int no_time_update);
/* Mask out flags that are inappropriate for the given type of inode. */
-static unsigned int btrfs_mask_flags(umode_t mode, unsigned int flags)
+static unsigned int btrfs_mask_fsflags_for_type(struct inode *inode,
+ unsigned int flags)
{
- if (S_ISDIR(mode))
+ if (S_ISDIR(inode->i_mode))
return flags;
- else if (S_ISREG(mode))
+ else if (S_ISREG(inode->i_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.
+ * Export internal inode flags to the format expected by the FS_IOC_GETFLAGS
+ * ioctl.
*/
-static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
+static unsigned int btrfs_inode_flags_to_fsflags(unsigned int flags)
{
unsigned int iflags = 0;
/*
* Update inode->i_flags based on the btrfs internal flags.
*/
-void btrfs_update_iflags(struct inode *inode)
+void btrfs_sync_inode_flags_to_i_flags(struct inode *inode)
{
- struct btrfs_inode *ip = BTRFS_I(inode);
+ struct btrfs_inode *binode = BTRFS_I(inode);
unsigned int new_fl = 0;
- if (ip->flags & BTRFS_INODE_SYNC)
+ if (binode->flags & BTRFS_INODE_SYNC)
new_fl |= S_SYNC;
- if (ip->flags & BTRFS_INODE_IMMUTABLE)
+ if (binode->flags & BTRFS_INODE_IMMUTABLE)
new_fl |= S_IMMUTABLE;
- if (ip->flags & BTRFS_INODE_APPEND)
+ if (binode->flags & BTRFS_INODE_APPEND)
new_fl |= S_APPEND;
- if (ip->flags & BTRFS_INODE_NOATIME)
+ if (binode->flags & BTRFS_INODE_NOATIME)
new_fl |= S_NOATIME;
- if (ip->flags & BTRFS_INODE_DIRSYNC)
+ if (binode->flags & BTRFS_INODE_DIRSYNC)
new_fl |= S_DIRSYNC;
set_mask_bits(&inode->i_flags,
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);
+ struct btrfs_inode *binode = BTRFS_I(file_inode(file));
+ unsigned int flags = btrfs_inode_flags_to_fsflags(binode->flags);
if (copy_to_user(arg, &flags, sizeof(flags)))
return -EFAULT;
return 0;
}
-static int check_flags(unsigned int flags)
+/* Check if @flags are a supported and valid set of FS_*_FL flags */
+static int check_fsflags(unsigned int flags)
{
if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
FS_NOATIME_FL | FS_NODUMP_FL | \
{
struct inode *inode = file_inode(file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_inode *ip = BTRFS_I(inode);
- struct btrfs_root *root = ip->root;
+ struct btrfs_inode *binode = BTRFS_I(inode);
+ struct btrfs_root *root = binode->root;
struct btrfs_trans_handle *trans;
- unsigned int flags, oldflags;
+ unsigned int fsflags, old_fsflags;
int ret;
- u64 ip_oldflags;
- unsigned int i_oldflags;
+ u64 old_flags;
+ unsigned int old_i_flags;
umode_t mode;
if (!inode_owner_or_capable(inode))
if (btrfs_root_readonly(root))
return -EROFS;
- if (copy_from_user(&flags, arg, sizeof(flags)))
+ if (copy_from_user(&fsflags, arg, sizeof(fsflags)))
return -EFAULT;
- ret = check_flags(flags);
+ ret = check_fsflags(fsflags);
if (ret)
return ret;
inode_lock(inode);
- ip_oldflags = ip->flags;
- i_oldflags = inode->i_flags;
+ old_flags = binode->flags;
+ old_i_flags = 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)) {
+ fsflags = btrfs_mask_fsflags_for_type(inode, fsflags);
+ old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags);
+ if ((fsflags ^ old_fsflags) & (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;
+ if (fsflags & FS_SYNC_FL)
+ binode->flags |= BTRFS_INODE_SYNC;
