diff options
Diffstat (limited to 'fs/btrfs/ioctl.c')
-rw-r--r-- | fs/btrfs/ioctl.c | 350 |
1 files changed, 288 insertions, 62 deletions
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a205027..ba26540 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -51,6 +51,7 @@ #include "volumes.h" #include "locking.h" #include "inode-map.h" +#include "backref.h" /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags) @@ -117,7 +118,7 @@ void btrfs_update_iflags(struct inode *inode) /* * Inherit flags from the parent inode. * - * Unlike extN we don't have any flags we don't want to inherit currently. + * Currently only the compression flags and the cow flags are inherited. */ void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) { @@ -128,12 +129,17 @@ void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) flags = BTRFS_I(dir)->flags; - if (S_ISREG(inode->i_mode)) - flags &= ~BTRFS_INODE_DIRSYNC; - else if (!S_ISDIR(inode->i_mode)) - flags &= (BTRFS_INODE_NODUMP | BTRFS_INODE_NOATIME); + 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; - BTRFS_I(inode)->flags = flags; btrfs_update_iflags(inode); } @@ -246,11 +252,11 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) trans = btrfs_join_transaction(root); BUG_ON(IS_ERR(trans)); + btrfs_update_iflags(inode); + inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); - btrfs_update_iflags(inode); - inode->i_ctime = CURRENT_TIME; btrfs_end_transaction(trans, root); mnt_drop_write(file->f_path.mnt); @@ -277,6 +283,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; + u64 total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy); int ret; if (!capable(CAP_SYS_ADMIN)) @@ -295,12 +302,15 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) } } rcu_read_unlock(); + if (!num_devices) return -EOPNOTSUPP; - if (copy_from_user(&range, arg, sizeof(range))) return -EFAULT; + if (range.start > total_bytes) + return -EINVAL; + range.len = min(range.len, total_bytes - range.start); range.minlen = max(range.minlen, minlen); ret = btrfs_trim_fs(root, &range); if (ret < 0) @@ -323,7 +333,7 @@ static noinline int create_subvol(struct btrfs_root *root, struct btrfs_inode_item *inode_item; struct extent_buffer *leaf; struct btrfs_root *new_root; - struct dentry *parent = dget_parent(dentry); + struct dentry *parent = dentry->d_parent; struct inode *dir; int ret; int err; @@ -332,10 +342,8 @@ static noinline int create_subvol(struct btrfs_root *root, u64 index = 0; ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid); - if (ret) { - dput(parent); + if (ret) return ret; - } dir = parent->d_inode; @@ -346,10 +354,8 @@ static noinline int create_subvol(struct btrfs_root *root, * 2 - dir items */ trans = btrfs_start_transaction(root, 6); - if (IS_ERR(trans)) { - dput(parent); + if (IS_ERR(trans)) return PTR_ERR(trans); - } leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, objectid, NULL, 0, 0, 0); @@ -439,7 +445,6 @@ static noinline int create_subvol(struct btrfs_root *root, d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry)); fail: - dput(parent); if (async_transid) { *async_transid = trans->transid; err = btrfs_commit_transaction_async(trans, root, 1); @@ -456,7 +461,6 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, bool readonly) { struct inode *inode; - struct dentry *parent; struct btrfs_pending_snapshot *pending_snapshot; struct btrfs_trans_handle *trans; int ret; @@ -504,9 +508,7 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, if (ret) goto fail; - parent = dget_parent(dentry); - inode = btrfs_lookup_dentry(parent->d_inode, dentry); - dput(parent); + inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto fail; @@ -768,7 +770,7 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len, int ret = 1; /* - * make sure that once we start defragging and extent, we keep on + * make sure that once we start defragging an extent, we keep on * defragging it */ if (start < *defrag_end) @@ -813,7 +815,6 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len, * extent will force at least part of that big extent to be defragged. */ if (ret) { - *last_len += len; *defrag_end = extent_map_end(em); } else { *last_len = 0; @@ -851,13 +852,16 @@ static