renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-30 08:04:13 +08:00
Code
f1de968376
linux-next/fs/btrfs/ioctl.c
Filipe David Borba Manana 63541927c8 Btrfs: add support for inode properties 
This change adds infrastructure to allow for generic properties for
inodes. Properties are name/value pairs that can be associated with
inodes for different purposes. They are stored as xattrs with the
prefix "btrfs."

Properties can be inherited - this means when a directory inode has
inheritable properties set, these are added to new inodes created
under that directory. Further, subvolumes can also have properties
associated with them, and they can be inherited from their parent
subvolume. Naturally, directory properties have priority over subvolume
properties (in practice a subvolume property is just a regular
property associated with the root inode, objectid 256, of the
subvolume's fs tree).

This change also adds one specific property implementation, named
"compression", whose values can be "lzo" or "zlib" and it's an
inheritable property.

The corresponding changes to btrfs-progs were also implemented.
A patch with xfstests for this feature will follow once there's
agreement on this change/feature.

Further, the script at the bottom of this commit message was used to
do some benchmarks to measure any performance penalties of this feature.

Basically the tests correspond to:

Test 1 - create a filesystem and mount it with compress-force=lzo,
then sequentially create N files of 64Kb each, measure how long it took
to create the files, unmount the filesystem, mount the filesystem and
perform an 'ls -lha' against the test directory holding the N files, and
report the time the command took.

Test 2 - create a filesystem and don't use any compression option when
mounting it - instead set the compression property of the subvolume's
root to 'lzo'. Then create N files of 64Kb, and report the time it took.
The unmount the filesystem, mount it again and perform an 'ls -lha' like
in the former test. This means every single file ends up with a property
(xattr) associated to it.

Test 3 - same as test 2, but uses 4 properties - 3 are duplicates of the
compression property, have no real effect other than adding more work
when inheriting properties and taking more btree leaf space.

Test 4 - same as test 3 but with 10 properties per file.

Results (in seconds, and averages of 5 runs each), for different N
numbers of files follow.

* Without properties (test 1)

                    file creation time        ls -lha time
10 000 files              3.49                   0.76
100 000 files            47.19                   8.37
1 000 000 files         518.51                 107.06

* With 1 property (compression property set to lzo - test 2)

                    file creation time        ls -lha time
10 000 files              3.63                    0.93
100 000 files            48.56                    9.74
1 000 000 files         537.72                  125.11

* With 4 properties (test 3)

                    file creation time        ls -lha time
10 000 files              3.94                    1.20
100 000 files            52.14                   11.48
1 000 000 files         572.70                  142.13

* With 10 properties (test 4)

                    file creation time        ls -lha time
10 000 files              4.61                    1.35
100 000 files            58.86                   13.83
1 000 000 files         656.01                  177.61

The increased latencies with properties are essencialy because of:

*) When creating an inode, we now synchronously write 1 more item
   (an xattr item) for each property inherited from the parent dir
   (or subvolume). This could be done in an asynchronous way such
   as we do for dir intex items (delayed-inode.c), which could help
   reduce the file creation latency;

*) With properties, we now have larger fs trees. For this particular
   test each xattr item uses 75 bytes of leaf space in the fs tree.
   This could be less by using a new item for xattr items, instead of
   the current btrfs_dir_item, since we could cut the 'location' and
   'type' fields (saving 18 bytes) and maybe 'transid' too (saving a
   total of 26 bytes per xattr item) from the btrfs_dir_item type.

Also tried batching the xattr insertions (ignoring proper hash
collision handling, since it didn't exist) when creating files that
inherit properties from their parent inode/subvolume, but the end
results were (surprisingly) essentially the same.

Test script:

$ cat test.pl
  #!/usr/bin/perl -w

  use strict;
  use Time::HiRes qw(time);
  use constant NUM_FILES => 10_000;
  use constant FILE_SIZES => (64 * 1024);
  use constant DEV => '/dev/sdb4';
  use constant MNT_POINT => '/home/fdmanana/btrfs-tests/dev';
  use constant TEST_DIR => (MNT_POINT . '/testdir');

  system("mkfs.btrfs", "-l", "16384", "-f", DEV) == 0 or die "mkfs.btrfs failed!";

  # following line for testing without properties
  #system("mount", "-o", "compress-force=lzo", DEV, MNT_POINT) == 0 or die "mount failed!";

  # following 2 lines for testing with properties
  system("mount", DEV, MNT_POINT) == 0 or die "mount failed!";
  system("btrfs", "prop", "set", MNT_POINT, "compression", "lzo") == 0 or die "set prop failed!";

  system("mkdir", TEST_DIR) == 0 or die "mkdir failed!";
  my ($t1, $t2);

  $t1 = time();
  for (my $i = 1; $i <= NUM_FILES; $i++) {
      my $p = TEST_DIR . '/file_' . $i;
      open(my $f, '>', $p) or die "Error opening file!";
      $f->autoflush(1);
      for (my $j = 0; $j < FILE_SIZES; $j += 4096) {
          print $f ('A' x 4096) or die "Error writing to file!";
      }
      close($f);
  }
  $t2 = time();
  print "Time to create " . NUM_FILES . ": " . ($t2 - $t1) . " seconds.\n";
  system("umount", DEV) == 0 or die "umount failed!";
  system("mount", DEV, MNT_POINT) == 0 or die "mount failed!";

  $t1 = time();
  system("bash -c 'ls -lha " . TEST_DIR . " > /dev/null'") == 0 or die "ls failed!";
  $t2 = time();
  print "Time to ls -lha all files: " . ($t2 - $t1) . " seconds.\n";
  system("umount", DEV) == 0 or die "umount failed!";

Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-01-28 13:20:24 -08:00

4832 lines
114 KiB
C
Raw Blame History

/*
* 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>
#include <linux/fsnotify.h>
#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>
#include <linux/mount.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/bit_spinlock.h>
#include <linux/security.h>
#include <linux/xattr.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/uuid.h>
#include <linux/btrfs.h>
#include <linux/uaccess.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "volumes.h"
#include "locking.h"
#include "inode-map.h"
#include "backref.h"
#include "rcu-string.h"
#include "send.h"
#include "dev-replace.h"
#include "props.h"
#include "sysfs.h"
static int btrfs_clone(struct inode *src, struct inode *inode,
u64 off, u64 olen, u64 olen_aligned, u64 destoff);
/* 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;
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;
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.
*
* Currently only the compression flags and the cow flags are inherited.
*/
void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
{
unsigned int flags;
if (!dir)
return;
flags = BTRFS_I(dir)->flags;
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;
if (S_ISREG(inode->i_mode))
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
}
btrfs_update_iflags(inode);
}
static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
{
struct btrfs_inode *ip = BTRFS_I(file_inode(file));
unsigned int flags = btrfs_flags_to_ioctl(ip->flags);
if (copy_to_user(arg, &flags, sizeof(flags)))
return -EFAULT;
return 0;
}
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 | \
FS_NOCOMP_FL | FS_COMPR_FL |
FS_NOCOW_FL))
return -EOPNOTSUPP;
if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
return -EINVAL;
return 0;
}
static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct btrfs_inode *ip = BTRFS_I(inode);
struct btrfs_root *root = ip->root;
struct btrfs_trans_handle *trans;
unsigned int flags, oldflags;
int ret;
u64 ip_oldflags;
unsigned int i_oldflags;
umode_t mode;
if (btrfs_root_readonly(root))
return -EROFS;
if (copy_from_user(&flags, arg, sizeof(flags)))
return -EFAULT;
ret = check_flags(flags);
if (ret)
return ret;
if (!inode_owner_or_capable(inode))
return -EACCES;
ret = mnt_want_write_file(file);
if (ret)
return ret;
mutex_lock(&inode->i_mutex);
ip_oldflags = ip->flags;
i_oldflags = inode->i_flags;
mode = inode->i_mode;
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;
}
}
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;
if (flags & FS_NOCOW_FL) {
if (S_ISREG(mode)) {
/*
* It's safe to turn csums off here, no extents exist.
* Otherwise we want the flag to reflect the real COW
* status of the file and will not set it.
*/
if (inode->i_size == 0)
ip->flags |= BTRFS_INODE_NODATACOW
| BTRFS_INODE_NODATASUM;
} else {
ip->flags |= BTRFS_INODE_NODATACOW;
}
} else {
/*
* Revert back under same assuptions as above
*/
if (S_ISREG(mode)) {
if (inode->i_size == 0)
ip->flags &= ~(BTRFS_INODE_NODATACOW
| BTRFS_INODE_NODATASUM);
} else {
ip->flags &= ~BTRFS_INODE_NODATACOW;
}
}
/*
* 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;
ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
if (ret && ret != -ENODATA)
goto out_drop;
} else if (flags & FS_COMPR_FL) {
const char *comp;
ip->flags |= BTRFS_INODE_COMPRESS;
ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
if (root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
comp = "lzo";
else
comp = "zlib";
ret = btrfs_set_prop(inode, "btrfs.compression",
comp, strlen(comp), 0);
if (ret)
goto out_drop;
} else {
ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_drop;
}
btrfs_update_iflags(inode);
inode_inc_iversion(inode);
inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
out_drop:
if (ret) {
ip->flags = ip_oldflags;
inode->i_flags = i_oldflags;
}
out_unlock:
mutex_unlock(&inode->i_mutex);
mnt_drop_write_file(file);
return ret;
}
static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
struct inode *inode = file_inode(file);
return put_user(inode->i_generation, arg);
}
static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
{
struct btrfs_fs_info *fs_info = btrfs_sb(file_inode(file)->i_sb);
struct btrfs_device *device;
struct request_queue *q;
struct fstrim_range range;
u64 minlen = ULLONG_MAX;
u64 num_devices = 0;
u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
dev_list) {
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);
}
}
rcu_read_unlock();
if (!num_devices)
return -EOPNOTSUPP;
if (copy_from_user(&range, arg, sizeof(range)))
return -EFAULT;
if (range.start > total_bytes ||
range.len < fs_info->sb->s_blocksize)
return -EINVAL;
range.len = min(range.len, total_bytes - range.start);
range.minlen = max(range.minlen, minlen);
ret = btrfs_trim_fs(fs_info->tree_root, &range);
if (ret < 0)
return ret;
if (copy_to_user(arg, &range, sizeof(range)))
return -EFAULT;
return 0;
}
int btrfs_is_empty_uuid(u8 *uuid)
{
int i;
for (i = 0; i < BTRFS_UUID_SIZE; i++) {
if (uuid[i])
return 0;
}
return 1;
}
static noinline int create_subvol(struct inode *dir,
struct dentry *dentry,
char *name, int namelen,
u64 *async_transid,
struct btrfs_qgroup_inherit *inherit)
{
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;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *new_root;
struct btrfs_block_rsv block_rsv;
struct timespec cur_time = CURRENT_TIME;
struct inode *inode;
int ret;
int err;
u64 objectid;
u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
u64 index = 0;
u64 qgroup_reserved;
uuid_le new_uuid;
ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
if (ret)
return ret;
btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
* The same as the snapshot creation, please see the comment
* of create_snapshot().
*/
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
8, &qgroup_reserved, false);
if (ret)
return ret;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
ret = btrfs_qgroup_inherit(trans, root->fs_info, 0, objectid, inherit);
if (ret)
goto fail;
leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
0, objectid, NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
goto fail;
}
memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
btrfs_set_header_bytenr(leaf, leaf->start);
btrfs_set_header_generation(leaf, trans->transid);
btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
btrfs_set_header_owner(leaf, objectid);
write_extent_buffer(leaf, root->fs_info->fsid, btrfs_header_fsid(),
BTRFS_FSID_SIZE);
write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
btrfs_header_chunk_tree_uuid(leaf),
BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
memset(&root_item, 0, sizeof(root_item));
inode_item = &root_item.inode;
btrfs_set_stack_inode_generation(inode_item, 1);
btrfs_set_stack_inode_size(inode_item, 3);
btrfs_set_stack_inode_nlink(inode_item, 1);
btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
btrfs_set_root_flags(&root_item, 0);
btrfs_set_root_limit(&root_item, 0);
btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT);
btrfs_set_root_bytenr(&root_item, leaf->start);
btrfs_set_root_generation(&root_item, trans->transid);
btrfs_set_root_level(&root_item, 0);
btrfs_set_root_refs(&root_item, 1);
btrfs_set_root_used(&root_item, leaf->len);
btrfs_set_root_last_snapshot(&root_item, 0);
btrfs_set_root_generation_v2(&root_item,
btrfs_root_generation(&root_item));
uuid_le_gen(&new_uuid);
memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec);
btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec);
root_item.ctime = root_item.otime;
btrfs_set_root_ctransid(&root_item, trans->transid);
btrfs_set_root_otransid(&root_item, trans->transid);
btrfs_tree_unlock(leaf);
free_extent_buffer(leaf);
leaf = NULL;
btrfs_set_root_dirid(&root_item, new_dirid);
key.objectid = objectid;
key.offset = 0;
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;
key.offset = (u64)-1;
new_root = btrfs_read_fs_root_no_name(root->fs_info, &key);
if (IS_ERR(new_root)) {
btrfs_abort_transaction(trans, root, PTR_ERR(new_root));
ret = PTR_ERR(new_root);
goto fail;
}
btrfs_record_root_in_trans(trans, new_root);
ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid);
if (ret) {
/* We potentially lose an unused inode item here */
btrfs_abort_transaction(trans, root, ret);
goto fail;
}
/*
* insert the directory item
*/
ret = btrfs_set_inode_index(dir, &index);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto fail;
}
ret = btrfs_insert_dir_item(trans, root,
name, namelen, dir, &key,
BTRFS_FT_DIR, index);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto fail;
}
btrfs_i_size_write(dir, dir->i_size + namelen * 2);
ret = btrfs_update_inode(trans, root, dir);
BUG_ON(ret);
ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
objectid, root->root_key.objectid,
btrfs_ino(dir), index, name, namelen);
BUG_ON(ret);
ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
objectid);
if (ret)
btrfs_abort_transaction(trans, root, ret);
fail:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
if (async_transid) {
*async_transid = trans->transid;
err = btrfs_commit_transaction_async(trans, root, 1);
if (err)
err = btrfs_commit_transaction(trans, root);
} else {
err = btrfs_commit_transaction(trans, root);
}
if (err && !ret)
ret = err;
if (!ret) {
inode = btrfs_lookup_dentry(dir, dentry);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto out;
}
d_instantiate(dentry, inode);
}
out:
btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
return ret;
}
static int create_snapshot(struct btrfs_root *root, struct inode *dir,
struct dentry *dentry, char *name, int namelen,
u64 *async_transid, bool readonly,
struct btrfs_qgroup_inherit *inherit)
{
struct inode *inode;
struct btrfs_pending_snapshot *pending_snapshot;
struct btrfs_trans_handle *trans;
int ret;
if (!root->ref_cows)
return -EINVAL;
ret = btrfs_start_delalloc_inodes(root, 0);
if (ret)
return ret;
btrfs_wait_ordered_extents(root, -1);
pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
if (!pending_snapshot)
return -ENOMEM;
btrfs_init_block_rsv(&pending_snapshot->block_rsv,
BTRFS_BLOCK_RSV_TEMP);
/*
* 1 - parent dir inode
* 2 - dir entries
* 1 - root item
* 2 - root ref/backref
* 1 - root of snapshot
* 1 - UUID item
*/
ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
&pending_snapshot->block_rsv, 8,
&pending_snapshot->qgroup_reserved,
false);
if (ret)
goto out;
pending_snapshot->dentry = dentry;
pending_snapshot->root = root;
pending_snapshot->readonly = readonly;
pending_snapshot->dir = dir;
pending_snapshot->inherit = inherit;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto fail;
}
spin_lock(&root->fs_info->trans_lock);
list_add(&pending_snapshot->list,
&trans->transaction->pending_snapshots);
spin_unlock(&root->fs_info->trans_lock);
if (async_transid) {
*async_transid = trans->transid;
ret = btrfs_commit_transaction_async(trans,
root->fs_info->extent_root, 1);
if (ret)
ret = btrfs_commit_transaction(trans, root);
} else {
ret = btrfs_commit_transaction(trans,
root->fs_info->extent_root);
}
if (ret)
goto fail;
ret = pending_snapshot->error;
if (ret)
goto fail;