else
- ip->flags &= ~BTRFS_INODE_SYNC;
- if (flags & FS_IMMUTABLE_FL)
- ip->flags |= BTRFS_INODE_IMMUTABLE;
+ binode->flags &= ~BTRFS_INODE_SYNC;
+ if (fsflags & FS_IMMUTABLE_FL)
+ binode->flags |= BTRFS_INODE_IMMUTABLE;
else
- ip->flags &= ~BTRFS_INODE_IMMUTABLE;
- if (flags & FS_APPEND_FL)
- ip->flags |= BTRFS_INODE_APPEND;
+ binode->flags &= ~BTRFS_INODE_IMMUTABLE;
+ if (fsflags & FS_APPEND_FL)
+ binode->flags |= BTRFS_INODE_APPEND;
else
- ip->flags &= ~BTRFS_INODE_APPEND;
- if (flags & FS_NODUMP_FL)
- ip->flags |= BTRFS_INODE_NODUMP;
+ binode->flags &= ~BTRFS_INODE_APPEND;
+ if (fsflags & FS_NODUMP_FL)
+ binode->flags |= BTRFS_INODE_NODUMP;
else
- ip->flags &= ~BTRFS_INODE_NODUMP;
- if (flags & FS_NOATIME_FL)
- ip->flags |= BTRFS_INODE_NOATIME;
+ binode->flags &= ~BTRFS_INODE_NODUMP;
+ if (fsflags & FS_NOATIME_FL)
+ binode->flags |= BTRFS_INODE_NOATIME;
else
- ip->flags &= ~BTRFS_INODE_NOATIME;
- if (flags & FS_DIRSYNC_FL)
- ip->flags |= BTRFS_INODE_DIRSYNC;
+ binode->flags &= ~BTRFS_INODE_NOATIME;
+ if (fsflags & FS_DIRSYNC_FL)
+ binode->flags |= BTRFS_INODE_DIRSYNC;
else
- ip->flags &= ~BTRFS_INODE_DIRSYNC;
- if (flags & FS_NOCOW_FL) {
+ binode->flags &= ~BTRFS_INODE_DIRSYNC;
+ if (fsflags & FS_NOCOW_FL) {
if (S_ISREG(mode)) {
/*
* It's safe to turn csums off here, no extents exist.
* status of the file and will not set it.
*/
if (inode->i_size == 0)
- ip->flags |= BTRFS_INODE_NODATACOW
- | BTRFS_INODE_NODATASUM;
+ binode->flags |= BTRFS_INODE_NODATACOW
+ | BTRFS_INODE_NODATASUM;
} else {
- ip->flags |= BTRFS_INODE_NODATACOW;
+ binode->flags |= BTRFS_INODE_NODATACOW;
}
} else {
/*
*/
if (S_ISREG(mode)) {
if (inode->i_size == 0)
- ip->flags &= ~(BTRFS_INODE_NODATACOW
+ binode->flags &= ~(BTRFS_INODE_NODATACOW
| BTRFS_INODE_NODATASUM);
} else {
- ip->flags &= ~BTRFS_INODE_NODATACOW;
+ binode->flags &= ~BTRFS_INODE_NODATACOW;
}
}
* 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;
+ if (fsflags & FS_NOCOMP_FL) {
+ binode->flags &= ~BTRFS_INODE_COMPRESS;
+ binode->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) {
+ } else if (fsflags & FS_COMPR_FL) {
const char *comp;
- ip->flags |= BTRFS_INODE_COMPRESS;
- ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+ binode->flags |= BTRFS_INODE_COMPRESS;
+ binode->flags &= ~BTRFS_INODE_NOCOMPRESS;
comp = btrfs_compress_type2str(fs_info->compress_type);
if (!comp || comp[0] == 0)
ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
if (ret && ret != -ENODATA)
goto out_drop;
- ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
+ binode->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
trans = btrfs_start_transaction(root, 1);
goto out_drop;
}
- btrfs_update_iflags(inode);
+ btrfs_sync_inode_flags_to_i_flags(inode);
inode_inc_iversion(inode);
inode->i_ctime = current_time(inode);
ret = btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans);
out_drop:
if (ret) {
- ip->flags = ip_oldflags;
- inode->i_flags = i_oldflags;
+ binode->flags = old_flags;
+ inode->i_flags = old_i_flags;
}
out_unlock:
return ret;
}
+/*
+ * Translate btrfs internal inode flags to xflags as expected by the
+ * FS_IOC_FSGETXATT ioctl. Filter only the supported ones, unknown flags are
+ * silently dropped.
