		page_cache_release(pages[i]);
	}
	return i_done;
out:
	for (i = 0; i < i_done; i++) {
		unlock_page(pages[i]);
		page_cache_release(pages[i]);
	}
	btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT);
	return ret;

}

int btrfs_defrag_file(struct inode *inode, struct file *file,
		      struct btrfs_ioctl_defrag_range_args *range,
		      u64 newer_than, unsigned long max_to_defrag)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
982
	struct btrfs_super_block *disk_super;
C
Chris Mason 已提交
983
	struct file_ra_state *ra = NULL;
C
Christoph Hellwig 已提交
984
	unsigned long last_index;
985
	u64 isize = i_size_read(inode);
986
	u64 features;
987 988 989
	u64 last_len = 0;
	u64 skip = 0;
	u64 defrag_end = 0;
C
Chris Mason 已提交
990
	u64 newer_off = range->start;
C
Christoph Hellwig 已提交
991
	unsigned long i;
992
	unsigned long ra_index = 0;
C
Christoph Hellwig 已提交
993
	int ret;
C
Chris Mason 已提交
994
	int defrag_count = 0;
995
	int compress_type = BTRFS_COMPRESS_ZLIB;
C
Chris Mason 已提交
996
	int extent_thresh = range->extent_thresh;
997 998
	int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
	int cluster = max_cluster;
C
Chris Mason 已提交
999 1000 1001 1002 1003
	u64 new_align = ~((u64)128 * 1024 - 1);
	struct page **pages = NULL;

	if (extent_thresh == 0)
		extent_thresh = 256 * 1024;
1004 1005 1006 1007 1008 1009 1010

	if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
		if (range->compress_type > BTRFS_COMPRESS_TYPES)
			return -EINVAL;
		if (range->compress_type)
			compress_type = range->compress_type;
	}
C
Christoph Hellwig 已提交
1011

1012
	if (isize == 0)
1013 1014
		return 0;

C
Chris Mason 已提交
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
	/*
	 * if we were not given a file, allocate a readahead
	 * context
	 */
	if (!file) {
		ra = kzalloc(sizeof(*ra), GFP_NOFS);
		if (!ra)
			return -ENOMEM;
		file_ra_state_init(ra, inode->i_mapping);
	} else {
		ra = &file->f_ra;
	}

1028
	pages = kmalloc(sizeof(struct page *) * max_cluster,
C
Chris Mason 已提交
1029 1030 1031 1032 1033 1034 1035
			GFP_NOFS);
	if (!pages) {
		ret = -ENOMEM;
		goto out_ra;
	}

	/* find the last page to defrag */
C
Chris Mason 已提交
1036
	if (range->start + range->len > range->start) {
1037
		last_index = min_t(u64, isize - 1,
C
Chris Mason 已提交
1038 1039
			 range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
	} else {
1040
		last_index = (isize - 1) >> PAGE_CACHE_SHIFT;
C
Chris Mason 已提交
1041 1042
	}

C
Chris Mason 已提交
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058
	if (newer_than) {
		ret = find_new_extents(root, inode, newer_than,
				       &newer_off, 64 * 1024);
		if (!ret) {
			range->start = newer_off;
			/*
			 * we always align our defrag to help keep
			 * the extents in the file evenly spaced
			 */
			i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
		} else
			goto out_ra;
	} else {
		i = range->start >> PAGE_CACHE_SHIFT;
	}
	if (!max_to_defrag)
1059
		max_to_defrag = last_index;
C
Chris Mason 已提交
1060

L
Li Zefan 已提交
1061 1062 1063 1064 1065 1066 1067
	/*
	 * make writeback starts from i, so the defrag range can be
	 * written sequentially.
	 */
	if (i < inode->i_mapping->writeback_index)
		inode->i_mapping->writeback_index = i;

1068 1069 1070
	while (i <= last_index && defrag_count < max_to_defrag &&
	       (i < (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
		PAGE_CACHE_SHIFT)) {
C
Chris Mason 已提交
1071 1072 1073 1074 1075 1076 1077 1078 1079
		/*
		 * make sure we stop running if someone unmounts
		 * the FS
		 */
		if (!(inode->i_sb->s_flags & MS_ACTIVE))
			break;

		if (!newer_than &&
		    !should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
C
Chris Mason 已提交
1080
					PAGE_CACHE_SIZE,
C
Chris Mason 已提交
1081
					extent_thresh,
C
Chris Mason 已提交
1082
					&last_len, &skip,
1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
					&defrag_end)) {
			unsigned long next;
			/*
			 * the should_defrag function tells us how much to skip
			 * bump our counter by the suggested amount
			 */
			next = (skip + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
			i = max(i + 1, next);
			continue;
		}
1093 1094 1095 1096 1097 1098 1099 1100 1101

		if (!newer_than) {
			cluster = (PAGE_CACHE_ALIGN(defrag_end) >>
				   PAGE_CACHE_SHIFT) - i;
			cluster = min(cluster, max_cluster);
		} else {
			cluster = max_cluster;
		}

C
Chris Mason 已提交
1102
		if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
1103
			BTRFS_I(inode)->force_compress = compress_type;
1104

1105 1106 1107 1108 1109 1110
		if (i + cluster > ra_index) {
			ra_index = max(i, ra_index);
			btrfs_force_ra(inode->i_mapping, ra, file, ra_index,
				       cluster);
			ra_index += max_cluster;
		}
1111

1112
		ret = cluster_pages_for_defrag(inode, pages, i, cluster);
C
Chris Mason 已提交
1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
		if (ret < 0)
			goto out_ra;

		defrag_count += ret;
		balance_dirty_pages_ratelimited_nr(inode->i_mapping, ret);

		if (newer_than) {
			if (newer_off == (u64)-1)
				break;

			newer_off = max(newer_off + 1,
					(u64)i << PAGE_CACHE_SHIFT);

			ret = find_new_extents(root, inode,
					       newer_than, &newer_off,
					       64 * 1024);
			if (!ret) {
				range->start = newer_off;
				i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
			} else {
				break;
C
Christoph Hellwig 已提交
1134
			}
C
Chris Mason 已提交
1135
		} else {
1136
			if (ret > 0) {
L
Li Zefan 已提交
1137
				i += ret;
1138 1139
				last_len += ret << PAGE_CACHE_SHIFT;
			} else {
L
Li Zefan 已提交
1140
				i++;
1141 1142
				last_len = 0;
			}
C
Christoph Hellwig 已提交
1143 1144 1145
		}
	}

C
Chris Mason 已提交
1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
	if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO))
		filemap_flush(inode->i_mapping);

	if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
		/* the filemap_flush will queue IO into the worker threads, but
		 * we have to make sure the IO is actually started and that
		 * ordered extents get created before we return
		 */
		atomic_inc(&root->fs_info->async_submit_draining);
		while (atomic_read(&root->fs_info->nr_async_submits) ||
		      atomic_read(&root->fs_info->async_delalloc_pages)) {
			wait_event(root->fs_info->async_submit_wait,
			   (atomic_read(&root->fs_info->nr_async_submits) == 0 &&
			    atomic_read(&root->fs_info->async_delalloc_pages) == 0));
		}
		atomic_dec(&root->fs_info->async_submit_draining);

		mutex_lock(&inode->i_mutex);
1164
		BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
C
Chris Mason 已提交
1165 1166 1167
		mutex_unlock(&inode->i_mutex);
	}

1168
	disk_super = root->fs_info->super_copy;
1169 1170 1171 1172 1173 1174
	features = btrfs_super_incompat_flags(disk_super);
	if (range->compress_type == BTRFS_COMPRESS_LZO) {
		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
		btrfs_set_super_incompat_flags(disk_super, features);
	}

1175
	ret = defrag_count;
1176

C
Chris Mason 已提交
1177 1178 1179 1180
out_ra:
	if (!file)
		kfree(ra);
	kfree(pages);
1181
	return ret;
C
Christoph Hellwig 已提交
1182 1183
}

1184 1185
static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
					void __user *arg)
C
Christoph Hellwig 已提交
1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197
{
	u64 new_size;
	u64 old_size;
	u64 devid = 1;
	struct btrfs_ioctl_vol_args *vol_args;
	struct btrfs_trans_handle *trans;
	struct btrfs_device *device = NULL;
	char *sizestr;
	char *devstr = NULL;
	int ret = 0;
	int mod = 0;

Y
Yan Zheng 已提交
1198 1199 1200
	if (root->fs_info->sb->s_flags & MS_RDONLY)
		return -EROFS;

1201 1202 1203
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

L
Li Zefan 已提交
1204 1205 1206
	vol_args = memdup_user(arg, sizeof(*vol_args));
	if (IS_ERR(vol_args))
		return PTR_ERR(vol_args);
1207 1208

	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
C
Christoph Hellwig 已提交
1209