ret = btrfs_orphan_cleanup(pending_snapshot->snap);
if (ret)
goto fail;
inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto fail;
}
d_instantiate(dentry, inode);
ret = 0;
fail:
btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
&pending_snapshot->block_rsv,
pending_snapshot->qgroup_reserved);
out:
kfree(pending_snapshot);
return ret;
}
/* 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)
{
kuid_t fsuid = current_fsuid();
if (!(dir->i_mode & S_ISVTX))
return 0;
if (uid_eq(inode->i_uid, fsuid))
return 0;
if (uid_eq(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(dir, victim, AUDIT_TYPE_CHILD_DELETE);
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;
}
/* 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.
*/
static noinline int btrfs_mksubvol(struct path *parent,
char *name, int namelen,
struct btrfs_root *snap_src,
u64 *async_transid, bool readonly,
struct btrfs_qgroup_inherit *inherit)
{
struct inode *dir = parent->dentry->d_inode;
struct dentry *dentry;
int error;
error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
if (error == -EINTR)
return error;
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 = btrfs_may_create(dir, dentry);
if (error)
goto out_dput;
/*
* even if this name doesn't exist, we may get hash collisions.
* check for them now when we can safely fail
*/
error = btrfs_check_dir_item_collision(BTRFS_I(dir)->root,
dir->i_ino, name,
namelen);
if (error)
goto out_dput;
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;
if (snap_src) {
error = create_snapshot(snap_src, dir, dentry, name, namelen,
async_transid, readonly, inherit);
} else {
error = create_subvol(dir, dentry, name, namelen,
async_transid, inherit);
}
if (!error)
fsnotify_mkdir(dir, dentry);
out_up_read:
up_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
out_dput:
dput(dentry);
out_unlock:
mutex_unlock(&dir->i_mutex);
return error;
}
/*
* 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 extent_buffer *leaf;
struct btrfs_file_extent_item *extent;
int type;
int ret;
u64 ino = btrfs_ino(inode);
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
min_key.objectid = ino;
min_key.type = BTRFS_EXTENT_DATA_KEY;
min_key.offset = *off;
path->keep_locks = 1;
while (1) {
ret = btrfs_search_forward(root, &min_key, path, newer_than);
if (ret != 0)
goto none;
if (min_key.objectid != ino)
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;
}
static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
{
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_map *em;
u64 len = PAGE_CACHE_SIZE;
/*
* 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);
em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
unlock_extent(io_tree, start, start + len - 1);
if (IS_ERR(em))
return NULL;
}
return em;
}
static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
{
struct extent_map *next;
bool ret = true;
/* this is the last extent */
if (em->start + em->len >= i_size_read(inode))
return false;
next = defrag_lookup_extent(inode, em->start + em->len);
if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
ret = false;
free_extent_map(next);
return ret;
}
static int should_defrag_range(struct inode *inode, u64 start, int thresh,
u64 *last_len, u64 *skip, u64 *defrag_end,
int compress)
{
struct extent_map *em;
int ret = 1;
bool next_mergeable = true;
/*
* make sure that once we start defragging an extent, we keep on
* defragging it
*/
if (start < *defrag_end)
return 1;
*skip = 0;
em = defrag_lookup_extent(inode, start);
if (!em)
return 0;
/* this will cover holes, and inline extents */
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
ret = 0;
goto out;
}
next_mergeable = defrag_check_next_extent(inode, em);
/*
* we hit a real extent, if it is big or the next extent is not a
* real extent, don't bother defragging it
*/
if (!compress && (*last_len == 0 || *last_len >= thresh) &&
(em->len >= thresh || !next_mergeable))
ret = 0;
out:
/*
* 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;
}
/*
* 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)
{
unsigned long file_end;
u64 isize = i_size_read(inode);
u64 page_start;
u64 page_end;
u64 page_cnt;
int ret;
int i;
int i_done;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
struct extent_io_tree *tree;
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
if (!isize || start_index > file_end)
return 0;
page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
ret = btrfs_delalloc_reserve_space(inode,
page_cnt << PAGE_CACHE_SHIFT);
if (ret)
return ret;
i_done = 0;
tree = &BTRFS_I(inode)->io_tree;
/* step one, lock all the pages */
for (i = 0; i < page_cnt; i++) {
struct page *page;
again:
page = find_or_create_page(inode->i_mapping,
start_index + i, mask);
if (!page)
break;
page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
while (1) {
lock_extent(tree, page_start, page_end);
ordered = btrfs_lookup_ordered_extent(inode,
page_start);
unlock_extent(tree, page_start, page_end);
if (!ordered)
break;
unlock_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
btrfs_put_ordered_extent(ordered);
lock_page(page);
/*
* we unlocked the page above, so we need check if
* it was released or not.
*/
if (page->mapping != inode->i_mapping) {
unlock_page(page);
page_cache_release(page);
goto again;
}
}
if (!PageUptodate(page)) {
btrfs_readpage(NULL, page);
lock_page(page);
if (!PageUptodate(page)) {
unlock_page(page);
page_cache_release(page);
ret = -EIO;
break;
}
}
if (page->mapping != inode->i_mapping) {
unlock_page(page);
page_cache_release(page);
goto again;
}
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);
clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
&cached_state, GFP_NOFS);
if (i_done != page_cnt) {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(inode,
(page_cnt - i_done) << PAGE_CACHE_SHIFT);
}
set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
&cached_state, GFP_NOFS);
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, page_cnt << 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;
struct file_ra_state *ra = NULL;
unsigned long last_index;
u64 isize = i_size_read(inode);
u64 last_len = 0;
u64 skip = 0;
u64 defrag_end = 0;
u64 newer_off = range->start;
unsigned long i;
unsigned long ra_index = 0;
int ret;
int defrag_count = 0;
int compress_type = BTRFS_COMPRESS_ZLIB;
int extent_thresh = range->extent_thresh;
int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
int cluster = max_cluster;
u64 new_align = ~((u64)128 * 1024 - 1);
struct page **pages = NULL;
if (isize == 0)
return 0;
if (range->start >= isize)
return -EINVAL;
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;
}
if (extent_thresh == 0)
extent_thresh = 256 * 1024;
/*
* 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;
}
pages = kmalloc_array(max_cluster, sizeof(struct page *),
GFP_NOFS);
if (!pages) {
ret = -ENOMEM;
goto out_ra;
}
/* find the last page to defrag */
if (range->start + range->len > range->start) {
last_index = min_t(u64, isize - 1,
range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
} else {
last_index = (isize - 1) >> PAGE_CACHE_SHIFT;
}
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)
max_to_defrag = last_index + 1;
/*
* 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;
while (i <= last_index && defrag_count < max_to_defrag &&
(i < (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
PAGE_CACHE_SHIFT)) {
/*
* make sure we stop running if someone unmounts
* the FS
*/
if (!(inode->i_sb->s_flags & MS_ACTIVE))
break;
if (btrfs_defrag_cancelled(root->fs_info)) {
printk(KERN_DEBUG "BTRFS: defrag_file cancelled\n");
ret = -EAGAIN;
break;
}
if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
extent_thresh, &last_len, &skip,
&defrag_end, range->flags &
BTRFS_DEFRAG_RANGE_COMPRESS)) {
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;
}
if (!newer_than) {
cluster = (PAGE_CACHE_ALIGN(defrag_end) >>
PAGE_CACHE_SHIFT) - i;
cluster = min(cluster, max_cluster);
} else {
cluster = max_cluster;
}
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;
}
mutex_lock(&inode->i_mutex);
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
BTRFS_I(inode)->force_compress = compress_type;
ret = cluster_pages_for_defrag(inode, pages, i, cluster);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
goto out_ra;
}
defrag_count += ret;
balance_dirty_pages_ratelimited(inode->i_mapping);
mutex_unlock(&inode->i_mutex);
if (newer_than) {
if (newer_off == (u64)-1)
break;
if (ret > 0)
i += ret;
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;
}
} else {
if (ret > 0) {
i += ret;
last_len += ret << PAGE_CACHE_SHIFT;
} else {
i++;
last_len = 0;
}
}
}
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);
}
if (range->compress_type == BTRFS_COMPRESS_LZO) {
btrfs_set_fs_incompat(root->fs_info, COMPRESS_LZO);
}
ret = defrag_count;
out_ra:
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
mutex_lock(&inode->i_mutex);
BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
mutex_unlock(&inode->i_mutex);
}
if (!file)
kfree(ra);
kfree(pages);
return ret;
}
static noinline int btrfs_ioctl_resize(struct file *file,
void __user *arg)
{
u64 new_size;
u64 old_size;
u64 devid = 1;
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
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;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
mnt_drop_write_file(file);
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
mutex_lock(&root->fs_info->volume_mutex);
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
goto out;
}
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
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);
if (!devid) {
ret = -EINVAL;
goto out_free;
}
btrfs_info(root->fs_info, "resizing devid %llu", devid);
}
device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
if (!device) {
btrfs_info(root->fs_info, "resizer unable to find device %llu",
devid);
ret = -ENODEV;
goto out_free;
}
if (!device->writeable) {
btrfs_info(root->fs_info,
"resizer unable to apply on readonly device %llu",
devid);
ret = -EPERM;
goto out_free;
}
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++;
}
new_size = memparse(sizestr, NULL);
if (new_size == 0) {
ret = -EINVAL;
goto out_free;
}
}
if (device->is_tgtdev_for_dev_replace) {
ret = -EPERM;
goto out_free;
}
old_size = device->total_bytes;
if (mod < 0) {
if (new_size > old_size) {
ret = -EINVAL;
goto out_free;
}
new_size = old_size - new_size;
} else if (mod > 0) {
if (new_size > ULLONG_MAX - old_size) {
ret = -EINVAL;
goto out_free;
}
new_size = old_size + new_size;
}
if (new_size < 256 * 1024 * 1024) {
ret = -EINVAL;
goto out_free;
}
if (new_size > device->bdev->bd_inode->i_size) {
ret = -EFBIG;
goto out_free;
}
do_div(new_size, root->sectorsize);
new_size *= root->sectorsize;
printk_in_rcu(KERN_INFO "BTRFS: new size for %s is %llu\n",
rcu_str_deref(device->name), new_size);
if (new_size > old_size) {
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_free;
}
ret = btrfs_grow_device(trans, device, new_size);
btrfs_commit_transaction(trans, root);
} else if (new_size < old_size) {
ret = btrfs_shrink_device(device, new_size);
} /* equal, nothing need to do */
out_free:
kfree(vol_args);
out:
mutex_unlock(&root->fs_info->volume_mutex);
atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
mnt_drop_write_file(file);
return ret;
}
static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
char *name, unsigned long fd, int subvol,
u64 *transid, bool readonly,
struct btrfs_qgroup_inherit *inherit)
{
int namelen;
int ret = 0;
ret = mnt_want_write_file(file);
if (ret)
goto out;
namelen = strlen(name);
if (strchr(name, '/')) {
ret = -EINVAL;
goto out_drop_write;
}
if (name[0] == '.' &&
(namelen == 1 || (name[1] == '.' && namelen == 2))) {
ret = -EEXIST;
goto out_drop_write;
}
if (subvol) {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
NULL, transid, readonly, inherit);
} else {
struct fd src = fdget(fd);
struct inode *src_inode;
if (!src.file) {
ret = -EINVAL;
goto out_drop_write;
}
src_inode = file_inode(src.file);
if (src_inode->i_sb != file_inode(file)->i_sb) {
btrfs_info(BTRFS_I(src_inode)->root->fs_info,
"Snapshot src from another FS");
ret = -EINVAL;
} else {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
BTRFS_I(src_inode)->root,
transid, readonly, inherit);
}
fdput(src);
}
out_drop_write:
mnt_drop_write_file(file);
out:
return ret;
}
static noinline int btrfs_ioctl_snap_create(struct file *file,
void __user *arg, int subvol)
{
struct btrfs_ioctl_vol_args *vol_args;
int ret;
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';
ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
vol_args->fd, subvol,
NULL, false, NULL);
kfree(vol_args);
return ret;
}
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;
bool readonly = false;
struct btrfs_qgroup_inherit *inherit = NULL;
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';
if (vol_args->flags &
~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY |
BTRFS_SUBVOL_QGROUP_INHERIT)) {
ret = -EOPNOTSUPP;
goto out;
}
if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC)
ptr = &transid;
if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
readonly = true;
if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) {
if (vol_args->size > PAGE_CACHE_SIZE) {
ret = -EINVAL;
goto out;
}
inherit = memdup_user(vol_args->qgroup_inherit, vol_args->size);
if (IS_ERR(inherit)) {
ret = PTR_ERR(inherit);
goto out;
}
}
ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
vol_args->fd, subvol, ptr,
readonly, inherit);
if (ret == 0 && ptr &&
copy_to_user(arg +
offsetof(struct btrfs_ioctl_vol_args_v2,
transid), ptr, sizeof(*ptr)))
ret = -EFAULT;
out:
kfree(vol_args);
kfree(inherit);
return ret;
}
static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
void __user *arg)
{
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
u64 flags = 0;
if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
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 = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
u64 root_flags;
u64 flags;
int ret = 0;
ret = mnt_want_write_file(file);
if (ret)
goto out;
if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
ret = -EINVAL;
goto out_drop_write;
}
if (copy_from_user(&flags, arg, sizeof(flags))) {
ret = -EFAULT;
goto out_drop_write;
}
if (flags & BTRFS_SUBVOL_CREATE_ASYNC) {
ret = -EINVAL;
goto out_drop_write;
}
if (flags & ~BTRFS_SUBVOL_RDONLY) {
ret = -EOPNOTSUPP;
goto out_drop_write;
}
if (!inode_owner_or_capable(inode)) {
ret = -EACCES;
goto out_drop_write;
}
down_write(&root->fs_info->subvol_sem);
/* nothing to do */
if (!!(flags & BTRFS_SUBVOL_RDONLY) == btrfs_root_readonly(root))
goto out_drop_sem;
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 {
/*
* Block RO -> RW transition if this subvolume is involved in
* send
*/
spin_lock(&root->root_item_lock);
if (root->send_in_progress == 0) {
btrfs_set_root_flags(&root->root_item,
root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
spin_unlock(&root->root_item_lock);
} else {
spin_unlock(&root->root_item_lock);
btrfs_warn(root->fs_info,
"Attempt to set subvolume %llu read-write during send",
root->root_key.objectid);
ret = -EPERM;
goto out_drop_sem;
}
}
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_reset;
}
ret = btrfs_update_root(trans, root->fs_info->tree_root,
&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_drop_sem:
up_write(&root->fs_info->subvol_sem);
out_drop_write:
mnt_drop_write_file(file);
out:
return ret;
}
/*
* 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_dir_item *di;
struct btrfs_key key;
u64 dir_id;
int ret;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
/* Make sure this root isn't set as the default subvol */
dir_id = btrfs_super_root_dir(root->fs_info->super_copy);
di = btrfs_lookup_dir_item(NULL, root->fs_info->tree_root, path,
dir_id, "default", 7, 0);
if (di && !IS_ERR(di)) {
btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
if (key.objectid == root->root_key.objectid) {
ret = -ENOTEMPTY;
goto out;
}
btrfs_release_path(path);
}
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;
}
static noinline int key_in_sk(struct btrfs_key *key,
struct btrfs_ioctl_search_key *sk)
{
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)
return 0;
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)
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);
btrfs_item_key_to_cpu(leaf, key, i);
if (!key_in_sk(key, sk))
continue;
if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
item_len = 0;
if (sizeof(sh) + item_len + *sk_offset >
BTRFS_SEARCH_ARGS_BUFSIZE) {
ret = 1;
goto overflow;
}
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;
}
(*num_found)++;
if (*num_found >= sk->nr_items)
break;
}
advance_key:
ret = 0;
if (key->offset < (u64)-1 && key->offset < sk->max_offset)
key->offset++;
else if (key->type < (u8)-1 && key->type < sk->max_type) {
key->offset = 0;
key->type++;
} else if (key->objectid < (u64)-1 && key->objectid < sk->max_objectid) {
key->offset = 0;
key->type = 0;
key->objectid++;
} else
ret = 1;
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_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 "BTRFS: 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;
path->keep_locks = 1;
while (1) {
ret = btrfs_search_forward(root, &key, path, 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);
btrfs_release_path(path);
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;
args = memdup_user(argp, sizeof(*args));
if (IS_ERR(args))
return PTR_ERR(args);
inode = file_inode(file);
ret = search_ioctl(inode, args);
if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
ret = -EFAULT;
kfree(args);
return ret;
}
/*
* Search INODE_REFs to identify path name of 'dirid' directory
* in a 'tree_id' tree. and sets path name to 'name'.
*/
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;
char *ptr;
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;
ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX];
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 "BTRFS: could not find root %llu\n", tree_id);
ret = -ENOENT;
goto out;
}
key.objectid = dirid;
key.type = BTRFS_INODE_REF_KEY;
key.offset = (u64)-1;
while (1) {
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
else if (ret > 0) {
ret = btrfs_previous_item(root, path, dirid,
BTRFS_INODE_REF_KEY);
if (ret < 0)
goto out;
else if (ret > 0) {
ret = -ENOENT;
goto out;
}
}
l = path->nodes[0];
slot = path->slots[0];
btrfs_item_key_to_cpu(l, &key, slot);
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;
if (ptr < name) {
ret = -ENAMETOOLONG;
goto out;
}
*(ptr + len) = '/';
read_extent_buffer(l, ptr, (unsigned long)(iref + 1), len);
if (key.offset == BTRFS_FIRST_FREE_OBJECTID)
break;
btrfs_release_path(path);
key.objectid = key.offset;
key.offset = (u64)-1;
dirid = key.objectid;
}
memmove(name, ptr, total_len);
name[total_len] = '\0';
ret = 0;
out:
btrfs_free_path(path);
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;
args = memdup_user(argp, sizeof(*args));
if (IS_ERR(args))
return PTR_ERR(args);
inode = file_inode(file);
if (args->treeid == 0)
args->treeid = BTRFS_I(inode)->root->root_key.objectid;
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);
return ret;
}
static noinline int btrfs_ioctl_snap_destroy(struct file *file,
void __user *arg)
{
struct dentry *parent = file->f_path.dentry;
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;
struct btrfs_block_rsv block_rsv;
u64 qgroup_reserved;
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(file);
if (err)
goto out;
err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
if (err == -EINTR)
goto out_drop_write;
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;
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 user */
err = btrfs_may_delete(dir, dentry, 1);
if (err)
goto out_dput;
if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
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;
btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
* One for dir inode, two for dir entries, two for root
* ref/backref.
*/
err = btrfs_subvolume_reserve_metadata(root, &block_rsv,
5, &qgroup_reserved, true);
if (err)
goto out_up_write;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_release;
}
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
ret = btrfs_unlink_subvol(trans, root, dir,
dest->root_key.objectid,
dentry->d_name.name,
dentry->d_name.len);
if (ret) {
err = ret;
btrfs_abort_transaction(trans, root, ret);
goto out_end_trans;
}
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);
if (!xchg(&dest->orphan_item_inserted, 1)) {
ret = btrfs_insert_orphan_item(trans,
root->fs_info->tree_root,
dest->root_key.objectid);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
err = ret;
goto out_end_trans;
}
}
ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
dest->root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
dest->root_key.objectid);
if (ret && ret != -ENOENT) {
btrfs_abort_transaction(trans, root, ret);
err = ret;
goto out_end_trans;
}
if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
dest->root_item.received_uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
dest->root_key.objectid);
if (ret && ret != -ENOENT) {
btrfs_abort_transaction(trans, root, ret);
err = ret;
goto out_end_trans;
}
}
out_end_trans:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
ret = btrfs_end_transaction(trans, root);
if (ret && !err)
err = ret;
inode->i_flags |= S_DEAD;
out_release:
btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
out_up_write:
up_write(&root->fs_info->subvol_sem);
out_unlock:
mutex_unlock(&inode->i_mutex);
if (!err) {
shrink_dcache_sb(root->fs_info->sb);
btrfs_invalidate_inodes(dest);
d_delete(dentry);
/* the last ref */
if (dest->cache_inode) {
iput(dest->cache_inode);
dest->cache_inode = NULL;
}
}
out_dput:
dput(dentry);
out_unlock_dir:
mutex_unlock(&dir->i_mutex);
out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
return err;
}
static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
{
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ioctl_defrag_range_args *range;
int ret;
ret = mnt_want_write_file(file);
if (ret)
return ret;
if (btrfs_root_readonly(root)) {
ret = -EROFS;
goto out;
}
switch (inode->i_mode & S_IFMT) {
case S_IFDIR:
if (!capable(CAP_SYS_ADMIN)) {
ret = -EPERM;
goto out;
}
ret = btrfs_defrag_root(root);
if (ret)
goto out;