+ */
+static unsigned int btrfs_inode_flags_to_xflags(unsigned int flags)
+{
+ unsigned int xflags = 0;
+
+ if (flags & BTRFS_INODE_APPEND)
+ xflags |= FS_XFLAG_APPEND;
+ if (flags & BTRFS_INODE_IMMUTABLE)
+ xflags |= FS_XFLAG_IMMUTABLE;
+ if (flags & BTRFS_INODE_NOATIME)
+ xflags |= FS_XFLAG_NOATIME;
+ if (flags & BTRFS_INODE_NODUMP)
+ xflags |= FS_XFLAG_NODUMP;
+ if (flags & BTRFS_INODE_SYNC)
+ xflags |= FS_XFLAG_SYNC;
+
+ return xflags;
+}
+
+/* Check if @flags are a supported and valid set of FS_XFLAGS_* flags */
+static int check_xflags(unsigned int flags)
+{
+ if (flags & ~(FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE | FS_XFLAG_NOATIME |
+ FS_XFLAG_NODUMP | FS_XFLAG_SYNC))
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+/*
+ * Set the xflags from the internal inode flags. The remaining items of fsxattr
+ * are zeroed.
+ */
+static int btrfs_ioctl_fsgetxattr(struct file *file, void __user *arg)
+{
+ struct btrfs_inode *binode = BTRFS_I(file_inode(file));
+ struct fsxattr fa;
+
+ memset(&fa, 0, sizeof(fa));
+ fa.fsx_xflags = btrfs_inode_flags_to_xflags(binode->flags);
+
+ if (copy_to_user(arg, &fa, sizeof(fa)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg)
+{
+ struct inode *inode = file_inode(file);
+ struct btrfs_inode *binode = BTRFS_I(inode);
+ struct btrfs_root *root = binode->root;
+ struct btrfs_trans_handle *trans;
+ struct fsxattr fa;
+ unsigned old_flags;
+ unsigned old_i_flags;
+ int ret = 0;
+
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
+ if (btrfs_root_readonly(root))
+ return -EROFS;
+
+ memset(&fa, 0, sizeof(fa));
+ if (copy_from_user(&fa, arg, sizeof(fa)))
+ return -EFAULT;
+
+ ret = check_xflags(fa.fsx_xflags);
+ if (ret)
+ return ret;
+
+ if (fa.fsx_extsize != 0 || fa.fsx_projid != 0 || fa.fsx_cowextsize != 0)
+ return -EOPNOTSUPP;
+
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ old_flags = binode->flags;
+ old_i_flags = inode->i_flags;
+
+ /* We need the capabilities to change append-only or immutable inode */
+ if (((old_flags & (BTRFS_INODE_APPEND | BTRFS_INODE_IMMUTABLE)) ||
+ (fa.fsx_xflags & (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE))) &&
+ !capable(CAP_LINUX_IMMUTABLE)) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
+ if (fa.fsx_xflags & FS_XFLAG_SYNC)
+ binode->flags |= BTRFS_INODE_SYNC;
+ else
+ binode->flags &= ~BTRFS_INODE_SYNC;
+ if (fa.fsx_xflags & FS_XFLAG_IMMUTABLE)
+ binode->flags |= BTRFS_INODE_IMMUTABLE;
+ else
+ binode->flags &= ~BTRFS_INODE_IMMUTABLE;
+ if (fa.fsx_xflags & FS_XFLAG_APPEND)
+ binode->flags |= BTRFS_INODE_APPEND;
+ else
+ binode->flags &= ~BTRFS_INODE_APPEND;
+ if (fa.fsx_xflags & FS_XFLAG_NODUMP)
+ binode->flags |= BTRFS_INODE_NODUMP;
+ else
+ binode->flags &= ~BTRFS_INODE_NODUMP;
+ if (fa.fsx_xflags & FS_XFLAG_NOATIME)
+ binode->flags |= BTRFS_INODE_NOATIME;
+ else
+ binode->flags &= ~BTRFS_INODE_NOATIME;
+
+ /* 1 item for the inode */
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_unlock;
+ }
+
+ btrfs_sync_inode_flags_to_i_flags(inode);
+ inode_inc_iversion(inode);
+ inode->i_ctime = current_time(inode);
+ ret = btrfs_update_inode(trans, root, inode);
+
+ btrfs_end_transaction(trans);
+
+out_unlock:
+ if (ret) {
+ binode->flags = old_flags;
+ inode->i_flags = old_i_flags;
+ }
+
+ inode_unlock(inode);
+ mnt_drop_write_file(file);
+
+ return ret;
+}
+
static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
struct inode *inode = file_inode(file);
wait_event(root->subv_writers->wait,
percpu_counter_sum(&root->subv_writers->counter) == 0);
- ret = btrfs_start_delalloc_inodes(root, 0);
+ ret = btrfs_start_delalloc_inodes(root);
if (ret)
goto dec_and_free;
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
- mutex_lock(&fs_info->volume_mutex);
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
out_free:
kfree(vol_args);
out:
- mutex_unlock(&fs_info->volume_mutex);
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
mnt_drop_write_file(file);
return ret;
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 root_flags;
- u64 qgroup_reserved;
int namelen;
- int ret;
int err = 0;
if (!S_ISDIR(dir->i_mode))
}
inode_lock(inode);
-
- /*
- * Don't allow to delete a subvolume with send in progress. This is
- * inside the i_mutex so the error handling that has to drop the bit
- * again is not run concurrently.