1210
	mutex_lock(&root->fs_info->volume_mutex);
C
Christoph Hellwig 已提交
1211 1212 1213 1214 1215 1216 1217 1218
	sizestr = vol_args->name;
	devstr = strchr(sizestr, ':');
	if (devstr) {
		char *end;
		sizestr = devstr + 1;
		*devstr = '\0';
		devstr = vol_args->name;
		devid = simple_strtoull(devstr, &end, 10);
1219
		printk(KERN_INFO "btrfs: resizing devid %llu\n",
1220
		       (unsigned long long)devid);
C
Christoph Hellwig 已提交
1221
	}
Y
Yan Zheng 已提交
1222
	device = btrfs_find_device(root, devid, NULL, NULL);
C
Christoph Hellwig 已提交
1223
	if (!device) {
1224
		printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
1225
		       (unsigned long long)devid);
C
Christoph Hellwig 已提交
1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
		ret = -EINVAL;
		goto out_unlock;
	}
	if (!strcmp(sizestr, "max"))
		new_size = device->bdev->bd_inode->i_size;
	else {
		if (sizestr[0] == '-') {
			mod = -1;
			sizestr++;
		} else if (sizestr[0] == '+') {
			mod = 1;
			sizestr++;
		}
A
Akinobu Mita 已提交
1239
		new_size = memparse(sizestr, NULL);
C
Christoph Hellwig 已提交
1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
		if (new_size == 0) {
			ret = -EINVAL;
			goto out_unlock;
		}
	}

	old_size = device->total_bytes;

	if (mod < 0) {
		if (new_size > old_size) {
			ret = -EINVAL;
			goto out_unlock;
		}
		new_size = old_size - new_size;
	} else if (mod > 0) {
		new_size = old_size + new_size;
	}

	if (new_size < 256 * 1024 * 1024) {
		ret = -EINVAL;
		goto out_unlock;
	}
	if (new_size > device->bdev->bd_inode->i_size) {
		ret = -EFBIG;
		goto out_unlock;
	}

	do_div(new_size, root->sectorsize);
	new_size *= root->sectorsize;

1270
	printk(KERN_INFO "btrfs: new size for %s is %llu\n",
C
Christoph Hellwig 已提交
1271 1272 1273
		device->name, (unsigned long long)new_size);

	if (new_size > old_size) {
1274
		trans = btrfs_start_transaction(root, 0);
1275 1276 1277 1278
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			goto out_unlock;
		}
C
Christoph Hellwig 已提交
1279 1280
		ret = btrfs_grow_device(trans, device, new_size);
		btrfs_commit_transaction(trans, root);
1281
	} else if (new_size < old_size) {
C
Christoph Hellwig 已提交
1282 1283 1284 1285
		ret = btrfs_shrink_device(device, new_size);
	}

out_unlock:
1286
	mutex_unlock(&root->fs_info->volume_mutex);
C
Christoph Hellwig 已提交
1287 1288 1289 1290
	kfree(vol_args);
	return ret;
}

S
Sage Weil 已提交
1291 1292 1293 1294
static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
						    char *name,
						    unsigned long fd,
						    int subvol,
L
Li Zefan 已提交
1295 1296
						    u64 *transid,
						    bool readonly)
C
Christoph Hellwig 已提交
1297
{
1298
	struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
1299
	struct file *src_file;
C
Christoph Hellwig 已提交
1300
	int namelen;
1301
	int ret = 0;
C
Christoph Hellwig 已提交
1302

Y
Yan Zheng 已提交
1303 1304 1305
	if (root->fs_info->sb->s_flags & MS_RDONLY)
		return -EROFS;

S
Sage Weil 已提交
1306 1307
	namelen = strlen(name);
	if (strchr(name, '/')) {
C
Christoph Hellwig 已提交
1308 1309 1310 1311
		ret = -EINVAL;
		goto out;
	}

1312
	if (subvol) {
S
Sage Weil 已提交
1313
		ret = btrfs_mksubvol(&file->f_path, name, namelen,
L
Li Zefan 已提交
1314
				     NULL, transid, readonly);
1315
	} else {
1316
		struct inode *src_inode;
S
Sage Weil 已提交
1317
		src_file = fget(fd);
1318 1319 1320 1321 1322 1323 1324
		if (!src_file) {
			ret = -EINVAL;
			goto out;
		}

		src_inode = src_file->f_path.dentry->d_inode;
		if (src_inode->i_sb != file->f_path.dentry->d_inode->i_sb) {
C
Chris Mason 已提交
1325 1326
			printk(KERN_INFO "btrfs: Snapshot src from "
			       "another FS\n");
1327 1328 1329 1330
			ret = -EINVAL;
			fput(src_file);
			goto out;
		}
S
Sage Weil 已提交
1331 1332
		ret = btrfs_mksubvol(&file->f_path, name, namelen,
				     BTRFS_I(src_inode)->root,
L
Li Zefan 已提交
1333
				     transid, readonly);
1334
		fput(src_file);
1335
	}
C
Christoph Hellwig 已提交
1336
out:
S
Sage Weil 已提交
1337 1338 1339 1340
	return ret;
}

static noinline int btrfs_ioctl_snap_create(struct file *file,
1341
					    void __user *arg, int subvol)
S
Sage Weil 已提交
1342
{
1343
	struct btrfs_ioctl_vol_args *vol_args;
S
Sage Weil 已提交
1344 1345
	int ret;

1346 1347 1348 1349
	vol_args = memdup_user(arg, sizeof(*vol_args));
	if (IS_ERR(vol_args))
		return PTR_ERR(vol_args);
	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
S
Sage Weil 已提交
1350

1351
	ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
L
Li Zefan 已提交
1352 1353
					      vol_args->fd, subvol,
					      NULL, false);
1354

1355 1356 1357
	kfree(vol_args);
	return ret;
}
1358

1359 1360 1361 1362 1363 1364 1365
static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
					       void __user *arg, int subvol)
{
	struct btrfs_ioctl_vol_args_v2 *vol_args;
	int ret;
	u64 transid = 0;
	u64 *ptr = NULL;
L
Li Zefan 已提交
1366
	bool readonly = false;
1367

1368 1369 1370 1371
	vol_args = memdup_user(arg, sizeof(*vol_args));
	if (IS_ERR(vol_args))
		return PTR_ERR(vol_args);
	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
1372

L
Li Zefan 已提交
1373 1374 1375
	if (vol_args->flags &
	    ~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY)) {
		ret = -EOPNOTSUPP;
1376
		goto out;
S
Sage Weil 已提交
1377
	}
1378 1379 1380

	if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC)
		ptr = &transid;
L
Li Zefan 已提交
1381 1382
	if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
		readonly = true;
1383 1384

	ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
L
Li Zefan 已提交
1385 1386
					      vol_args->fd, subvol,
					      ptr, readonly);
1387 1388 1389 1390 1391 1392

	if (ret == 0 && ptr &&
	    copy_to_user(arg +
			 offsetof(struct btrfs_ioctl_vol_args_v2,
				  transid), ptr, sizeof(*ptr)))
		ret = -EFAULT;
1393
out:
C
Christoph Hellwig 已提交
1394 1395 1396 1397
	kfree(vol_args);
	return ret;
}

1398 1399 1400 1401 1402 1403 1404 1405
static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
						void __user *arg)
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int ret = 0;
	u64 flags = 0;

L
Li Zefan 已提交
1406
	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432
		return -EINVAL;

	down_read(&root->fs_info->subvol_sem);
	if (btrfs_root_readonly(root))
		flags |= BTRFS_SUBVOL_RDONLY;
	up_read(&root->fs_info->subvol_sem);

	if (copy_to_user(arg, &flags, sizeof(flags)))
		ret = -EFAULT;

	return ret;
}

static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
					      void __user *arg)
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	u64 root_flags;
	u64 flags;
	int ret = 0;

	if (root->fs_info->sb->s_flags & MS_RDONLY)
		return -EROFS;

L
Li Zefan 已提交
1433
	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
1434 1435 1436 1437 1438
		return -EINVAL;

	if (copy_from_user(&flags, arg, sizeof(flags)))
		return -EFAULT;

1439
	if (flags & BTRFS_SUBVOL_CREATE_ASYNC)
1440 1441 1442 1443 1444
		return -EINVAL;

	if (flags & ~BTRFS_SUBVOL_RDONLY)
		return -EOPNOTSUPP;

1445
	if (!inode_owner_or_capable(inode))
1446 1447
		return -EACCES;

1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467
	down_write(&root->fs_info->subvol_sem);

	/* nothing to do */
	if (!!(flags & BTRFS_SUBVOL_RDONLY) == btrfs_root_readonly(root))
		goto out;

	root_flags = btrfs_root_flags(&root->root_item);
	if (flags & BTRFS_SUBVOL_RDONLY)
		btrfs_set_root_flags(&root->root_item,
				     root_flags | BTRFS_ROOT_SUBVOL_RDONLY);
	else
		btrfs_set_root_flags(&root->root_item,
				     root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);

	trans = btrfs_start_transaction(root, 1);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out_reset;
	}

1468
	ret = btrfs_update_root(trans, root->fs_info->tree_root,
1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479
				&root->root_key, &root->root_item);

	btrfs_commit_transaction(trans, root);
out_reset:
	if (ret)
		btrfs_set_root_flags(&root->root_item, root_flags);
out:
	up_write(&root->fs_info->subvol_sem);
	return ret;
}