ret = btrfs_defrag_root(root->fs_info->extent_root);
break;
case S_IFREG:
if (!(file->f_mode & FMODE_WRITE)) {
ret = -EINVAL;
goto out;
}
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);
goto out;
}
/* 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;
}
ret = btrfs_defrag_file(file_inode(file), file,
range, 0, 0);
if (ret > 0)
ret = 0;
kfree(range);
break;
default:
ret = -EINVAL;
}
out:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
{
struct btrfs_ioctl_vol_args *vol_args;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
mutex_lock(&root->fs_info->volume_mutex);
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
goto out;
}
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
ret = btrfs_init_new_device(root, vol_args->name);
kfree(vol_args);
out:
mutex_unlock(&root->fs_info->volume_mutex);
atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
return ret;
}
static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_vol_args *vol_args;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
goto out;
}
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out;
}
mutex_lock(&root->fs_info->volume_mutex);
ret = btrfs_rm_device(root, vol_args->name);
mutex_unlock(&root->fs_info->volume_mutex);
atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
out:
kfree(vol_args);
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
{
struct btrfs_ioctl_fs_info_args *fi_args;
struct btrfs_device *device;
struct btrfs_device *next;
struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
if (!fi_args)
return -ENOMEM;
mutex_lock(&fs_devices->device_list_mutex);
fi_args->num_devices = fs_devices->num_devices;
memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid));
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
if (device->devid > fi_args->max_id)
fi_args->max_id = device->devid;
}
mutex_unlock(&fs_devices->device_list_mutex);
if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
ret = -EFAULT;
kfree(fi_args);
return ret;
}
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;
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 (!btrfs_is_empty_uuid(di_args->uuid))
s_uuid = di_args->uuid;
mutex_lock(&fs_devices->device_list_mutex);
dev = btrfs_find_device(root->fs_info, di_args->devid, s_uuid, NULL);
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));
if (dev->name) {
struct rcu_string *name;
rcu_read_lock();
name = rcu_dereference(dev->name);
strncpy(di_args->path, name->str, sizeof(di_args->path));
rcu_read_unlock();
di_args->path[sizeof(di_args->path) - 1] = 0;
} else {
di_args->path[0] = '\0';
}
out:
mutex_unlock(&fs_devices->device_list_mutex);
if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
ret = -EFAULT;
kfree(di_args);
return ret;
}
static struct page *extent_same_get_page(struct inode *inode, u64 off)
{
struct page *page;
pgoff_t index;
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
index = off >> PAGE_CACHE_SHIFT;
page = grab_cache_page(inode->i_mapping, index);
if (!page)
return NULL;
if (!PageUptodate(page)) {
if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
0))
return NULL;
lock_page(page);
if (!PageUptodate(page)) {
unlock_page(page);
page_cache_release(page);
return NULL;
}
}
unlock_page(page);
return page;
}
static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
{
/* do any pending delalloc/csum calc on src, one way or
another, and lock file content */
while (1) {
struct btrfs_ordered_extent *ordered;
lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
ordered = btrfs_lookup_first_ordered_extent(inode,
off + len - 1);
if (!ordered &&
!test_range_bit(&BTRFS_I(inode)->io_tree, off,
off + len - 1, EXTENT_DELALLOC, 0, NULL))
break;
unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
if (ordered)
btrfs_put_ordered_extent(ordered);
btrfs_wait_ordered_range(inode, off, len);
}
}
static void btrfs_double_unlock(struct inode *inode1, u64 loff1,
struct inode *inode2, u64 loff2, u64 len)
{
unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
mutex_unlock(&inode1->i_mutex);
mutex_unlock(&inode2->i_mutex);
}
static void btrfs_double_lock(struct inode *inode1, u64 loff1,
struct inode *inode2, u64 loff2, u64 len)
{
if (inode1 < inode2) {
swap(inode1, inode2);
swap(loff1, loff2);
}
mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
lock_extent_range(inode1, loff1, len);
if (inode1 != inode2) {
mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
lock_extent_range(inode2, loff2, len);
}
}
static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
u64 dst_loff, u64 len)
{
int ret = 0;
struct page *src_page, *dst_page;
unsigned int cmp_len = PAGE_CACHE_SIZE;
void *addr, *dst_addr;
while (len) {
if (len < PAGE_CACHE_SIZE)
cmp_len = len;
src_page = extent_same_get_page(src, loff);
if (!src_page)
return -EINVAL;
dst_page = extent_same_get_page(dst, dst_loff);
if (!dst_page) {
page_cache_release(src_page);
return -EINVAL;
}
addr = kmap_atomic(src_page);
dst_addr = kmap_atomic(dst_page);
flush_dcache_page(src_page);
flush_dcache_page(dst_page);
if (memcmp(addr, dst_addr, cmp_len))
ret = BTRFS_SAME_DATA_DIFFERS;
kunmap_atomic(addr);
kunmap_atomic(dst_addr);
page_cache_release(src_page);
page_cache_release(dst_page);
if (ret)
break;
loff += cmp_len;
dst_loff += cmp_len;
len -= cmp_len;
}
return ret;
}
static int extent_same_check_offsets(struct inode *inode, u64 off, u64 len)
{
u64 bs = BTRFS_I(inode)->root->fs_info->sb->s_blocksize;
if (off + len > inode->i_size || off + len < off)
return -EINVAL;
/* Check that we are block aligned - btrfs_clone() requires this */
if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs))
return -EINVAL;
return 0;
}
static int btrfs_extent_same(struct inode *src, u64 loff, u64 len,
struct inode *dst, u64 dst_loff)
{
int ret;
/*
* btrfs_clone() can't handle extents in the same file
* yet. Once that works, we can drop this check and replace it
* with a check for the same inode, but overlapping extents.
*/
if (src == dst)
return -EINVAL;
btrfs_double_lock(src, loff, dst, dst_loff, len);
ret = extent_same_check_offsets(src, loff, len);
if (ret)
goto out_unlock;
ret = extent_same_check_offsets(dst, dst_loff, len);
if (ret)
goto out_unlock;
/* don't make the dst file partly checksummed */
if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
(BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
ret = -EINVAL;
goto out_unlock;
}
ret = btrfs_cmp_data(src, loff, dst, dst_loff, len);
if (ret == 0)
ret = btrfs_clone(src, dst, loff, len, len, dst_loff);
out_unlock:
btrfs_double_unlock(src, loff, dst, dst_loff, len);
return ret;
}
#define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024)
static long btrfs_ioctl_file_extent_same(struct file *file,
void __user *argp)
{
struct btrfs_ioctl_same_args tmp;
struct btrfs_ioctl_same_args *same;
struct btrfs_ioctl_same_extent_info *info;
struct inode *src = file->f_dentry->d_inode;
struct file *dst_file = NULL;
struct inode *dst;
u64 off;
u64 len;
int i;
int ret;
unsigned long size;
u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
bool is_admin = capable(CAP_SYS_ADMIN);
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
ret = mnt_want_write_file(file);
if (ret)
return ret;
if (copy_from_user(&tmp,
(struct btrfs_ioctl_same_args __user *)argp,
sizeof(tmp))) {
ret = -EFAULT;
goto out;
}
size = sizeof(tmp) +
tmp.dest_count * sizeof(struct btrfs_ioctl_same_extent_info);
same = memdup_user((struct btrfs_ioctl_same_args __user *)argp, size);
if (IS_ERR(same)) {
ret = PTR_ERR(same);
goto out;
}
off = same->logical_offset;
len = same->length;
/*
* Limit the total length we will dedupe for each operation.
* This is intended to bound the total time spent in this
* ioctl to something sane.
*/
if (len > BTRFS_MAX_DEDUPE_LEN)
len = BTRFS_MAX_DEDUPE_LEN;
if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
/*
* Btrfs does not support blocksize < page_size. As a
* result, btrfs_cmp_data() won't correctly handle
* this situation without an update.
*/
ret = -EINVAL;
goto out;
}
ret = -EISDIR;
if (S_ISDIR(src->i_mode))
goto out;
ret = -EACCES;
if (!S_ISREG(src->i_mode))
goto out;
/* pre-format output fields to sane values */
for (i = 0; i < same->dest_count; i++) {
same->info[i].bytes_deduped = 0ULL;
same->info[i].status = 0;
}
ret = 0;
for (i = 0; i < same->dest_count; i++) {
info = &same->info[i];
dst_file = fget(info->fd);
if (!dst_file) {
info->status = -EBADF;
goto next;
}
if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
info->status = -EINVAL;
goto next;
}
info->status = -EXDEV;
if (file->f_path.mnt != dst_file->f_path.mnt)
goto next;
dst = dst_file->f_dentry->d_inode;
if (src->i_sb != dst->i_sb)
goto next;
if (S_ISDIR(dst->i_mode)) {
info->status = -EISDIR;
goto next;
}
if (!S_ISREG(dst->i_mode)) {
info->status = -EACCES;
goto next;
}
info->status = btrfs_extent_same(src, off, len, dst,
info->logical_offset);
if (info->status == 0)
info->bytes_deduped += len;
next:
if (dst_file)
fput(dst_file);
}
ret = copy_to_user(argp, same, size);
if (ret)
ret = -EFAULT;
out:
mnt_drop_write_file(file);
return ret;
}
/**
* btrfs_clone() - clone a range from inode file to another
*
* @src: Inode to clone from
* @inode: Inode to clone to
* @off: Offset within source to start clone from
* @olen: Original length, passed by user, of range to clone
* @olen_aligned: Block-aligned value of olen, extent_same uses
* identical values here
* @destoff: Offset within @inode to start clone
*/
static int btrfs_clone(struct inode *src, struct inode *inode,
u64 off, u64 olen, u64 olen_aligned, u64 destoff)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path = NULL;
struct extent_buffer *leaf;
struct btrfs_trans_handle *trans;
char *buf = NULL;
struct btrfs_key key;
u32 nritems;
int slot;
int ret;
u64 len = olen_aligned;
ret = -ENOMEM;
buf = vmalloc(btrfs_level_size(root, 0));
if (!buf)
return ret;
path = btrfs_alloc_path();
if (!path) {
vfree(buf);
return ret;
}
path->reada = 2;
/* clone data */
key.objectid = btrfs_ino(src);
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = 0;
while (1) {
/*
* note the key will change type as we walk through the
* tree.
*/
ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path,
0, 0);
if (ret < 0)
goto out;
nritems = btrfs_header_nritems(path->nodes[0]);
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
if (ret < 0)
goto out;
if (ret > 0)
break;
nritems = btrfs_header_nritems(path->nodes[0]);
}
leaf = path->nodes[0];
slot = path->slots[0];
btrfs_item_key_to_cpu(leaf, &key, slot);
if (btrfs_key_type(&key) > BTRFS_EXTENT_DATA_KEY ||
key.objectid != btrfs_ino(src))
break;
if (btrfs_key_type(&key) == BTRFS_EXTENT_DATA_KEY) {
struct btrfs_file_extent_item *extent;
int type;
u32 size;
struct btrfs_key new_key;
u64 disko = 0, diskl = 0;
u64 datao = 0, datal = 0;
u8 comp;
u64 endoff;
size = btrfs_item_size_nr(leaf, slot);
read_extent_buffer(leaf, buf,
btrfs_item_ptr_offset(leaf, slot),
size);
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);
if (type == BTRFS_FILE_EXTENT_REG ||
type == BTRFS_FILE_EXTENT_PREALLOC) {
disko = btrfs_file_extent_disk_bytenr(leaf,
extent);
diskl = btrfs_file_extent_disk_num_bytes(leaf,
extent);
datao = btrfs_file_extent_offset(leaf, extent);
datal = btrfs_file_extent_num_bytes(leaf,