- */
- spin_lock(&dest->root_item_lock);
- root_flags = btrfs_root_flags(&dest->root_item);
- if (dest->send_in_progress == 0) {
- btrfs_set_root_flags(&dest->root_item,
- root_flags | BTRFS_ROOT_SUBVOL_DEAD);
- spin_unlock(&dest->root_item_lock);
- } else {
- spin_unlock(&dest->root_item_lock);
- btrfs_warn(fs_info,
- "Attempt to delete subvolume %llu during send",
- dest->root_key.objectid);
- err = -EPERM;
- goto out_unlock_inode;
- }
-
- down_write(&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;
-
- btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
-
- 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, 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 (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
- ret = btrfs_insert_orphan_item(trans,
- fs_info->tree_root,
- dest->root_key.objectid);
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- err = ret;
- goto out_end_trans;
- }
- }
-
- ret = btrfs_uuid_tree_rem(trans, fs_info, dest->root_item.uuid,
- BTRFS_UUID_KEY_SUBVOL,
- dest->root_key.objectid);
- if (ret && ret != -ENOENT) {
- btrfs_abort_transaction(trans, ret);
- err = ret;
- goto out_end_trans;
- }
- if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
- ret = btrfs_uuid_tree_rem(trans, fs_info,
- dest->root_item.received_uuid,
- BTRFS_UUID_KEY_RECEIVED_SUBVOL,
- dest->root_key.objectid);
- if (ret && ret != -ENOENT) {
- btrfs_abort_transaction(trans, ret);
- err = ret;
- goto out_end_trans;
- }
- }
-
-out_end_trans:
- trans->block_rsv = NULL;
- trans->bytes_reserved = 0;
- ret = btrfs_end_transaction(trans);
- if (ret && !err)
- err = ret;
- inode->i_flags |= S_DEAD;
-out_release:
- btrfs_subvolume_release_metadata(fs_info, &block_rsv);
-out_up_write:
- up_write(&fs_info->subvol_sem);
- if (err) {
- spin_lock(&dest->root_item_lock);
- root_flags = btrfs_root_flags(&dest->root_item);
- btrfs_set_root_flags(&dest->root_item,
- root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
- spin_unlock(&dest->root_item_lock);
- }
-out_unlock_inode:
+ err = btrfs_delete_subvolume(dir, dentry);
inode_unlock(inode);
- if (!err) {
- d_invalidate(dentry);
- btrfs_invalidate_inodes(dest);
+ if (!err)
d_delete(dentry);
- ASSERT(dest->send_in_progress == 0);
- /* the last ref */
- if (dest->ino_cache_inode) {
- iput(dest->ino_cache_inode);
- dest->ino_cache_inode = NULL;
- }
- }
out_dput:
dput(dentry);
out_unlock_dir:
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
- mutex_lock(&fs_info->volume_mutex);
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
kfree(vol_args);
out:
- mutex_unlock(&fs_info->volume_mutex);
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
return ret;
}
put_page(pg);
}
}
- kfree(cmp->src_pages);
- kfree(cmp->dst_pages);
}
static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
{
int ret;
int num_pages = PAGE_ALIGN(len) >> PAGE_SHIFT;
- struct page **src_pgarr, **dst_pgarr;
- /*
- * We must gather up all the pages before we initiate our
- * extent locking. We use an array for the page pointers. Size
- * of the array is bounded by len, which is in turn bounded by
- * BTRFS_MAX_DEDUPE_LEN.