1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
/*
 * helper to check if the subvolume references other subvolumes
 */
static noinline int may_destroy_subvol(struct btrfs_root *root)
{
	struct btrfs_path *path;
	struct btrfs_key key;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	key.objectid = root->root_key.objectid;
	key.type = BTRFS_ROOT_REF_KEY;
	key.offset = (u64)-1;

	ret = btrfs_search_slot(NULL, root->fs_info->tree_root,
				&key, path, 0, 0);
	if (ret < 0)
		goto out;
	BUG_ON(ret == 0);

	ret = 0;
	if (path->slots[0] > 0) {
		path->slots[0]--;
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid == root->root_key.objectid &&
		    key.type == BTRFS_ROOT_REF_KEY)
			ret = -ENOTEMPTY;
	}
out:
	btrfs_free_path(path);
	return ret;
}

1516 1517 1518
static noinline int key_in_sk(struct btrfs_key *key,
			      struct btrfs_ioctl_search_key *sk)
{
1519 1520 1521 1522 1523 1524 1525 1526 1527
	struct btrfs_key test;
	int ret;

	test.objectid = sk->min_objectid;
	test.type = sk->min_type;
	test.offset = sk->min_offset;

	ret = btrfs_comp_cpu_keys(key, &test);
	if (ret < 0)
1528
		return 0;
1529 1530 1531 1532 1533 1534 1535

	test.objectid = sk->max_objectid;
	test.type = sk->max_type;
	test.offset = sk->max_offset;

	ret = btrfs_comp_cpu_keys(key, &test);
	if (ret > 0)
1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 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
		return 0;
	return 1;
}

static noinline int copy_to_sk(struct btrfs_root *root,
			       struct btrfs_path *path,
			       struct btrfs_key *key,
			       struct btrfs_ioctl_search_key *sk,
			       char *buf,
			       unsigned long *sk_offset,
			       int *num_found)
{
	u64 found_transid;
	struct extent_buffer *leaf;
	struct btrfs_ioctl_search_header sh;
	unsigned long item_off;
	unsigned long item_len;
	int nritems;
	int i;
	int slot;
	int ret = 0;

	leaf = path->nodes[0];
	slot = path->slots[0];
	nritems = btrfs_header_nritems(leaf);

	if (btrfs_header_generation(leaf) > sk->max_transid) {
		i = nritems;
		goto advance_key;
	}
	found_transid = btrfs_header_generation(leaf);

	for (i = slot; i < nritems; i++) {
		item_off = btrfs_item_ptr_offset(leaf, i);
		item_len = btrfs_item_size_nr(leaf, i);

		if (item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
			item_len = 0;

		if (sizeof(sh) + item_len + *sk_offset >
		    BTRFS_SEARCH_ARGS_BUFSIZE) {
			ret = 1;
			goto overflow;
		}

		btrfs_item_key_to_cpu(leaf, key, i);
		if (!key_in_sk(key, sk))
			continue;

		sh.objectid = key->objectid;
		sh.offset = key->offset;
		sh.type = key->type;
		sh.len = item_len;
		sh.transid = found_transid;

		/* copy search result header */
		memcpy(buf + *sk_offset, &sh, sizeof(sh));
		*sk_offset += sizeof(sh);

		if (item_len) {
			char *p = buf + *sk_offset;
			/* copy the item */
			read_extent_buffer(leaf, p,
					   item_off, item_len);
			*sk_offset += item_len;
		}
1602
		(*num_found)++;
1603 1604 1605 1606 1607

		if (*num_found >= sk->nr_items)
			break;
	}
advance_key:
1608 1609
	ret = 0;
	if (key->offset < (u64)-1 && key->offset < sk->max_offset)
1610
		key->offset++;
1611 1612
	else if (key->type < (u8)-1 && key->type < sk->max_type) {
		key->offset = 0;
1613
		key->type++;
1614 1615 1616
	} else if (key->objectid < (u64)-1 && key->objectid < sk->max_objectid) {
		key->offset = 0;
		key->type = 0;
1617
		key->objectid++;
1618 1619
	} else
		ret = 1;
1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 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
overflow:
	return ret;
}

static noinline int search_ioctl(struct inode *inode,
				 struct btrfs_ioctl_search_args *args)
{
	struct btrfs_root *root;
	struct btrfs_key key;
	struct btrfs_key max_key;
	struct btrfs_path *path;
	struct btrfs_ioctl_search_key *sk = &args->key;
	struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info;
	int ret;
	int num_found = 0;
	unsigned long sk_offset = 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	if (sk->tree_id == 0) {
		/* search the root of the inode that was passed */
		root = BTRFS_I(inode)->root;
	} else {
		key.objectid = sk->tree_id;
		key.type = BTRFS_ROOT_ITEM_KEY;
		key.offset = (u64)-1;
		root = btrfs_read_fs_root_no_name(info, &key);
		if (IS_ERR(root)) {
			printk(KERN_ERR "could not find root %llu\n",
			       sk->tree_id);
			btrfs_free_path(path);
			return -ENOENT;
		}
	}

	key.objectid = sk->min_objectid;
	key.type = sk->min_type;
	key.offset = sk->min_offset;

	max_key.objectid = sk->max_objectid;
	max_key.type = sk->max_type;
	max_key.offset = sk->max_offset;

	path->keep_locks = 1;

	while(1) {
		ret = btrfs_search_forward(root, &key, &max_key, path, 0,
					   sk->min_transid);
		if (ret != 0) {
			if (ret > 0)
				ret = 0;
			goto err;
		}
		ret = copy_to_sk(root, path, &key, sk, args->buf,
				 &sk_offset, &num_found);
1677
		btrfs_release_path(path);
1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698
		if (ret || num_found >= sk->nr_items)
			break;

	}
	ret = 0;
err:
	sk->nr_items = num_found;
	btrfs_free_path(path);
	return ret;
}

static noinline int btrfs_ioctl_tree_search(struct file *file,
					   void __user *argp)
{
	 struct btrfs_ioctl_search_args *args;
	 struct inode *inode;
	 int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

J
Julia Lawall 已提交
1699 1700 1701
	args = memdup_user(argp, sizeof(*args));
	if (IS_ERR(args))
		return PTR_ERR(args);
1702 1703 1704 1705 1706 1707 1708 1709 1710

	inode = fdentry(file)->d_inode;
	ret = search_ioctl(inode, args);
	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
		ret = -EFAULT;
	kfree(args);
	return ret;
}

1711
/*
1712 1713 1714
 * Search INODE_REFs to identify path name of 'dirid' directory
 * in a 'tree_id' tree. and sets path name to 'name'.
 */
1715 1716 1717 1718 1719
static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
				u64 tree_id, u64 dirid, char *name)
{
	struct btrfs_root *root;
	struct btrfs_key key;
1720
	char *ptr;
1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737
	int ret = -1;
	int slot;
	int len;
	int total_len = 0;
	struct btrfs_inode_ref *iref;
	struct extent_buffer *l;
	struct btrfs_path *path;

	if (dirid == BTRFS_FIRST_FREE_OBJECTID) {
		name[0]='\0';
		return 0;
	}

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

1738
	ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX];
1739 1740 1741 1742 1743 1744 1745

	key.objectid = tree_id;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;
	root = btrfs_read_fs_root_no_name(info, &key);
	if (IS_ERR(root)) {
		printk(KERN_ERR "could not find root %llu\n", tree_id);
1746 1747
		ret = -ENOENT;
		goto out;
1748 1749 1750 1751
	}

	key.objectid = dirid;
	key.type = BTRFS_INODE_REF_KEY;
1752
	key.offset = (u64)-1;
1753 1754 1755 1756 1757 1758 1759 1760

	while(1) {
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		if (ret < 0)
			goto out;

		l = path->nodes[0];
		slot = path->slots[0];
1761 1762
		if (ret > 0 && slot > 0)
			slot--;
1763 1764 1765
		btrfs_item_key_to_cpu(l, &key, slot);

		if (ret > 0 && (key.objectid != dirid ||
1766 1767
				key.type != BTRFS_INODE_REF_KEY)) {
			ret = -ENOENT;
1768
			goto out;
1769
		}
1770 1771 1772 1773 1774

		iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref);
		len = btrfs_inode_ref_name_len(l, iref);
		ptr -= len + 1;
		total_len += len + 1;
1775
		if (ptr < name)
1776 1777 1778 1779 1780 1781 1782 1783
			goto out;

		*(ptr + len) = '/';
		read_extent_buffer(l, ptr,(unsigned long)(iref + 1), len);

		if (key.offset == BTRFS_FIRST_FREE_OBJECTID)
			break;

1784
		btrfs_release_path(path);
1785
		key.objectid = key.offset;
1786
		key.offset = (u64)-1;
1787 1788
		dirid = key.objectid;
	}
1789
	if (ptr < name)
1790
		goto out;
1791
	memmove(name, ptr, total_len);
1792 1793 1794 1795
	name[total_len]='\0';
	ret = 0;
out:
	btrfs_free_path(path);
1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808
	return ret;
}

static noinline int btrfs_ioctl_ino_lookup(struct file *file,
					   void __user *argp)
{
	 struct btrfs_ioctl_ino_lookup_args *args;
	 struct inode *inode;
	 int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

J
Julia Lawall 已提交
1809 1810 1811
	args = memdup_user(argp, sizeof(*args));
	if (IS_ERR(args))
		return PTR_ERR(args);
1812