extent);
} else if (type == BTRFS_FILE_EXTENT_INLINE) {
/* take upper bound, may be compressed */
datal = btrfs_file_extent_ram_bytes(leaf,
extent);
}
btrfs_release_path(path);
if (key.offset + datal <= off ||
key.offset >= off + len - 1)
goto next;
memcpy(&new_key, &key, sizeof(new_key));
new_key.objectid = btrfs_ino(inode);
if (off <= key.offset)
new_key.offset = key.offset + destoff - off;
else
new_key.offset = destoff;
/*
* 1 - adjusting old extent (we may have to split it)
* 1 - add new extent
* 1 - inode update
*/
trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
if (type == BTRFS_FILE_EXTENT_REG ||
type == BTRFS_FILE_EXTENT_PREALLOC) {
/*
* a | --- range to clone ---| b
* | ------------- extent ------------- |
*/
/* substract range b */
if (key.offset + datal > off + len)
datal = off + len - key.offset;
/* substract range a */
if (off > key.offset) {
datao += off - key.offset;
datal -= off - key.offset;
}
ret = btrfs_drop_extents(trans, root, inode,
new_key.offset,
new_key.offset + datal,
1);
if (ret) {
btrfs_abort_transaction(trans, root,
ret);
btrfs_end_transaction(trans, root);
goto out;
}
ret = btrfs_insert_empty_item(trans, root, path,
&new_key, size);
if (ret) {
btrfs_abort_transaction(trans, root,
ret);
btrfs_end_transaction(trans, root);
goto out;
}
leaf = path->nodes[0];
slot = path->slots[0];
write_extent_buffer(leaf, buf,
btrfs_item_ptr_offset(leaf, slot),
size);
extent = btrfs_item_ptr(leaf, slot,
struct btrfs_file_extent_item);
/* 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);
ret = btrfs_inc_extent_ref(trans, root,
disko, diskl, 0,
root->root_key.objectid,
btrfs_ino(inode),
new_key.offset - datao,
0);
if (ret) {
btrfs_abort_transaction(trans,
root,
ret);
btrfs_end_transaction(trans,
root);
goto out;
}
}
} 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;
}
if (key.offset + datal > off + len)
trim = key.offset + datal - (off + len);
if (comp && (skip || trim)) {
ret = -EINVAL;
btrfs_end_transaction(trans, root);
goto out;
}
size -= skip + trim;
datal -= skip + trim;
ret = btrfs_drop_extents(trans, root, inode,
new_key.offset,
new_key.offset + datal,
1);
if (ret) {
btrfs_abort_transaction(trans, root,
ret);
btrfs_end_transaction(trans, root);
goto out;
}
ret = btrfs_insert_empty_item(trans, root, path,
&new_key, size);
if (ret) {
btrfs_abort_transaction(trans, root,
ret);
btrfs_end_transaction(trans, root);
goto out;
}
if (skip) {
u32 start =
btrfs_file_extent_calc_inline_size(0);
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);
}
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
inode_inc_iversion(inode);
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
/*
* 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;
if (endoff > destoff+olen)
endoff = destoff+olen;
if (endoff > inode->i_size)
btrfs_i_size_write(inode, endoff);
ret = btrfs_update_inode(trans, root, inode);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
btrfs_end_transaction(trans, root);
goto out;
}
ret = btrfs_end_transaction(trans, root);
}
next:
btrfs_release_path(path);
key.offset++;
}
ret = 0;
out:
btrfs_release_path(path);
btrfs_free_path(path);
vfree(buf);
return ret;
}
static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
u64 off, u64 olen, u64 destoff)
{
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct fd src_file;
struct inode *src;
int ret;
u64 len = olen;
u64 bs = root->fs_info->sb->s_blocksize;
int same_inode = 0;
/*
* 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)?
*/
/* the destination must be opened for writing */
if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
return -EINVAL;
if (btrfs_root_readonly(root))
return -EROFS;
ret = mnt_want_write_file(file);
if (ret)
return ret;
src_file = fdget(srcfd);
if (!src_file.file) {
ret = -EBADF;
goto out_drop_write;
}
ret = -EXDEV;
if (src_file.file->f_path.mnt != file->f_path.mnt)
goto out_fput;
src = file_inode(src_file.file);
ret = -EINVAL;
if (src == inode)
same_inode = 1;
/* the src must be open for reading */
if (!(src_file.file->f_mode & FMODE_READ))
goto out_fput;
/* 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;
ret = -EISDIR;
if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
goto out_fput;
ret = -EXDEV;
if (src->i_sb != inode->i_sb)
goto out_fput;
if (!same_inode) {
if (inode < src) {
mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
} else {
mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
}
} else {
mutex_lock(&src->i_mutex);
}
/* determine range to clone */
ret = -EINVAL;
if (off + len > src->i_size || off + len < off)
goto out_unlock;
if (len == 0)
olen = len = src->i_size - off;
/* if we extend to eof, continue to block boundary */
if (off + len == src->i_size)
len = ALIGN(src->i_size, bs) - off;
/* verify the end result is block aligned */
if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
!IS_ALIGNED(destoff, bs))
goto out_unlock;
/* verify if ranges are overlapped within the same file */
if (same_inode) {
if (destoff + len > off && destoff < off + len)
goto out_unlock;
}
if (destoff > inode->i_size) {
ret = btrfs_cont_expand(inode, inode->i_size, destoff);
if (ret)
goto out_unlock;
}
/* truncate page cache pages from target inode range */
truncate_inode_pages_range(&inode->i_data, destoff,
PAGE_CACHE_ALIGN(destoff + len) - 1);
lock_extent_range(src, off, len);
ret = btrfs_clone(src, inode, off, olen, len, destoff);
unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
out_unlock:
mutex_unlock(&src->i_mutex);
if (!same_inode)
mutex_unlock(&inode->i_mutex);
out_fput:
fdput(src_file);
out_drop_write:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
{
struct btrfs_ioctl_clone_range_args args;
if (copy_from_user(&args, argp, sizeof(args)))
return -EFAULT;
return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
args.src_length, args.dest_offset);
}
/*
* 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.
*/
static long btrfs_ioctl_trans_start(struct file *file)
{
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret;
ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out;
ret = -EINPROGRESS;
if (file->private_data)
goto out;
ret = -EROFS;
if (btrfs_root_readonly(root))
goto out;
ret = mnt_want_write_file(file);
if (ret)
goto out;
atomic_inc(&root->fs_info->open_ioctl_trans);
ret = -ENOMEM;
trans = btrfs_start_ioctl_transaction(root);
if (IS_ERR(trans))
goto out_drop;
file->private_data = trans;
return 0;
out_drop:
atomic_dec(&root->fs_info->open_ioctl_trans);
mnt_drop_write_file(file);
out:
return ret;
}
static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
{
struct inode *inode = file_inode(file);
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;
u64 objectid = 0;
u64 dir_id;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
if (copy_from_user(&objectid, argp, sizeof(objectid))) {
ret = -EFAULT;
goto out;
}
if (!objectid)
objectid = BTRFS_FS_TREE_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)) {
ret = PTR_ERR(new_root);
goto out;
}
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
path->leave_spinning = 1;
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
btrfs_free_path(path);
ret = PTR_ERR(trans);
goto out;
}
dir_id = btrfs_super_root_dir(root->fs_info->super_copy);
di = btrfs_lookup_dir_item(trans, root->fs_info->tree_root, path,
dir_id, "default", 7, 1);
if (IS_ERR_OR_NULL(di)) {
btrfs_free_path(path);
btrfs_end_transaction(trans, root);
btrfs_err(new_root->fs_info, "Umm, you don't have the default dir"
"item, this isn't going to work");
ret = -ENOENT;
goto out;
}
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);
btrfs_set_fs_incompat(root->fs_info, DEFAULT_SUBVOL);
btrfs_end_transaction(trans, root);
out:
mnt_drop_write_file(file);
return ret;
}
void btrfs_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);
}
}
static 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;
struct btrfs_ioctl_space_info *dest_orig;
struct btrfs_ioctl_space_info __user *user_dest;
struct btrfs_space_info *info;
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;
int alloc_size;
int ret = 0;
u64 slot_count = 0;
int i, c;
if (copy_from_user(&space_args,
(struct btrfs_ioctl_space_args __user *)arg,
sizeof(space_args)))
return -EFAULT;
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);
}
/* space_slots == 0 means they are asking for a count */
if (space_args.space_slots == 0) {
space_args.total_spaces = slot_count;
goto out;
}
slot_count = min_t(u64, space_args.space_slots, slot_count);
alloc_size = sizeof(*dest) * slot_count;
/* 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;
space_args.total_spaces = 0;
dest = kmalloc(alloc_size, GFP_NOFS);
if (!dest)
return -ENOMEM;
dest_orig = dest;
/* now we have a buffer to copy into */
for (i = 0; i < num_types; i++) {
struct btrfs_space_info *tmp;
if (!slot_count)
break;
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])) {
btrfs_get_block_group_info(
&info->block_groups[c], &space);
memcpy(dest, &space, sizeof(space));
dest++;
space_args.total_spaces++;
slot_count--;
}
if (!slot_count)
break;
}
up_read(&info->groups_sem);
}
user_dest = (struct btrfs_ioctl_space_info __user *)
(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)))
ret = -EFAULT;
return ret;
}
static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg)
{
struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv;
u64 reserved;
spin_lock(&block_rsv->lock);
reserved = block_rsv->reserved;
spin_unlock(&block_rsv->lock);
if (arg && copy_to_user(arg, &reserved, sizeof(reserved)))
return -EFAULT;
return 0;
}
/*
* 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 = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
trans = file->private_data;
if (!trans)
return -EINVAL;
file->private_data = NULL;
btrfs_end_transaction(trans, root);
atomic_dec(&root->fs_info->open_ioctl_trans);
mnt_drop_write_file(file);
return 0;
}
static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root,
void __user *argp)
{
struct btrfs_trans_handle *trans;
u64 transid;
int ret;
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
return PTR_ERR(trans);
/* No running transaction, don't bother */
transid = root->fs_info->last_trans_committed;
goto out;
}
transid = trans->transid;
ret = btrfs_commit_transaction_async(trans, root, 0);
if (ret) {
btrfs_end_transaction(trans, root);
return ret;
}
out:
if (argp)
if (copy_to_user(argp, &transid, sizeof(transid)))
return -EFAULT;
return 0;
}
static noinline long btrfs_ioctl_wait_sync(struct btrfs_root *root,
void __user *argp)
{
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);
}
static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
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);
if (!(sa->flags & BTRFS_SCRUB_READONLY)) {
ret = mnt_want_write_file(file);
if (ret)
goto out;
}
ret = btrfs_scrub_dev(root->fs_info, sa->devid, sa->start, sa->end,
&sa->progress, sa->flags & BTRFS_SCRUB_READONLY,
0);
if (copy_to_user(arg, sa, sizeof(*sa)))
ret = -EFAULT;
if (!(sa->flags & BTRFS_SCRUB_READONLY))
mnt_drop_write_file(file);
out:
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->fs_info);
}
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;
}