- */
- src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
- dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
- if (!src_pgarr || !dst_pgarr) {
- kfree(src_pgarr);
- kfree(dst_pgarr);
- return -ENOMEM;
- }
cmp->num_pages = num_pages;
- cmp->src_pages = src_pgarr;
- cmp->dst_pages = dst_pgarr;
-
- /*
- * If deduping ranges in the same inode, locking rules make it mandatory
- * to always lock pages in ascending order to avoid deadlocks with
- * concurrent tasks (such as starting writeback/delalloc).
- */
- if (src == dst && dst_loff < loff) {
- swap(src_pgarr, dst_pgarr);
- swap(loff, dst_loff);
- }
- ret = gather_extent_pages(src, src_pgarr, cmp->num_pages, loff);
+ ret = gather_extent_pages(src, cmp->src_pages, num_pages, loff);
if (ret)
goto out;
- ret = gather_extent_pages(dst, dst_pgarr, cmp->num_pages, dst_loff);
+ ret = gather_extent_pages(dst, cmp->dst_pages, num_pages, dst_loff);
out:
if (ret)
return 0;
}
-static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
- struct inode *dst, u64 dst_loff)
+static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
+ struct inode *dst, u64 dst_loff,
+ struct cmp_pages *cmp)
{
int ret;
u64 len = olen;
- struct cmp_pages cmp;
bool same_inode = (src == dst);
u64 same_lock_start = 0;
u64 same_lock_len = 0;
- if (len == 0)
- return 0;
-
- if (same_inode)
- inode_lock(src);
- else
- btrfs_double_inode_lock(src, dst);
-
ret = extent_same_check_offsets(src, loff, &len, olen);
if (ret)
- goto out_unlock;
+ return ret;
ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
if (ret)
- goto out_unlock;
+ return ret;
if (same_inode) {
/*
* allow an unaligned length so long as it ends at
* i_size.
*/
- if (len != olen) {
- ret = -EINVAL;
- goto out_unlock;
- }
+ if (len != olen)
+ return -EINVAL;
/* Check for overlapping ranges */
- if (dst_loff + len > loff && dst_loff < loff + len) {
- ret = -EINVAL;
- goto out_unlock;
- }
+ if (dst_loff + len > loff && dst_loff < loff + len)
+ return -EINVAL;
same_lock_start = min_t(u64, loff, dst_loff);
same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start;
}
- /* 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;
- }
-
again:
- ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
+ ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, cmp);
if (ret)
- goto out_unlock;
+ return ret;
if (same_inode)
ret = lock_extent_range(src, same_lock_start, same_lock_len,
* Ranges in the io trees already unlocked. Now unlock all
* pages before waiting for all IO to complete.
*/
- btrfs_cmp_data_free(&cmp);
+ btrfs_cmp_data_free(cmp);
if (same_inode) {
btrfs_wait_ordered_range(src, same_lock_start,
same_lock_len);
ASSERT(ret == 0);
if (WARN_ON(ret)) {
/* ranges in the io trees already unlocked */
- btrfs_cmp_data_free(&cmp);
+ btrfs_cmp_data_free(cmp);
return ret;
}
/* pass original length for comparison so we stay within i_size */
- ret = btrfs_cmp_data(olen, &cmp);
+ ret = btrfs_cmp_data(olen, cmp);
if (ret == 0)
ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
else
btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
- btrfs_cmp_data_free(&cmp);
+ btrfs_cmp_data_free(cmp);
+
+ return ret;
+}
+
+#define BTRFS_MAX_DEDUPE_LEN SZ_16M
+
+static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
+ struct inode *dst, u64 dst_loff)
+{
+ int ret;
+ struct cmp_pages cmp;
+ int num_pages = PAGE_ALIGN(BTRFS_MAX_DEDUPE_LEN) >> PAGE_SHIFT;
+ bool same_inode = (src == dst);
+ u64 i, tail_len, chunk_count;
+
+ if (olen == 0)
+ return 0;
+
+ if (same_inode)
+ inode_lock(src);
+ else
+ btrfs_double_inode_lock(src, dst);
+
+ /* 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;
+ }
+
+ tail_len = olen % BTRFS_MAX_DEDUPE_LEN;
+ chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN);
+ if (chunk_count == 0)
+ num_pages = PAGE_ALIGN(tail_len) >> PAGE_SHIFT;
+
+ /*
+ * If deduping ranges in the same inode, locking rules make it
+ * mandatory to always lock pages in ascending order to avoid deadlocks
+ * with concurrent tasks (such as starting writeback/delalloc).