1813 1814
	inode = fdentry(file)->d_inode;

1815 1816 1817
	if (args->treeid == 0)
		args->treeid = BTRFS_I(inode)->root->root_key.objectid;

1818 1819 1820 1821 1822 1823 1824 1825
	ret = btrfs_search_path_in_tree(BTRFS_I(inode)->root->fs_info,
					args->treeid, args->objectid,
					args->name);

	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
		ret = -EFAULT;

	kfree(args);
1826 1827 1828
	return ret;
}

1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 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
static noinline int btrfs_ioctl_snap_destroy(struct file *file,
					     void __user *arg)
{
	struct dentry *parent = fdentry(file);
	struct dentry *dentry;
	struct inode *dir = parent->d_inode;
	struct inode *inode;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_root *dest = NULL;
	struct btrfs_ioctl_vol_args *vol_args;
	struct btrfs_trans_handle *trans;
	int namelen;
	int ret;
	int err = 0;

	vol_args = memdup_user(arg, sizeof(*vol_args));
	if (IS_ERR(vol_args))
		return PTR_ERR(vol_args);

	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
	namelen = strlen(vol_args->name);
	if (strchr(vol_args->name, '/') ||
	    strncmp(vol_args->name, "..", namelen) == 0) {
		err = -EINVAL;
		goto out;
	}

	err = mnt_want_write(file->f_path.mnt);
	if (err)
		goto out;

	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
	dentry = lookup_one_len(vol_args->name, parent, namelen);
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out_unlock_dir;
	}

	if (!dentry->d_inode) {
		err = -ENOENT;
		goto out_dput;
	}

	inode = dentry->d_inode;
1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912
	dest = BTRFS_I(inode)->root;
	if (!capable(CAP_SYS_ADMIN)){
		/*
		 * Regular user.  Only allow this with a special mount
		 * option, when the user has write+exec access to the
		 * subvol root, and when rmdir(2) would have been
		 * allowed.
		 *
		 * Note that this is _not_ check that the subvol is
		 * empty or doesn't contain data that we wouldn't
		 * otherwise be able to delete.
		 *
		 * Users who want to delete empty subvols should try
		 * rmdir(2).
		 */
		err = -EPERM;
		if (!btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
			goto out_dput;

		/*
		 * Do not allow deletion if the parent dir is the same
		 * as the dir to be deleted.  That means the ioctl
		 * must be called on the dentry referencing the root
		 * of the subvol, not a random directory contained
		 * within it.
		 */
		err = -EINVAL;
		if (root == dest)
			goto out_dput;

		err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
		if (err)
			goto out_dput;

		/* check if subvolume may be deleted by a non-root user */
		err = btrfs_may_delete(dir, dentry, 1);
		if (err)
			goto out_dput;
	}

L
Li Zefan 已提交
1913
	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928
		err = -EINVAL;
		goto out_dput;
	}

	mutex_lock(&inode->i_mutex);
	err = d_invalidate(dentry);
	if (err)
		goto out_unlock;

	down_write(&root->fs_info->subvol_sem);

	err = may_destroy_subvol(dest);
	if (err)
		goto out_up_write;

1929 1930 1931
	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
1932
		goto out_up_write;
1933 1934 1935
	}
	trans->block_rsv = &root->fs_info->global_block_rsv;

1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948
	ret = btrfs_unlink_subvol(trans, root, dir,
				dest->root_key.objectid,
				dentry->d_name.name,
				dentry->d_name.len);
	BUG_ON(ret);

	btrfs_record_root_in_trans(trans, dest);

	memset(&dest->root_item.drop_progress, 0,
		sizeof(dest->root_item.drop_progress));
	dest->root_item.drop_level = 0;
	btrfs_set_root_refs(&dest->root_item, 0);

1949 1950 1951 1952 1953 1954
	if (!xchg(&dest->orphan_item_inserted, 1)) {
		ret = btrfs_insert_orphan_item(trans,
					root->fs_info->tree_root,
					dest->root_key.objectid);
		BUG_ON(ret);
	}
1955

S
Sage Weil 已提交
1956
	ret = btrfs_end_transaction(trans, root);
1957 1958 1959 1960 1961 1962 1963
	BUG_ON(ret);
	inode->i_flags |= S_DEAD;
out_up_write:
	up_write(&root->fs_info->subvol_sem);
out_unlock:
	mutex_unlock(&inode->i_mutex);
	if (!err) {
1964
		shrink_dcache_sb(root->fs_info->sb);
1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977
		btrfs_invalidate_inodes(dest);
		d_delete(dentry);
	}
out_dput:
	dput(dentry);
out_unlock_dir:
	mutex_unlock(&dir->i_mutex);
	mnt_drop_write(file->f_path.mnt);
out:
	kfree(vol_args);
	return err;
}

C
Chris Mason 已提交
1978
static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
C
Christoph Hellwig 已提交
1979 1980 1981
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
C
Chris Mason 已提交
1982
	struct btrfs_ioctl_defrag_range_args *range;
Y
Yan Zheng 已提交
1983 1984
	int ret;

L
Li Zefan 已提交
1985 1986 1987
	if (btrfs_root_readonly(root))
		return -EROFS;

Y
Yan Zheng 已提交
1988 1989 1990
	ret = mnt_want_write(file->f_path.mnt);
	if (ret)
		return ret;
C
Christoph Hellwig 已提交
1991 1992 1993

	switch (inode->i_mode & S_IFMT) {
	case S_IFDIR:
1994 1995 1996 1997
		if (!capable(CAP_SYS_ADMIN)) {
			ret = -EPERM;
			goto out;
		}
1998 1999 2000 2001
		ret = btrfs_defrag_root(root, 0);
		if (ret)
			goto out;
		ret = btrfs_defrag_root(root->fs_info->extent_root, 0);
C
Christoph Hellwig 已提交
2002 2003
		break;
	case S_IFREG:
2004 2005 2006 2007
		if (!(file->f_mode & FMODE_WRITE)) {
			ret = -EINVAL;
			goto out;
		}
C
Chris Mason 已提交
2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019

		range = kzalloc(sizeof(*range), GFP_KERNEL);
		if (!range) {
			ret = -ENOMEM;
			goto out;
		}

		if (argp) {
			if (copy_from_user(range, argp,
					   sizeof(*range))) {
				ret = -EFAULT;
				kfree(range);
2020
				goto out;
C
Chris Mason 已提交
2021 2022 2023 2024 2025 2026 2027 2028 2029 2030
			}
			/* compression requires us to start the IO */
			if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
				range->flags |= BTRFS_DEFRAG_RANGE_START_IO;
				range->extent_thresh = (u32)-1;
			}
		} else {
			/* the rest are all set to zero by kzalloc */
			range->len = (u64)-1;
		}
C
Chris Mason 已提交
2031 2032 2033 2034
		ret = btrfs_defrag_file(fdentry(file)->d_inode, file,
					range, 0, 0);
		if (ret > 0)
			ret = 0;
C
Chris Mason 已提交
2035
		kfree(range);
C
Christoph Hellwig 已提交
2036
		break;
2037 2038
	default:
		ret = -EINVAL;
C
Christoph Hellwig 已提交
2039
	}
2040
out:
2041
	mnt_drop_write(file->f_path.mnt);
2042
	return ret;
C
Christoph Hellwig 已提交
2043 2044
}

2045
static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
C
Christoph Hellwig 已提交
2046 2047 2048 2049
{
	struct btrfs_ioctl_vol_args *vol_args;
	int ret;

2050 2051 2052
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

L
Li Zefan 已提交
2053 2054 2055
	vol_args = memdup_user(arg, sizeof(*vol_args));
	if (IS_ERR(vol_args))
		return PTR_ERR(vol_args);
C
Christoph Hellwig 已提交
2056

2057
	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
C
Christoph Hellwig 已提交
2058 2059 2060 2061 2062 2063
	ret = btrfs_init_new_device(root, vol_args->name);

	kfree(vol_args);
	return ret;
}

2064
static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg)
C
Christoph Hellwig 已提交
2065 2066 2067 2068
{
	struct btrfs_ioctl_vol_args *vol_args;
	int ret;

2069 2070 2071
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

Y
Yan Zheng 已提交
2072 2073 2074
	if (root->fs_info->sb->s_flags & MS_RDONLY)
		return -EROFS;

L
Li Zefan 已提交
2075 2076 2077
	vol_args = memdup_user(arg, sizeof(*vol_args));
	if (IS_ERR(vol_args))
		return PTR_ERR(vol_args);
C
Christoph Hellwig 已提交
2078

2079
	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
C
Christoph Hellwig 已提交
2080 2081 2082 2083 2084 2085
	ret = btrfs_rm_device(root, vol_args->name);

	kfree(vol_args);
	return ret;
}

J
Jan Schmidt 已提交
2086 2087
static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
{
2088
	struct btrfs_ioctl_fs_info_args *fi_args;
J
Jan Schmidt 已提交
2089 2090 2091
	struct btrfs_device *device;
	struct btrfs_device *next;
	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
2092
	int ret = 0;
J
Jan Schmidt 已提交
2093 2094 2095 2096