static long btrfs_ioctl_get_dev_stats(struct btrfs_root *root,
void __user *arg)
{
struct btrfs_ioctl_get_dev_stats *sa;
int ret;
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa))
return PTR_ERR(sa);
if ((sa->flags & BTRFS_DEV_STATS_RESET) && !capable(CAP_SYS_ADMIN)) {
kfree(sa);
return -EPERM;
}
ret = btrfs_get_dev_stats(root, sa);
if (copy_to_user(arg, sa, sizeof(*sa)))
ret = -EFAULT;
kfree(sa);
return ret;
}
static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg)
{
struct btrfs_ioctl_dev_replace_args *p;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
p = memdup_user(arg, sizeof(*p));
if (IS_ERR(p))
return PTR_ERR(p);
switch (p->cmd) {
case BTRFS_IOCTL_DEV_REPLACE_CMD_START:
if (root->fs_info->sb->s_flags & MS_RDONLY) {
ret = -EROFS;
goto out;
}
if (atomic_xchg(
&root->fs_info->mutually_exclusive_operation_running,
1)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
} else {
ret = btrfs_dev_replace_start(root, p);
atomic_set(
&root->fs_info->mutually_exclusive_operation_running,
0);
}
break;
case BTRFS_IOCTL_DEV_REPLACE_CMD_STATUS:
btrfs_dev_replace_status(root->fs_info, p);
ret = 0;
break;
case BTRFS_IOCTL_DEV_REPLACE_CMD_CANCEL:
ret = btrfs_dev_replace_cancel(root->fs_info, p);
break;
default:
ret = -EINVAL;
break;
}
if (copy_to_user(arg, p, sizeof(*p)))
ret = -EFAULT;
out:
kfree(p);
return ret;
}
static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
{
int ret = 0;
int i;
u64 rel_ptr;
int size;
struct btrfs_ioctl_ino_path_args *ipa = NULL;
struct inode_fs_paths *ipath = NULL;
struct btrfs_path *path;
if (!capable(CAP_DAC_READ_SEARCH))
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) {
rel_ptr = ipath->fspath->val[i] -
(u64)(unsigned long)ipath->fspath->val;
ipath->fspath->val[i] = rel_ptr;
}
ret = copy_to_user((void *)(unsigned long)ipa->fspath,
(void *)(unsigned long)ipath->fspath, size);
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;
struct btrfs_ioctl_logical_ino_args *loi;
struct btrfs_data_container *inodes = NULL;
struct btrfs_path *path = NULL;
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, 64 * 1024);
inodes = init_data_container(size);
if (IS_ERR(inodes)) {
ret = PTR_ERR(inodes);
inodes = NULL;
goto out;
}
ret = iterate_inodes_from_logical(loi->logical, root->fs_info, path,
build_ino_list, inodes);
if (ret == -EINVAL)
ret = -ENOENT;
if (ret < 0)
goto out;
ret = copy_to_user((void *)(unsigned long)loi->inodes,
(void *)(unsigned long)inodes, size);
if (ret)
ret = -EFAULT;
out:
btrfs_free_path(path);
vfree(inodes);
kfree(loi);
return ret;
}
void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
struct btrfs_ioctl_balance_args *bargs)
{
struct btrfs_balance_control *bctl = fs_info->balance_ctl;
bargs->flags = bctl->flags;
if (atomic_read(&fs_info->balance_running))
bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
if (atomic_read(&fs_info->balance_pause_req))
bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
if (atomic_read(&fs_info->balance_cancel_req))
bargs->state |= BTRFS_BALANCE_STATE_CANCEL_REQ;
memcpy(&bargs->data, &bctl->data, sizeof(bargs->data));
memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
if (lock) {
spin_lock(&fs_info->balance_lock);
memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
spin_unlock(&fs_info->balance_lock);
} else {
memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
}
}
static long btrfs_ioctl_balance(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_ioctl_balance_args *bargs;
struct btrfs_balance_control *bctl;
bool need_unlock; /* for mut. excl. ops lock */
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
again:
if (!atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
need_unlock = true;
goto locked;
}
/*
* mut. excl. ops lock is locked. Three possibilites:
* (1) some other op is running
* (2) balance is running
* (3) balance is paused -- special case (think resume)
*/
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl) {
/* this is either (2) or (3) */
if (!atomic_read(&fs_info->balance_running)) {
mutex_unlock(&fs_info->balance_mutex);
if (!mutex_trylock(&fs_info->volume_mutex))
goto again;
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl &&
!atomic_read(&fs_info->balance_running)) {
/* this is (3) */
need_unlock = false;
goto locked;
}
mutex_unlock(&fs_info->balance_mutex);
mutex_unlock(&fs_info->volume_mutex);
goto again;
} else {
/* this is (2) */
mutex_unlock(&fs_info->balance_mutex);
ret = -EINPROGRESS;
goto out;
}
} else {
/* this is (1) */
mutex_unlock(&fs_info->balance_mutex);
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out;
}
locked:
BUG_ON(!atomic_read(&fs_info->mutually_exclusive_operation_running));
if (arg) {
bargs = memdup_user(arg, sizeof(*bargs));
if (IS_ERR(bargs)) {
ret = PTR_ERR(bargs);
goto out_unlock;
}
if (bargs->flags & BTRFS_BALANCE_RESUME) {
if (!fs_info->balance_ctl) {
ret = -ENOTCONN;
goto out_bargs;
}
bctl = fs_info->balance_ctl;
spin_lock(&fs_info->balance_lock);
bctl->flags |= BTRFS_BALANCE_RESUME;
spin_unlock(&fs_info->balance_lock);
goto do_balance;
}
} else {
bargs = NULL;
}
if (fs_info->balance_ctl) {
ret = -EINPROGRESS;
goto out_bargs;
}
bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
if (!bctl) {
ret = -ENOMEM;
goto out_bargs;
}
bctl->fs_info = fs_info;
if (arg) {
memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
bctl->flags = bargs->flags;
} else {
/* balance everything - no filters */
bctl->flags |= BTRFS_BALANCE_TYPE_MASK;
}
do_balance:
/*
* Ownership of bctl and mutually_exclusive_operation_running
* goes to to btrfs_balance. bctl is freed in __cancel_balance,
* or, if restriper was paused all the way until unmount, in
* free_fs_info. mutually_exclusive_operation_running is
* cleared in __cancel_balance.
*/
need_unlock = false;
ret = btrfs_balance(bctl, bargs);
if (arg) {
if (copy_to_user(arg, bargs, sizeof(*bargs)))
ret = -EFAULT;
}
out_bargs:
kfree(bargs);
out_unlock:
mutex_unlock(&fs_info->balance_mutex);
mutex_unlock(&fs_info->volume_mutex);
if (need_unlock)
atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
out:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd)
{
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
switch (cmd) {
case BTRFS_BALANCE_CTL_PAUSE:
return btrfs_pause_balance(root->fs_info);
case BTRFS_BALANCE_CTL_CANCEL:
return btrfs_cancel_balance(root->fs_info);
}
return -EINVAL;
}
static long btrfs_ioctl_balance_progress(struct btrfs_root *root,
void __user *arg)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_ioctl_balance_args *bargs;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
mutex_lock(&fs_info->balance_mutex);
if (!fs_info->balance_ctl) {
ret = -ENOTCONN;
goto out;
}
bargs = kzalloc(sizeof(*bargs), GFP_NOFS);
if (!bargs) {
ret = -ENOMEM;
goto out;
}
update_ioctl_balance_args(fs_info, 1, bargs);
if (copy_to_user(arg, bargs, sizeof(*bargs)))
ret = -EFAULT;
kfree(bargs);
out:
mutex_unlock(&fs_info->balance_mutex);
return ret;
}
static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_quota_ctl_args *sa;
struct btrfs_trans_handle *trans = NULL;
int ret;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
goto drop_write;
}
down_write(&root->fs_info->subvol_sem);
trans = btrfs_start_transaction(root->fs_info->tree_root, 2);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
switch (sa->cmd) {
case BTRFS_QUOTA_CTL_ENABLE:
ret = btrfs_quota_enable(trans, root->fs_info);
break;
case BTRFS_QUOTA_CTL_DISABLE:
ret = btrfs_quota_disable(trans, root->fs_info);
break;
default:
ret = -EINVAL;
break;
}
err = btrfs_commit_transaction(trans, root->fs_info->tree_root);
if (err && !ret)
ret = err;
out:
kfree(sa);
up_write(&root->fs_info->subvol_sem);
drop_write:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_qgroup_assign_args *sa;
struct btrfs_trans_handle *trans;
int ret;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
goto drop_write;
}
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
/* FIXME: check if the IDs really exist */
if (sa->assign) {
ret = btrfs_add_qgroup_relation(trans, root->fs_info,
sa->src, sa->dst);
} else {
ret = btrfs_del_qgroup_relation(trans, root->fs_info,
sa->src, sa->dst);
}
err = btrfs_end_transaction(trans, root);
if (err && !ret)
ret = err;
out:
kfree(sa);
drop_write:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_qgroup_create_args *sa;
struct btrfs_trans_handle *trans;
int ret;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
goto drop_write;
}
if (!sa->qgroupid) {
ret = -EINVAL;
goto out;
}
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
/* FIXME: check if the IDs really exist */
if (sa->create) {
ret = btrfs_create_qgroup(trans, root->fs_info, sa->qgroupid,
NULL);
} else {
ret = btrfs_remove_qgroup(trans, root->fs_info, sa->qgroupid);
}
err = btrfs_end_transaction(trans, root);
if (err && !ret)
ret = err;
out:
kfree(sa);
drop_write:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_qgroup_limit_args *sa;
struct btrfs_trans_handle *trans;
int ret;
int err;
u64 qgroupid;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
goto drop_write;
}
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out;
}
qgroupid = sa->qgroupid;
if (!qgroupid) {
/* take the current subvol as qgroup */
qgroupid = root->root_key.objectid;
}
/* FIXME: check if the IDs really exist */
ret = btrfs_limit_qgroup(trans, root->fs_info, qgroupid, &sa->lim);
err = btrfs_end_transaction(trans, root);
if (err && !ret)
ret = err;
out:
kfree(sa);
drop_write:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_quota_rescan(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_quota_rescan_args *qsa;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
ret = mnt_want_write_file(file);
if (ret)
return ret;
qsa = memdup_user(arg, sizeof(*qsa));
if (IS_ERR(qsa)) {
ret = PTR_ERR(qsa);
goto drop_write;
}
if (qsa->flags) {
ret = -EINVAL;
goto out;
}
ret = btrfs_qgroup_rescan(root->fs_info);
out:
kfree(qsa);
drop_write:
mnt_drop_write_file(file);
return ret;
}
static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_quota_rescan_args *qsa;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
qsa = kzalloc(sizeof(*qsa), GFP_NOFS);
if (!qsa)
return -ENOMEM;
if (root->fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
qsa->flags = 1;
qsa->progress = root->fs_info->qgroup_rescan_progress.objectid;
}
if (copy_to_user(arg, qsa, sizeof(*qsa)))
ret = -EFAULT;
kfree(qsa);
return ret;
}
static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return btrfs_qgroup_wait_for_completion(root->fs_info);
}
static long btrfs_ioctl_set_received_subvol(struct file *file,
void __user *arg)
{
struct btrfs_ioctl_received_subvol_args *sa = NULL;
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_root_item *root_item = &root->root_item;
struct btrfs_trans_handle *trans;
struct timespec ct = CURRENT_TIME;
int ret = 0;
int received_uuid_changed;
ret = mnt_want_write_file(file);
if (ret < 0)
return ret;
down_write(&root->fs_info->subvol_sem);
if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
ret = -EINVAL;
goto out;
}
if (btrfs_root_readonly(root)) {
ret = -EROFS;
goto out;
}
if (!inode_owner_or_capable(inode)) {
ret = -EACCES;
goto out;
}
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
sa = NULL;
goto out;