+ */
+ if (same_inode && dst_loff < loff)
+ swap(loff, dst_loff);
+
+ /*
+ * We must gather up all the pages before we initiate our extent
+ * locking. We use an array for the page pointers. Size of the array is
+ * bounded by len, which is in turn bounded by BTRFS_MAX_DEDUPE_LEN.
+ */
+ cmp.src_pages = kvmalloc_array(num_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_ZERO);
+ cmp.dst_pages = kvmalloc_array(num_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!cmp.src_pages || !cmp.dst_pages) {
+ ret = -ENOMEM;
+ goto out_free;
+ }
+
+ for (i = 0; i < chunk_count; i++) {
+ ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
+ dst, dst_loff, &cmp);
+ if (ret)
+ goto out_unlock;
+
+ loff += BTRFS_MAX_DEDUPE_LEN;
+ dst_loff += BTRFS_MAX_DEDUPE_LEN;
+ }
+
+ if (tail_len > 0)
+ ret = btrfs_extent_same_range(src, loff, tail_len, dst,
+ dst_loff, &cmp);
+
out_unlock:
if (same_inode)
inode_unlock(src);
else
btrfs_double_inode_unlock(src, dst);
+out_free:
+ kvfree(cmp.src_pages);
+ kvfree(cmp.dst_pages);
+
return ret;
}
-#define BTRFS_MAX_DEDUPE_LEN SZ_16M
-
ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
struct file *dst_file, u64 dst_loff)
{
u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
ssize_t res;
- if (olen > BTRFS_MAX_DEDUPE_LEN)
- olen = BTRFS_MAX_DEDUPE_LEN;
-
if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
/*
* Btrfs does not support blocksize < page_size. As a
return ret;
}
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
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))
+ if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags))
bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
if (atomic_read(&fs_info->balance_pause_req))
bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
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));
- }
+ spin_lock(&fs_info->balance_lock);
+ memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+ spin_unlock(&fs_info->balance_lock);
}
static long btrfs_ioctl_balance(struct file *file, void __user *arg)
again:
if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
- mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
need_unlock = true;
goto locked;
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl) {
/* this is either (2) or (3) */
- if (!atomic_read(&fs_info->balance_running)) {
+ if (!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
mutex_unlock(&fs_info->balance_mutex);
- if (!mutex_trylock(&fs_info->volume_mutex))
- goto again;
+ /*
+ * Lock released to allow other waiters to continue,
+ * we'll reexamine the status again.
+ */
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl &&
- !atomic_read(&fs_info->balance_running)) {
+ !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
/* 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) */
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));
do_balance:
/*
- * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP
- * 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. The flag is cleared in __cancel_balance.
+ * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP goes to
+ * btrfs_balance. bctl is freed in reset_balance_state, or, if
+ * restriper was paused all the way until unmount, in free_fs_info.
+ * The flag should be cleared after reset_balance_state.
*/
need_unlock = false;
- ret = btrfs_balance(bctl, bargs);
+ ret = btrfs_balance(fs_info, bctl, bargs);
bctl = NULL;
if (arg) {
kfree(bargs);
out_unlock:
mutex_unlock(&fs_info->balance_mutex);
- mutex_unlock(&fs_info->volume_mutex);
if (need_unlock)
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
out:
goto out;
}
- update_ioctl_balance_args(fs_info, 1, bargs);
+ btrfs_update_ioctl_balance_args(fs_info, bargs);
if (copy_to_user(arg, bargs, sizeof(*bargs)))
ret = -EFAULT;
case BTRFS_IOC_SYNC: {
int ret;
- ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
+ ret = btrfs_start_delalloc_roots(fs_info, -1);
if (ret)
return ret;
ret = btrfs_sync_fs(inode->i_sb, 1);
return btrfs_ioctl_get_features(file, argp);
case BTRFS_IOC_SET_FEATURES:
return btrfs_ioctl_set_features(file, argp);
+ case FS_IOC_FSGETXATTR:
+ return btrfs_ioctl_fsgetxattr(file, argp);
+ case FS_IOC_FSSETXATTR:
+ return btrfs_ioctl_fssetxattr(file, argp);
}
return -ENOTTY;
git.samba.org / sfrench / cifs-2.6.git / blobdiff