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

2097 2098 2099 2100 2101 2102
	fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
	if (!fi_args)
		return -ENOMEM;

	fi_args->num_devices = fs_devices->num_devices;
	memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid));
J
Jan Schmidt 已提交
2103 2104 2105

	mutex_lock(&fs_devices->device_list_mutex);
	list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
2106 2107
		if (device->devid > fi_args->max_id)
			fi_args->max_id = device->devid;
J
Jan Schmidt 已提交
2108 2109 2110
	}
	mutex_unlock(&fs_devices->device_list_mutex);

2111 2112
	if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
		ret = -EFAULT;
J
Jan Schmidt 已提交
2113

2114 2115
	kfree(fi_args);
	return ret;
J
Jan Schmidt 已提交
2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159
}

static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
{
	struct btrfs_ioctl_dev_info_args *di_args;
	struct btrfs_device *dev;
	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
	int ret = 0;
	char *s_uuid = NULL;
	char empty_uuid[BTRFS_UUID_SIZE] = {0};

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	di_args = memdup_user(arg, sizeof(*di_args));
	if (IS_ERR(di_args))
		return PTR_ERR(di_args);

	if (memcmp(empty_uuid, di_args->uuid, BTRFS_UUID_SIZE) != 0)
		s_uuid = di_args->uuid;

	mutex_lock(&fs_devices->device_list_mutex);
	dev = btrfs_find_device(root, di_args->devid, s_uuid, NULL);
	mutex_unlock(&fs_devices->device_list_mutex);

	if (!dev) {
		ret = -ENODEV;
		goto out;
	}

	di_args->devid = dev->devid;
	di_args->bytes_used = dev->bytes_used;
	di_args->total_bytes = dev->total_bytes;
	memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
	strncpy(di_args->path, dev->name, sizeof(di_args->path));

out:
	if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
		ret = -EFAULT;

	kfree(di_args);
	return ret;
}

2160 2161
static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
				       u64 off, u64 olen, u64 destoff)
C
Christoph Hellwig 已提交
2162 2163 2164 2165 2166 2167 2168 2169
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct file *src_file;
	struct inode *src;
	struct btrfs_trans_handle *trans;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
Y
Yan Zheng 已提交
2170 2171
	char *buf;
	struct btrfs_key key;
C
Christoph Hellwig 已提交
2172 2173
	u32 nritems;
	int slot;
Y
Yan Zheng 已提交
2174
	int ret;
2175 2176 2177
	u64 len = olen;
	u64 bs = root->fs_info->sb->s_blocksize;
	u64 hint_byte;
2178

2179 2180 2181 2182 2183 2184 2185 2186 2187 2188
	/*
	 * TODO:
	 * - split compressed inline extents.  annoying: we need to
	 *   decompress into destination's address_space (the file offset
	 *   may change, so source mapping won't do), then recompress (or
	 *   otherwise reinsert) a subrange.
	 * - allow ranges within the same file to be cloned (provided
	 *   they don't overlap)?
	 */

2189
	/* the destination must be opened for writing */
2190
	if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
2191 2192
		return -EINVAL;

L
Li Zefan 已提交
2193 2194 2195
	if (btrfs_root_readonly(root))
		return -EROFS;

Y
Yan Zheng 已提交
2196 2197 2198 2199
	ret = mnt_want_write(file->f_path.mnt);
	if (ret)
		return ret;

2200
	src_file = fget(srcfd);
2201 2202 2203 2204
	if (!src_file) {
		ret = -EBADF;
		goto out_drop_write;
	}
2205

C
Christoph Hellwig 已提交
2206 2207
	src = src_file->f_dentry->d_inode;

2208 2209 2210 2211
	ret = -EINVAL;
	if (src == inode)
		goto out_fput;

2212 2213 2214 2215
	/* the src must be open for reading */
	if (!(src_file->f_mode & FMODE_READ))
		goto out_fput;

2216 2217 2218 2219 2220
	/* don't make the dst file partly checksummed */
	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
		goto out_fput;

Y
Yan Zheng 已提交
2221 2222 2223 2224
	ret = -EISDIR;
	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
		goto out_fput;

C
Christoph Hellwig 已提交
2225
	ret = -EXDEV;
Y
Yan Zheng 已提交
2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236
	if (src->i_sb != inode->i_sb || BTRFS_I(src)->root != root)
		goto out_fput;

	ret = -ENOMEM;
	buf = vmalloc(btrfs_level_size(root, 0));
	if (!buf)
		goto out_fput;

	path = btrfs_alloc_path();
	if (!path) {
		vfree(buf);
C
Christoph Hellwig 已提交
2237
		goto out_fput;
Y
Yan Zheng 已提交
2238 2239
	}
	path->reada = 2;
C
Christoph Hellwig 已提交
2240 2241

	if (inode < src) {
2242 2243
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
		mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
C
Christoph Hellwig 已提交
2244
	} else {
2245 2246
		mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
C
Christoph Hellwig 已提交
2247 2248
	}

2249 2250
	/* determine range to clone */
	ret = -EINVAL;
2251
	if (off + len > src->i_size || off + len < off)
C
Christoph Hellwig 已提交
2252
		goto out_unlock;
2253 2254 2255 2256
	if (len == 0)
		olen = len = src->i_size - off;
	/* if we extend to eof, continue to block boundary */
	if (off + len == src->i_size)
2257
		len = ALIGN(src->i_size, bs) - off;
2258 2259

	/* verify the end result is block aligned */
2260 2261
	if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
	    !IS_ALIGNED(destoff, bs))
2262 2263
		goto out_unlock;

2264 2265 2266 2267 2268 2269
	if (destoff > inode->i_size) {
		ret = btrfs_cont_expand(inode, inode->i_size, destoff);
		if (ret)
			goto out_unlock;
	}

2270 2271 2272 2273
	/* truncate page cache pages from target inode range */
	truncate_inode_pages_range(&inode->i_data, destoff,
				   PAGE_CACHE_ALIGN(destoff + len) - 1);

C
Christoph Hellwig 已提交
2274 2275 2276
	/* do any pending delalloc/csum calc on src, one way or
	   another, and lock file content */
	while (1) {
Z
Zheng Yan 已提交
2277
		struct btrfs_ordered_extent *ordered;
2278
		lock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
2279 2280 2281 2282
		ordered = btrfs_lookup_first_ordered_extent(src, off+len);
		if (!ordered &&
		    !test_range_bit(&BTRFS_I(src)->io_tree, off, off+len,
				   EXTENT_DELALLOC, 0, NULL))
C
Christoph Hellwig 已提交
2283
			break;
2284
		unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
Y
Yan Zheng 已提交
2285 2286
		if (ordered)
			btrfs_put_ordered_extent(ordered);
2287
		btrfs_wait_ordered_range(src, off, len);
C
Christoph Hellwig 已提交
2288 2289
	}

2290
	/* clone data */
L
Li Zefan 已提交
2291
	key.objectid = btrfs_ino(src);
Y
Yan Zheng 已提交
2292 2293
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = 0;
C
Christoph Hellwig 已提交
2294 2295 2296 2297 2298 2299

	while (1) {
		/*
		 * note the key will change type as we walk through the
		 * tree.
		 */
2300
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
C
Christoph Hellwig 已提交
2301 2302 2303
		if (ret < 0)
			goto out;

Y
Yan Zheng 已提交
2304 2305
		nritems = btrfs_header_nritems(path->nodes[0]);
		if (path->slots[0] >= nritems) {
C
Christoph Hellwig 已提交
2306 2307 2308 2309 2310
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				goto out;
			if (ret > 0)
				break;
Y
Yan Zheng 已提交
2311
			nritems = btrfs_header_nritems(path->nodes[0]);
C
Christoph Hellwig 已提交
2312 2313 2314 2315
		}
		leaf = path->nodes[0];
		slot = path->slots[0];

Y
Yan Zheng 已提交
2316
		btrfs_item_key_to_cpu(leaf, &key, slot);
2317
		if (btrfs_key_type(&key) > BTRFS_EXTENT_DATA_KEY ||
L
Li Zefan 已提交
2318
		    key.objectid != btrfs_ino(src))
C
Christoph Hellwig 已提交
2319 2320
			break;

2321 2322 2323
		if (btrfs_key_type(&key) == BTRFS_EXTENT_DATA_KEY) {
			struct btrfs_file_extent_item *extent;
			int type;
Z
Zheng Yan 已提交
2324 2325
			u32 size;
			struct btrfs_key new_key;
2326 2327 2328
			u64 disko = 0, diskl = 0;
			u64 datao = 0, datal = 0;
			u8 comp;
2329
			u64 endoff;
Z
Zheng Yan 已提交
2330 2331 2332 2333 2334

			size = btrfs_item_size_nr(leaf, slot);
			read_extent_buffer(leaf, buf,
					   btrfs_item_ptr_offset(leaf, slot),
					   size);
2335 2336 2337 2338 2339

			extent = btrfs_item_ptr(leaf, slot,
						struct btrfs_file_extent_item);
			comp = btrfs_file_extent_compression(leaf, extent);
			type = btrfs_file_extent_type(leaf, extent);
2340 2341
			if (type == BTRFS_FILE_EXTENT_REG ||
			    type == BTRFS_FILE_EXTENT_PREALLOC) {
C
Chris Mason 已提交
2342 2343 2344 2345
				disko = btrfs_file_extent_disk_bytenr(leaf,
								      extent);
				diskl = btrfs_file_extent_disk_num_bytes(leaf,
								 extent);
2346
				datao = btrfs_file_extent_offset(leaf, extent);
C
Chris Mason 已提交
2347 2348
				datal = btrfs_file_extent_num_bytes(leaf,
								    extent);
2349 2350 2351 2352 2353
			} else if (type == BTRFS_FILE_EXTENT_INLINE) {
				/* take upper bound, may be compressed */
				datal = btrfs_file_extent_ram_bytes(leaf,
								    extent);
			}
2354
			btrfs_release_path(path);
Z
Zheng Yan 已提交
2355