}
/*
* 1 - root item
* 2 - uuid items (received uuid + subvol uuid)
*/
trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
goto out;
}
sa->rtransid = trans->transid;
sa->rtime.sec = ct.tv_sec;
sa->rtime.nsec = ct.tv_nsec;
received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid,
BTRFS_UUID_SIZE);
if (received_uuid_changed &&
!btrfs_is_empty_uuid(root_item->received_uuid))
btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
root_item->received_uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
root->root_key.objectid);
memcpy(root_item->received_uuid, sa->uuid, BTRFS_UUID_SIZE);
btrfs_set_root_stransid(root_item, sa->stransid);
btrfs_set_root_rtransid(root_item, sa->rtransid);
btrfs_set_stack_timespec_sec(&root_item->stime, sa->stime.sec);
btrfs_set_stack_timespec_nsec(&root_item->stime, sa->stime.nsec);
btrfs_set_stack_timespec_sec(&root_item->rtime, sa->rtime.sec);
btrfs_set_stack_timespec_nsec(&root_item->rtime, sa->rtime.nsec);
ret = btrfs_update_root(trans, root->fs_info->tree_root,
&root->root_key, &root->root_item);
if (ret < 0) {
btrfs_end_transaction(trans, root);
goto out;
}
if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
sa->uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
root->root_key.objectid);
if (ret < 0 && ret != -EEXIST) {
btrfs_abort_transaction(trans, root, ret);
goto out;
}
}
ret = btrfs_commit_transaction(trans, root);
if (ret < 0) {
btrfs_abort_transaction(trans, root, ret);
goto out;
}
ret = copy_to_user(arg, sa, sizeof(*sa));
if (ret)
ret = -EFAULT;
out:
kfree(sa);
up_write(&root->fs_info->subvol_sem);
mnt_drop_write_file(file);
return ret;
}
static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
size_t len;
int ret;
char label[BTRFS_LABEL_SIZE];
spin_lock(&root->fs_info->super_lock);
memcpy(label, root->fs_info->super_copy->label, BTRFS_LABEL_SIZE);
spin_unlock(&root->fs_info->super_lock);
len = strnlen(label, BTRFS_LABEL_SIZE);
if (len == BTRFS_LABEL_SIZE) {
btrfs_warn(root->fs_info,
"label is too long, return the first %zu bytes", --len);
}
ret = copy_to_user(arg, label, len);
return ret ? -EFAULT : 0;
}
static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_super_block *super_block = root->fs_info->super_copy;
struct btrfs_trans_handle *trans;
char label[BTRFS_LABEL_SIZE];
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(label, arg, sizeof(label)))
return -EFAULT;
if (strnlen(label, BTRFS_LABEL_SIZE) == BTRFS_LABEL_SIZE) {
btrfs_err(root->fs_info, "unable to set label with more than %d bytes",
BTRFS_LABEL_SIZE - 1);
return -EINVAL;
}
ret = mnt_want_write_file(file);
if (ret)
return ret;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_unlock;
}
spin_lock(&root->fs_info->super_lock);
strcpy(super_block->label, label);
spin_unlock(&root->fs_info->super_lock);
ret = btrfs_end_transaction(trans, root);
out_unlock:
mnt_drop_write_file(file);
return ret;
}
#define INIT_FEATURE_FLAGS(suffix) \
{ .compat_flags = BTRFS_FEATURE_COMPAT_##suffix, \
.compat_ro_flags = BTRFS_FEATURE_COMPAT_RO_##suffix, \
.incompat_flags = BTRFS_FEATURE_INCOMPAT_##suffix }
static int btrfs_ioctl_get_supported_features(struct file *file,
void __user *arg)
{
static struct btrfs_ioctl_feature_flags features[3] = {
INIT_FEATURE_FLAGS(SUPP),
INIT_FEATURE_FLAGS(SAFE_SET),
INIT_FEATURE_FLAGS(SAFE_CLEAR)
};
if (copy_to_user(arg, &features, sizeof(features)))
return -EFAULT;
return 0;
}
static int btrfs_ioctl_get_features(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_super_block *super_block = root->fs_info->super_copy;
struct btrfs_ioctl_feature_flags features;
features.compat_flags = btrfs_super_compat_flags(super_block);
features.compat_ro_flags = btrfs_super_compat_ro_flags(super_block);
features.incompat_flags = btrfs_super_incompat_flags(super_block);
if (copy_to_user(arg, &features, sizeof(features)))
return -EFAULT;
return 0;
}
static int check_feature_bits(struct btrfs_root *root,
enum btrfs_feature_set set,
u64 change_mask, u64 flags, u64 supported_flags,
u64 safe_set, u64 safe_clear)
{
const char *type = btrfs_feature_set_names[set];
char *names;
u64 disallowed, unsupported;
u64 set_mask = flags & change_mask;
u64 clear_mask = ~flags & change_mask;
unsupported = set_mask & ~supported_flags;
if (unsupported) {
names = btrfs_printable_features(set, unsupported);
if (names) {
btrfs_warn(root->fs_info,
"this kernel does not support the %s feature bit%s",
names, strchr(names, ',') ? "s" : "");
kfree(names);
} else
btrfs_warn(root->fs_info,
"this kernel does not support %s bits 0x%llx",
type, unsupported);
return -EOPNOTSUPP;
}
disallowed = set_mask & ~safe_set;
if (disallowed) {
names = btrfs_printable_features(set, disallowed);
if (names) {
btrfs_warn(root->fs_info,
"can't set the %s feature bit%s while mounted",
names, strchr(names, ',') ? "s" : "");
kfree(names);
} else
btrfs_warn(root->fs_info,
"can't set %s bits 0x%llx while mounted",
type, disallowed);
return -EPERM;
}
disallowed = clear_mask & ~safe_clear;
if (disallowed) {
names = btrfs_printable_features(set, disallowed);
if (names) {
btrfs_warn(root->fs_info,
"can't clear the %s feature bit%s while mounted",
names, strchr(names, ',') ? "s" : "");
kfree(names);
} else
btrfs_warn(root->fs_info,
"can't clear %s bits 0x%llx while mounted",
type, disallowed);
return -EPERM;
}
return 0;
}
#define check_feature(root, change_mask, flags, mask_base) \
check_feature_bits(root, FEAT_##mask_base, change_mask, flags, \
BTRFS_FEATURE_ ## mask_base ## _SUPP, \
BTRFS_FEATURE_ ## mask_base ## _SAFE_SET, \
BTRFS_FEATURE_ ## mask_base ## _SAFE_CLEAR)
static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_super_block *super_block = root->fs_info->super_copy;
struct btrfs_ioctl_feature_flags flags[2];
struct btrfs_trans_handle *trans;
u64 newflags;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(flags, arg, sizeof(flags)))
return -EFAULT;
/* Nothing to do */
if (!flags[0].compat_flags && !flags[0].compat_ro_flags &&
!flags[0].incompat_flags)
return 0;
ret = check_feature(root, flags[0].compat_flags,
flags[1].compat_flags, COMPAT);
if (ret)
return ret;
ret = check_feature(root, flags[0].compat_ro_flags,
flags[1].compat_ro_flags, COMPAT_RO);
if (ret)
return ret;
ret = check_feature(root, flags[0].incompat_flags,
flags[1].incompat_flags, INCOMPAT);
if (ret)
return ret;
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans))
return PTR_ERR(trans);
spin_lock(&root->fs_info->super_lock);
newflags = btrfs_super_compat_flags(super_block);
newflags |= flags[0].compat_flags & flags[1].compat_flags;
newflags &= ~(flags[0].compat_flags & ~flags[1].compat_flags);
btrfs_set_super_compat_flags(super_block, newflags);
newflags = btrfs_super_compat_ro_flags(super_block);
newflags |= flags[0].compat_ro_flags & flags[1].compat_ro_flags;
newflags &= ~(flags[0].compat_ro_flags & ~flags[1].compat_ro_flags);
btrfs_set_super_compat_ro_flags(super_block, newflags);
newflags = btrfs_super_incompat_flags(super_block);
newflags |= flags[0].incompat_flags & flags[1].incompat_flags;
newflags &= ~(flags[0].incompat_flags & ~flags[1].incompat_flags);
btrfs_set_super_incompat_flags(super_block, newflags);
spin_unlock(&root->fs_info->super_lock);
return btrfs_end_transaction(trans, root);
}
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
void __user *argp = (void __user *)arg;
switch (cmd) {
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);
case FITRIM:
return btrfs_ioctl_fitrim(file, argp);
case BTRFS_IOC_SNAP_CREATE:
return btrfs_ioctl_snap_create(file, argp, 0);
case BTRFS_IOC_SNAP_CREATE_V2:
return btrfs_ioctl_snap_create_v2(file, argp, 0);
case BTRFS_IOC_SUBVOL_CREATE:
return btrfs_ioctl_snap_create(file, argp, 1);
case BTRFS_IOC_SUBVOL_CREATE_V2:
return btrfs_ioctl_snap_create_v2(file, argp, 1);
case BTRFS_IOC_SNAP_DESTROY:
return btrfs_ioctl_snap_destroy(file, argp);
case BTRFS_IOC_SUBVOL_GETFLAGS:
return btrfs_ioctl_subvol_getflags(file, argp);
case BTRFS_IOC_SUBVOL_SETFLAGS:
return btrfs_ioctl_subvol_setflags(file, argp);
case BTRFS_IOC_DEFAULT_SUBVOL:
return btrfs_ioctl_default_subvol(file, argp);
case BTRFS_IOC_DEFRAG:
return btrfs_ioctl_defrag(file, NULL);
case BTRFS_IOC_DEFRAG_RANGE:
return btrfs_ioctl_defrag(file, argp);
case BTRFS_IOC_RESIZE:
return btrfs_ioctl_resize(file, argp);
case BTRFS_IOC_ADD_DEV:
return btrfs_ioctl_add_dev(root, argp);
case BTRFS_IOC_RM_DEV:
return btrfs_ioctl_rm_dev(file, argp);
case BTRFS_IOC_FS_INFO:
return btrfs_ioctl_fs_info(root, argp);
case BTRFS_IOC_DEV_INFO:
return btrfs_ioctl_dev_info(root, argp);
case BTRFS_IOC_BALANCE:
return btrfs_ioctl_balance(file, NULL);
case BTRFS_IOC_CLONE:
return btrfs_ioctl_clone(file, arg, 0, 0, 0);
case BTRFS_IOC_CLONE_RANGE:
return btrfs_ioctl_clone_range(file, argp);
case BTRFS_IOC_TRANS_START:
return btrfs_ioctl_trans_start(file);
case BTRFS_IOC_TRANS_END:
return btrfs_ioctl_trans_end(file);
case BTRFS_IOC_TREE_SEARCH:
return btrfs_ioctl_tree_search(file, argp);
case BTRFS_IOC_INO_LOOKUP:
return btrfs_ioctl_ino_lookup(file, argp);
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);
case BTRFS_IOC_SPACE_INFO:
return btrfs_ioctl_space_info(root, argp);
case BTRFS_IOC_GLOBAL_RSV:
return btrfs_ioctl_global_rsv(root, argp);
case BTRFS_IOC_SYNC: {
int ret;
ret = btrfs_start_delalloc_roots(root->fs_info, 0);
if (ret)
return ret;
ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
return ret;
}
case BTRFS_IOC_START_SYNC:
return btrfs_ioctl_start_sync(root, argp);
case BTRFS_IOC_WAIT_SYNC:
return btrfs_ioctl_wait_sync(root, argp);
case BTRFS_IOC_SCRUB:
return btrfs_ioctl_scrub(file, 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);
case BTRFS_IOC_BALANCE_V2:
return btrfs_ioctl_balance(file, argp);
case BTRFS_IOC_BALANCE_CTL:
return btrfs_ioctl_balance_ctl(root, arg);
case BTRFS_IOC_BALANCE_PROGRESS:
return btrfs_ioctl_balance_progress(root, argp);
case BTRFS_IOC_SET_RECEIVED_SUBVOL:
return btrfs_ioctl_set_received_subvol(file, argp);
case BTRFS_IOC_SEND:
return btrfs_ioctl_send(file, argp);
case BTRFS_IOC_GET_DEV_STATS:
return btrfs_ioctl_get_dev_stats(root, argp);
case BTRFS_IOC_QUOTA_CTL:
return btrfs_ioctl_quota_ctl(file, argp);
case BTRFS_IOC_QGROUP_ASSIGN:
return btrfs_ioctl_qgroup_assign(file, argp);
case BTRFS_IOC_QGROUP_CREATE:
return btrfs_ioctl_qgroup_create(file, argp);
case BTRFS_IOC_QGROUP_LIMIT:
return btrfs_ioctl_qgroup_limit(file, argp);
case BTRFS_IOC_QUOTA_RESCAN:
return btrfs_ioctl_quota_rescan(file, argp);
case BTRFS_IOC_QUOTA_RESCAN_STATUS:
return btrfs_ioctl_quota_rescan_status(file, argp);
case BTRFS_IOC_QUOTA_RESCAN_WAIT:
return btrfs_ioctl_quota_rescan_wait(file, argp);
case BTRFS_IOC_DEV_REPLACE:
return btrfs_ioctl_dev_replace(root, argp);
case BTRFS_IOC_GET_FSLABEL:
return btrfs_ioctl_get_fslabel(file, argp);
case BTRFS_IOC_SET_FSLABEL:
return btrfs_ioctl_set_fslabel(file, argp);
case BTRFS_IOC_FILE_EXTENT_SAME:
return btrfs_ioctl_file_extent_same(file, argp);
case BTRFS_IOC_GET_SUPPORTED_FEATURES:
return btrfs_ioctl_get_supported_features(file, argp);
case BTRFS_IOC_GET_FEATURES:
return btrfs_ioctl_get_features(file, argp);
case BTRFS_IOC_SET_FEATURES:
return btrfs_ioctl_set_features(file, argp);
}
return -ENOTTY;
}
View Git Blame Copy Permalink