2356
			if (key.offset + datal <= off ||
2357 2358 2359
			    key.offset >= off+len)
				goto next;

Z
Zheng Yan 已提交
2360
			memcpy(&new_key, &key, sizeof(new_key));
L
Li Zefan 已提交
2361
			new_key.objectid = btrfs_ino(inode);
2362 2363 2364 2365
			if (off <= key.offset)
				new_key.offset = key.offset + destoff - off;
			else
				new_key.offset = destoff;
Z
Zheng Yan 已提交
2366

2367 2368 2369 2370 2371 2372
			/*
			 * 1 - adjusting old extent (we may have to split it)
			 * 1 - add new extent
			 * 1 - inode update
			 */
			trans = btrfs_start_transaction(root, 3);
2373 2374 2375 2376 2377
			if (IS_ERR(trans)) {
				ret = PTR_ERR(trans);
				goto out;
			}

2378 2379
			if (type == BTRFS_FILE_EXTENT_REG ||
			    type == BTRFS_FILE_EXTENT_PREALLOC) {
2380 2381 2382 2383 2384 2385 2386 2387 2388 2389
				/*
				 *    a  | --- range to clone ---|  b
				 * | ------------- extent ------------- |
				 */

				/* substract range b */
				if (key.offset + datal > off + len)
					datal = off + len - key.offset;

				/* substract range a */
2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400
				if (off > key.offset) {
					datao += off - key.offset;
					datal -= off - key.offset;
				}

				ret = btrfs_drop_extents(trans, inode,
							 new_key.offset,
							 new_key.offset + datal,
							 &hint_byte, 1);
				BUG_ON(ret);

2401 2402
				ret = btrfs_insert_empty_item(trans, root, path,
							      &new_key, size);
2403
				BUG_ON(ret);
2404 2405 2406 2407

				leaf = path->nodes[0];
				slot = path->slots[0];
				write_extent_buffer(leaf, buf,
Z
Zheng Yan 已提交
2408 2409
					    btrfs_item_ptr_offset(leaf, slot),
					    size);
Y
Yan Zheng 已提交
2410

2411
				extent = btrfs_item_ptr(leaf, slot,
C
Christoph Hellwig 已提交
2412
						struct btrfs_file_extent_item);
2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423

				/* disko == 0 means it's a hole */
				if (!disko)
					datao = 0;

				btrfs_set_file_extent_offset(leaf, extent,
							     datao);
				btrfs_set_file_extent_num_bytes(leaf, extent,
								datal);
				if (disko) {
					inode_add_bytes(inode, datal);
Y
Yan Zheng 已提交
2424
					ret = btrfs_inc_extent_ref(trans, root,
2425 2426
							disko, diskl, 0,
							root->root_key.objectid,
L
Li Zefan 已提交
2427
							btrfs_ino(inode),
2428
							new_key.offset - datao);
Z
Zheng Yan 已提交
2429
					BUG_ON(ret);
C
Christoph Hellwig 已提交
2430
				}
2431 2432 2433 2434 2435 2436 2437
			} else if (type == BTRFS_FILE_EXTENT_INLINE) {
				u64 skip = 0;
				u64 trim = 0;
				if (off > key.offset) {
					skip = off - key.offset;
					new_key.offset += skip;
				}
C
Chris Mason 已提交
2438

2439 2440
				if (key.offset + datal > off+len)
					trim = key.offset + datal - (off+len);
C
Chris Mason 已提交
2441

2442 2443
				if (comp && (skip || trim)) {
					ret = -EINVAL;
2444
					btrfs_end_transaction(trans, root);
2445 2446 2447 2448
					goto out;
				}
				size -= skip + trim;
				datal -= skip + trim;
2449 2450 2451 2452 2453 2454 2455

				ret = btrfs_drop_extents(trans, inode,
							 new_key.offset,
							 new_key.offset + datal,
							 &hint_byte, 1);
				BUG_ON(ret);

2456 2457
				ret = btrfs_insert_empty_item(trans, root, path,
							      &new_key, size);
2458
				BUG_ON(ret);
2459 2460

				if (skip) {
C
Chris Mason 已提交
2461 2462
					u32 start =
					  btrfs_file_extent_calc_inline_size(0);
2463 2464 2465 2466 2467 2468 2469 2470 2471 2472
					memmove(buf+start, buf+start+skip,
						datal);
				}

				leaf = path->nodes[0];
				slot = path->slots[0];
				write_extent_buffer(leaf, buf,
					    btrfs_item_ptr_offset(leaf, slot),
					    size);
				inode_add_bytes(inode, datal);
C
Christoph Hellwig 已提交
2473
			}
2474 2475

			btrfs_mark_buffer_dirty(leaf);
2476
			btrfs_release_path(path);
2477

2478
			inode->i_mtime = inode->i_ctime = CURRENT_TIME;
2479 2480 2481 2482 2483 2484 2485

			/*
			 * we round up to the block size at eof when
			 * determining which extents to clone above,
			 * but shouldn't round up the file size
			 */
			endoff = new_key.offset + datal;
2486 2487
			if (endoff > destoff+olen)
				endoff = destoff+olen;
2488 2489 2490
			if (endoff > inode->i_size)
				btrfs_i_size_write(inode, endoff);

2491 2492 2493 2494
			ret = btrfs_update_inode(trans, root, inode);
			BUG_ON(ret);
			btrfs_end_transaction(trans, root);
		}
C
Chris Mason 已提交
2495
next:
2496
		btrfs_release_path(path);
C
Christoph Hellwig 已提交
2497 2498 2499 2500
		key.offset++;
	}
	ret = 0;
out:
2501
	btrfs_release_path(path);
2502
	unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS);
C
Christoph Hellwig 已提交
2503 2504 2505
out_unlock:
	mutex_unlock(&src->i_mutex);
	mutex_unlock(&inode->i_mutex);
Y
Yan Zheng 已提交
2506 2507
	vfree(buf);
	btrfs_free_path(path);
C
Christoph Hellwig 已提交
2508 2509
out_fput:
	fput(src_file);
2510 2511
out_drop_write:
	mnt_drop_write(file->f_path.mnt);
C
Christoph Hellwig 已提交
2512 2513 2514
	return ret;
}

2515
static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
2516 2517 2518
{
	struct btrfs_ioctl_clone_range_args args;

2519
	if (copy_from_user(&args, argp, sizeof(args)))
2520 2521 2522 2523 2524
		return -EFAULT;
	return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
				 args.src_length, args.dest_offset);
}

C
Christoph Hellwig 已提交
2525 2526 2527 2528 2529 2530
/*
 * there are many ways the trans_start and trans_end ioctls can lead
 * to deadlocks.  They should only be used by applications that
 * basically own the machine, and have a very in depth understanding
 * of all the possible deadlocks and enospc problems.
 */
2531
static long btrfs_ioctl_trans_start(struct file *file)
C
Christoph Hellwig 已提交
2532 2533 2534 2535
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
2536
	int ret;
C
Christoph Hellwig 已提交
2537

2538
	ret = -EPERM;
2539
	if (!capable(CAP_SYS_ADMIN))
2540
		goto out;
2541

2542 2543
	ret = -EINPROGRESS;
	if (file->private_data)
C
Christoph Hellwig 已提交
2544
		goto out;
2545

L
Li Zefan 已提交
2546 2547 2548 2549
	ret = -EROFS;
	if (btrfs_root_readonly(root))
		goto out;

Y
Yan Zheng 已提交
2550 2551 2552 2553
	ret = mnt_want_write(file->f_path.mnt);
	if (ret)
		goto out;

J
Josef Bacik 已提交
2554
	atomic_inc(&root->fs_info->open_ioctl_trans);
2555

2556
	ret = -ENOMEM;
2557
	trans = btrfs_start_ioctl_transaction(root);
2558
	if (IS_ERR(trans))
2559 2560 2561 2562 2563 2564
		goto out_drop;

	file->private_data = trans;
	return 0;

out_drop:
J
Josef Bacik 已提交
2565
	atomic_dec(&root->fs_info->open_ioctl_trans);
2566
	mnt_drop_write(file->f_path.mnt);
C
Christoph Hellwig 已提交
2567 2568 2569 2570
out:
	return ret;
}

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
static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_root *new_root;
	struct btrfs_dir_item *di;
	struct btrfs_trans_handle *trans;
	struct btrfs_path *path;
	struct btrfs_key location;
	struct btrfs_disk_key disk_key;
	struct btrfs_super_block *disk_super;
	u64 features;
	u64 objectid = 0;
	u64 dir_id;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (copy_from_user(&objectid, argp, sizeof(objectid)))
		return -EFAULT;

	if (!objectid)
		objectid = root->root_key.objectid;

	location.objectid = objectid;
	location.type = BTRFS_ROOT_ITEM_KEY;
	location.offset = (u64)-1;

	new_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
	if (IS_ERR(new_root))
		return PTR_ERR(new_root);

	if (btrfs_root_refs(&new_root->root_item) == 0)
		return -ENOENT;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	path->leave_spinning = 1;

	trans = btrfs_start_transaction(root, 1);
2612
	if (IS_ERR(trans)) {
2613
		btrfs_free_path(path);
2614
		return PTR_ERR(trans);
2615 2616
	}

2617
	dir_id = btrfs_super_root_dir(root->fs_info->super_copy);
2618 2619
	di = btrfs_lookup_dir_item(trans, root->fs_info->tree_root, path,
				   dir_id, "default", 7, 1);
2620
	if (IS_ERR_OR_NULL(di)) {
2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632
		btrfs_free_path(path);
		btrfs_end_transaction(trans, root);
		printk(KERN_ERR "Umm, you don't have the default dir item, "
		       "this isn't going to work\n");
		return -ENOENT;
	}

	btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key);
	btrfs_set_dir_item_key(path->nodes[0], di, &disk_key);
	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_free_path(path);

2633
	disk_super = root->fs_info->super_copy;
2634 2635 2636 2637 2638 2639 2640 2641 2642 2643
	features = btrfs_super_incompat_flags(disk_super);
	if (!(features & BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL)) {
		features |= BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL;
		btrfs_set_super_incompat_flags(disk_super, features);
	}
	btrfs_end_transaction(trans, root);

	return 0;
}

2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659
static void get_block_group_info(struct list_head *groups_list,
				 struct btrfs_ioctl_space_info *space)
{
	struct btrfs_block_group_cache *block_group;

	space->total_bytes = 0;
	space->used_bytes = 0;
	space->flags = 0;
	list_for_each_entry(block_group, groups_list, list) {
		space->flags = block_group->flags;
		space->total_bytes += block_group->key.offset;
		space->used_bytes +=
			btrfs_block_group_used(&block_group->item);
	}
}

J
Josef Bacik 已提交
2660 2661 2662 2663 2664
long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
{
	struct btrfs_ioctl_space_args space_args;
	struct btrfs_ioctl_space_info space;
	struct btrfs_ioctl_space_info *dest;
2665
	struct btrfs_ioctl_space_info *dest_orig;
2666
	struct btrfs_ioctl_space_info __user *user_dest;
J
Josef Bacik 已提交
2667
	struct btrfs_space_info *info;
2668 2669 2670 2671 2672
	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
		       BTRFS_BLOCK_GROUP_SYSTEM,
		       BTRFS_BLOCK_GROUP_METADATA,
		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
	int num_types = 4;
2673
	int alloc_size;
J
Josef Bacik 已提交
2674
	int ret = 0;
2675
	u64 slot_count = 0;
2676
	int i, c;
J
Josef Bacik 已提交
2677 2678 2679 2680 2681 2682

	if (copy_from_user(&space_args,
			   (struct btrfs_ioctl_space_args __user *)arg,
			   sizeof(space_args)))
		return -EFAULT;

2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706
	for (i = 0; i < num_types; i++) {
		struct btrfs_space_info *tmp;

		info = NULL;
		rcu_read_lock();
		list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
					list) {
			if (tmp->flags == types[i]) {
				info = tmp;
				break;
			}
		}
		rcu_read_unlock();

		if (!info)
			continue;

		down_read(&info->groups_sem);
		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
			if (!list_empty(&info->block_groups[c]))
				slot_count++;
		}
		up_read(&info->groups_sem);
	}
2707 2708 2709 2710 2711 2712

	/* space_slots == 0 means they are asking for a count */
	if (space_args.space_slots == 0) {
		space_args.total_spaces = slot_count;
		goto out;
	}
2713

2714
	slot_count = min_t(u64, space_args.space_slots, slot_count);
2715

2716
	alloc_size = sizeof(*dest) * slot_count;
2717

2718 2719 2720 2721 2722 2723
	/* we generally have at most 6 or so space infos, one for each raid
	 * level.  So, a whole page should be more than enough for everyone
	 */
	if (alloc_size > PAGE_CACHE_SIZE)
		return -ENOMEM;

J
Josef Bacik 已提交
2724
	space_args.total_spaces = 0;
2725 2726 2727 2728
	dest = kmalloc(alloc_size, GFP_NOFS);
	if (!dest)
		return -ENOMEM;
	dest_orig = dest;
J
Josef Bacik 已提交
2729

2730
	/* now we have a buffer to copy into */
2731 2732 2733
	for (i = 0; i < num_types; i++) {
		struct btrfs_space_info *tmp;

2734 2735 2736
		if (!slot_count)
			break;

2737 2738 2739 2740 2741 2742 2743 2744 2745 2746
		info = NULL;
		rcu_read_lock();
		list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
					list) {
			if (tmp->flags == types[i]) {
				info = tmp;
				break;
			}
		}
		rcu_read_unlock();
2747

2748 2749 2750 2751 2752 2753 2754 2755 2756 2757
		if (!info)
			continue;
		down_read(&info->groups_sem);
		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
			if (!list_empty(&info->block_groups[c])) {
				get_block_group_info(&info->block_groups[c],
						     &space);
				memcpy(dest, &space, sizeof(space));
				dest++;
				space_args.total_spaces++;
2758
				slot_count--;
2759
			}
2760 2761
			if (!slot_count)
				break;
2762 2763
		}
		up_read(&info->groups_sem);
J
Josef Bacik 已提交
2764 2765
	}

2766 2767 2768 2769 2770 2771 2772 2773 2774
	user_dest = (struct btrfs_ioctl_space_info *)
		(arg + sizeof(struct btrfs_ioctl_space_args));

	if (copy_to_user(user_dest, dest_orig, alloc_size))
		ret = -EFAULT;

	kfree(dest_orig);
out:
	if (ret == 0 && copy_to_user(arg, &space_args, sizeof(space_args)))
J
Josef Bacik 已提交
2775 2776 2777 2778 2779
		ret = -EFAULT;

	return ret;
}

C
Christoph Hellwig 已提交
2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792
/*
 * there are many ways the trans_start and trans_end ioctls can lead
 * to deadlocks.  They should only be used by applications that
 * basically own the machine, and have a very in depth understanding
 * of all the possible deadlocks and enospc problems.
 */
long btrfs_ioctl_trans_end(struct file *file)
{
	struct inode *inode = fdentry(file)->d_inode;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;

	trans = file->private_data;
2793 2794
	if (!trans)
		return -EINVAL;
C
Christoph Hellwig 已提交
2795
	file->private_data = NULL;
2796

2797 2798
	btrfs_end_transaction(trans, root);

J
Josef Bacik 已提交
2799
	atomic_dec(&root->fs_info->open_ioctl_trans);
2800

2801
	mnt_drop_write(file->f_path.mnt);
2802
	return 0;
C
Christoph Hellwig 已提交
2803 2804
}

2805 2806 2807 2808 2809
static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp)
{
	struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root;
	struct btrfs_trans_handle *trans;
	u64 transid;
T
Tsutomu Itoh 已提交
2810
	int ret;
2811 2812

	trans = btrfs_start_transaction(root, 0);
2813 2814
	if (IS_ERR(trans))
		return PTR_ERR(trans);
2815
	transid = trans->transid;
T
Tsutomu Itoh 已提交
2816
	ret = btrfs_commit_transaction_async(trans, root, 0);
2817 2818
	if (ret) {
		btrfs_end_transaction(trans, root);
T
Tsutomu Itoh 已提交
2819
		return ret;
2820
	}
2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841

	if (argp)
		if (copy_to_user(argp, &transid, sizeof(transid)))
			return -EFAULT;
	return 0;
}

static noinline long btrfs_ioctl_wait_sync(struct file *file, void __user *argp)
{
	struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root;
	u64 transid;

	if (argp) {
		if (copy_from_user(&transid, argp, sizeof(transid)))
			return -EFAULT;
	} else {
		transid = 0;  /* current trans */
	}
	return btrfs_wait_for_commit(root, transid);
}

J
Jan Schmidt 已提交
2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854
static long btrfs_ioctl_scrub(struct btrfs_root *root, void __user *arg)
{
	int ret;
	struct btrfs_ioctl_scrub_args *sa;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	sa = memdup_user(arg, sizeof(*sa));
	if (IS_ERR(sa))
		return PTR_ERR(sa);

	ret = btrfs_scrub_dev(root, sa->devid, sa->start, sa->end,
A
Arne Jansen 已提交
2855
			      &sa->progress, sa->flags & BTRFS_SCRUB_READONLY);
J
Jan Schmidt 已提交
2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893

	if (copy_to_user(arg, sa, sizeof(*sa)))
		ret = -EFAULT;

	kfree(sa);
	return ret;
}

static long btrfs_ioctl_scrub_cancel(struct btrfs_root *root, void __user *arg)
{
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	return btrfs_scrub_cancel(root);
}

static long btrfs_ioctl_scrub_progress(struct btrfs_root *root,
				       void __user *arg)
{
	struct btrfs_ioctl_scrub_args *sa;
	int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	sa = memdup_user(arg, sizeof(*sa));
	if (IS_ERR(sa))
		return PTR_ERR(sa);

	ret = btrfs_scrub_progress(root, sa->devid, &sa->progress);

	if (copy_to_user(arg, sa, sizeof(*sa)))
		ret = -EFAULT;

	kfree(sa);
	return ret;
}

2894 2895 2896 2897
static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
{
	int ret = 0;
	int i;
2898
	u64 rel_ptr;
2899
	int size;
2900
	struct btrfs_ioctl_ino_path_args *ipa = NULL;
2901 2902 2903 2904 2905 2906 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 2932
	struct inode_fs_paths *ipath = NULL;
	struct btrfs_path *path;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	ipa = memdup_user(arg, sizeof(*ipa));
	if (IS_ERR(ipa)) {
		ret = PTR_ERR(ipa);
		ipa = NULL;
		goto out;
	}

	size = min_t(u32, ipa->size, 4096);
	ipath = init_ipath(size, root, path);
	if (IS_ERR(ipath)) {
		ret = PTR_ERR(ipath);
		ipath = NULL;
		goto out;
	}

	ret = paths_from_inode(ipa->inum, ipath);
	if (ret < 0)
		goto out;

	for (i = 0; i < ipath->fspath->elem_cnt; ++i) {
2933 2934
		rel_ptr = ipath->fspath->val[i] -
			  (u64)(unsigned long)ipath->fspath->val;
2935
		ipath->fspath->val[i] = rel_ptr;
2936 2937
	}

2938 2939
	ret = copy_to_user((void *)(unsigned long)ipa->fspath,
			   (void *)(unsigned long)ipath->fspath, size);
2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021
	if (ret) {
		ret = -EFAULT;
		goto out;
	}

out:
	btrfs_free_path(path);
	free_ipath(ipath);
	kfree(ipa);

	return ret;
}

static int build_ino_list(u64 inum, u64 offset, u64 root, void *ctx)
{
	struct btrfs_data_container *inodes = ctx;
	const size_t c = 3 * sizeof(u64);

	if (inodes->bytes_left >= c) {
		inodes->bytes_left -= c;
		inodes->val[inodes->elem_cnt] = inum;
		inodes->val[inodes->elem_cnt + 1] = offset;
		inodes->val[inodes->elem_cnt + 2] = root;
		inodes->elem_cnt += 3;
	} else {
		inodes->bytes_missing += c - inodes->bytes_left;
		inodes->bytes_left = 0;
		inodes->elem_missed += 3;
	}

	return 0;
}

static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
					void __user *arg)
{
	int ret = 0;
	int size;
	u64 extent_offset;
	struct btrfs_ioctl_logical_ino_args *loi;
	struct btrfs_data_container *inodes = NULL;
	struct btrfs_path *path = NULL;
	struct btrfs_key key;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	loi = memdup_user(arg, sizeof(*loi));
	if (IS_ERR(loi)) {
		ret = PTR_ERR(loi);
		loi = NULL;
		goto out;
	}

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	size = min_t(u32, loi->size, 4096);
	inodes = init_data_container(size);
	if (IS_ERR(inodes)) {
		ret = PTR_ERR(inodes);
		inodes = NULL;
		goto out;
	}

	ret = extent_from_logical(root->fs_info, loi->logical, path, &key);

	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
		ret = -ENOENT;
	if (ret < 0)
		goto out;

	extent_offset = loi->logical - key.objectid;
	ret = iterate_extent_inodes(root->fs_info, path, key.objectid,
					extent_offset, build_ino_list, inodes);

	if (ret < 0)
		goto out;

3022 3023
	ret = copy_to_user((void *)(unsigned long)loi->inodes,
			   (void *)(unsigned long)inodes, size);
3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034
	if (ret)
		ret = -EFAULT;

out:
	btrfs_free_path(path);
	kfree(inodes);
	kfree(loi);

	return ret;
}

C
Christoph Hellwig 已提交
3035 3036 3037 3038
long btrfs_ioctl(struct file *file, unsigned int
		cmd, unsigned long arg)
{
	struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
3039
	void __user *argp = (void __user *)arg;
C
Christoph Hellwig 已提交
3040 3041

	switch (cmd) {
3042 3043 3044 3045 3046 3047
	case FS_IOC_GETFLAGS:
		return btrfs_ioctl_getflags(file, argp);
	case FS_IOC_SETFLAGS:
		return btrfs_ioctl_setflags(file, argp);
	case FS_IOC_GETVERSION:
		return btrfs_ioctl_getversion(file, argp);
3048 3049
	case FITRIM:
		return btrfs_ioctl_fitrim(file, argp);
C
Christoph Hellwig 已提交
3050
	case BTRFS_IOC_SNAP_CREATE:
3051
		return btrfs_ioctl_snap_create(file, argp, 0);
3052
	case BTRFS_IOC_SNAP_CREATE_V2:
3053
		return btrfs_ioctl_snap_create_v2(file, argp, 0);
3054
	case BTRFS_IOC_SUBVOL_CREATE:
3055
		return btrfs_ioctl_snap_create(file, argp, 1);
3056 3057
	case BTRFS_IOC_SNAP_DESTROY:
		return btrfs_ioctl_snap_destroy(file, argp);
3058 3059 3060 3061
	case BTRFS_IOC_SUBVOL_GETFLAGS:
		return btrfs_ioctl_subvol_getflags(file, argp);
	case BTRFS_IOC_SUBVOL_SETFLAGS:
		return btrfs_ioctl_subvol_setflags(file, argp);
3062 3063
	case BTRFS_IOC_DEFAULT_SUBVOL:
		return btrfs_ioctl_default_subvol(file, argp);
C
Christoph Hellwig 已提交
3064
	case BTRFS_IOC_DEFRAG:
C
Chris Mason 已提交
3065 3066 3067
		return btrfs_ioctl_defrag(file, NULL);
	case BTRFS_IOC_DEFRAG_RANGE:
		return btrfs_ioctl_defrag(file, argp);
C
Christoph Hellwig 已提交
3068
	case BTRFS_IOC_RESIZE:
3069
		return btrfs_ioctl_resize(root, argp);
C
Christoph Hellwig 已提交
3070
	case BTRFS_IOC_ADD_DEV:
3071
		return btrfs_ioctl_add_dev(root, argp);
C
Christoph Hellwig 已提交
3072
	case BTRFS_IOC_RM_DEV:
3073
		return btrfs_ioctl_rm_dev(root, argp);
J
Jan Schmidt 已提交
3074 3075 3076 3077
	case BTRFS_IOC_FS_INFO:
		return btrfs_ioctl_fs_info(root, argp);
	case BTRFS_IOC_DEV_INFO:
		return btrfs_ioctl_dev_info(root, argp);
C
Christoph Hellwig 已提交
3078 3079 3080
	case BTRFS_IOC_BALANCE:
		return btrfs_balance(root->fs_info->dev_root);
	case BTRFS_IOC_CLONE:
3081 3082
		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
	case BTRFS_IOC_CLONE_RANGE:
3083
		return btrfs_ioctl_clone_range(file, argp);
C
Christoph Hellwig 已提交
3084 3085 3086 3087
	case BTRFS_IOC_TRANS_START:
		return btrfs_ioctl_trans_start(file);
	case BTRFS_IOC_TRANS_END:
		return btrfs_ioctl_trans_end(file);
3088 3089 3090 3091
	case BTRFS_IOC_TREE_SEARCH:
		return btrfs_ioctl_tree_search(file, argp);
	case BTRFS_IOC_INO_LOOKUP:
		return btrfs_ioctl_ino_lookup(file, argp);
3092 3093 3094 3095
	case BTRFS_IOC_INO_PATHS:
		return btrfs_ioctl_ino_to_path(root, argp);
	case BTRFS_IOC_LOGICAL_INO:
		return btrfs_ioctl_logical_to_ino(root, argp);
J
Josef Bacik 已提交
3096 3097
	case BTRFS_IOC_SPACE_INFO:
		return btrfs_ioctl_space_info(root, argp);
C
Christoph Hellwig 已提交
3098 3099 3100
	case BTRFS_IOC_SYNC:
		btrfs_sync_fs(file->f_dentry->d_sb, 1);
		return 0;
3101 3102 3103 3104
	case BTRFS_IOC_START_SYNC:
		return btrfs_ioctl_start_sync(file, argp);
	case BTRFS_IOC_WAIT_SYNC:
		return btrfs_ioctl_wait_sync(file, argp);
J
Jan Schmidt 已提交
3105 3106 3107 3108 3109 3110
	case BTRFS_IOC_SCRUB:
		return btrfs_ioctl_scrub(root, argp);
	case BTRFS_IOC_SCRUB_CANCEL:
		return btrfs_ioctl_scrub_cancel(root, argp);
	case BTRFS_IOC_SCRUB_PROGRESS:
		return btrfs_ioctl_scrub_progress(root, argp);
C
Christoph Hellwig 已提交
3111 3112 3113 3114
	}

	return -ENOTTY;
}