int cluster_pages_for_defrag(struct inode *inode, int i_done; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); if (isize == 0) return 0; file_end = (isize - 1) >> PAGE_CACHE_SHIFT; + mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_space(inode, num_pages << PAGE_CACHE_SHIFT); + mutex_unlock(&inode->i_mutex); if (ret) return ret; again: @@ -867,8 +871,8 @@ again: /* step one, lock all the pages */ for (i = 0; i < num_pages; i++) { struct page *page; - page = grab_cache_page(inode->i_mapping, - start_index + i); + page = find_or_create_page(inode->i_mapping, + start_index + i, mask); if (!page) break; @@ -938,7 +942,9 @@ again: GFP_NOFS); if (i_done != num_pages) { - atomic_inc(&BTRFS_I(inode)->outstanding_extents); + spin_lock(&BTRFS_I(inode)->lock); + BTRFS_I(inode)->outstanding_extents++; + spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, (num_pages - i_done) << PAGE_CACHE_SHIFT); } @@ -978,18 +984,20 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, struct btrfs_super_block *disk_super; struct file_ra_state *ra = NULL; unsigned long last_index; + u64 isize = i_size_read(inode); u64 features; u64 last_len = 0; u64 skip = 0; u64 defrag_end = 0; u64 newer_off = range->start; - int newer_left = 0; 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 newer_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT; + int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT; + int cluster = max_cluster; u64 new_align = ~((u64)128 * 1024 - 1); struct page **pages = NULL; @@ -1003,7 +1011,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, compress_type = range->compress_type; } - if (inode->i_size == 0) + if (isize == 0) return 0; /* @@ -1019,7 +1027,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, ra = &file->f_ra; } - pages = kmalloc(sizeof(struct page *) * newer_cluster, + pages = kmalloc(sizeof(struct page *) * max_cluster, GFP_NOFS); if (!pages) { ret = -ENOMEM; @@ -1028,10 +1036,10 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, /* find the last page to defrag */ if (range->start + range->len > range->start) { - last_index = min_t(u64, inode->i_size - 1, + last_index = min_t(u64, isize - 1, range->start + range->len - 1) >> PAGE_CACHE_SHIFT; } else { - last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT; + last_index = (isize - 1) >> PAGE_CACHE_SHIFT; } if (newer_than) { @@ -1044,16 +1052,24 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, * the extents in the file evenly spaced */ i = (newer_off & new_align) >> PAGE_CACHE_SHIFT; - newer_left = newer_cluster; } else goto out_ra; } else { i = range->start >> PAGE_CACHE_SHIFT; } if (!max_to_defrag) - max_to_defrag = last_index - 1; + max_to_defrag = last_index; - while (i <= last_index && defrag_count < max_to_defrag) { + /* + * 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 @@ -1076,18 +1092,31 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, 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 (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) BTRFS_I(inode)->force_compress = compress_type; - btrfs_force_ra(inode->i_mapping, ra, file, i, newer_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; + } - ret = cluster_pages_for_defrag(inode, pages, i, newer_cluster); + ret = cluster_pages_for_defrag(inode, pages, i, cluster); if (ret < 0) goto out_ra; defrag_count += ret; balance_dirty_pages_ratelimited_nr(inode->i_mapping, ret); - i += ret; if (newer_than) { if (newer_off == (u64)-1) @@ -1102,12 +1131,17 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (!ret) { range->start = newer_off; i = (newer_off & new_align) >> PAGE_CACHE_SHIFT; - newer_left = newer_cluster; } else { break; } } else { - i++; + if (ret > 0) { + i += ret; + last_len += ret << PAGE_CACHE_SHIFT; + } else { + i++; + last_len = 0; + } } } @@ -1133,16 +1167,14 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, mutex_unlock(&inode->i_mutex); } - disk_super = &root->fs_info->super_copy; + disk_super = root->fs_info->super_copy; features = btrfs_super_incompat_flags(disk_super); if (range->compress_type == BTRFS_COMPRESS_LZO) { features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; btrfs_set_super_incompat_flags(disk_super, features); } - if (!file) - kfree(ra); - return defrag_count; + ret = defrag_count; out_ra: if (!file) @@ -1186,12 +1218,12 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, *devstr = '\0'; devstr = vol_args->name; devid = simple_strtoull(devstr, &end, 10); - printk(KERN_INFO "resizing devid %llu\n", + printk(KERN_INFO "btrfs: resizing devid %llu\n", (unsigned long long)devid); } device = btrfs_find_device(root, devid, NULL, NULL); if (!device) { - printk(KERN_INFO "resizer unable to find device %llu\n", + printk(KERN_INFO "btrfs: resizer unable to find device %llu\n", (unsigned long long)devid); ret = -EINVAL; goto out_unlock; @@ -1237,7 +1269,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, do_div(new_size, root->sectorsize); new_size *= root->sectorsize; - printk(KERN_INFO "new size for %s is %llu\n", + printk(KERN_INFO "btrfs: new size for %s is %llu\n", device->name, (unsigned long long)new_size); if (new_size > old_size) { @@ -1248,7 +1280,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans, root); - } else { + } else if (new_size < old_size) { ret = btrfs_shrink_device(device, new_size); } @@ -1295,12 +1327,17 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, printk(KERN_INFO "btrfs: Snapshot src from " "another FS\n"); ret = -EINVAL; - fput(src_file); - goto out; + } else if (!inode_owner_or_capable(src_inode)) { + /* + * Subvolume creation is not restricted, but snapshots + * are limited to own subvolumes only + */ + ret = -EPERM; + } else { + ret = btrfs_mksubvol(&file->f_path, name, namelen, + BTRFS_I(src_inode)->root, + transid, readonly); } - ret = btrfs_mksubvol(&file->f_path, name, namelen, - BTRFS_I(src_inode)->root, - transid, readonly); fput(src_file); } out: @@ -1755,11 +1792,10 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid; - } if (ptr < name) goto out; - memcpy(name, ptr, total_len); + memmove(name, ptr, total_len); name[total_len]='\0'; ret = 0; out: @@ -2184,6 +2220,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (!(src_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; @@ -2222,11 +2263,26 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (off + len == src->i_size) len = ALIGN(src->i_size, bs) - off; + if (len == 0) { + ret = 0; + goto out_unlock; + } + /* verify the end result is block aligned */ if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || !IS_ALIGNED(destoff, bs)) 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); + /* do any pending delalloc/csum calc on src, one way or another, and lock file content */ while (1) { @@ -2320,7 +2376,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, else new_key.offset = destoff; - trans = btrfs_start_transaction(root, 1); + /* + * 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; @@ -2328,14 +2389,21 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, 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; } - if (key.offset + datal > off + len) - datal = off + len - key.offset; - ret = btrfs_drop_extents(trans, inode, new_key.offset, new_key.offset + datal, @@ -2380,6 +2448,20 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, new_key.offset += skip; } + /* + * Don't copy an inline extent into an offset + * greater than zero. Having an inline extent + * at such an offset results in chaos as btrfs + * isn't prepared for such cases. Just skip + * this case for the same reasons as commented + * at btrfs_ioctl_clone(). + */ + if (new_key.offset > 0) { + ret = -EOPNOTSUPP; + btrfs_end_transaction(trans, root); + goto out; + } + if (key.offset + datal > off+len) trim = key.offset + datal - (off+len); @@ -2432,7 +2514,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (endoff > inode->i_size) btrfs_i_size_write(inode, endoff); - BTRFS_I(inode)->flags = BTRFS_I(src)->flags; ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); btrfs_end_transaction(trans, root); @@ -2559,7 +2640,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) return PTR_ERR(trans); } - dir_id = btrfs_super_root_dir(&root->fs_info->super_copy); + 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)) { @@ -2575,7 +2656,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) btrfs_mark_buffer_dirty(path->nodes[0]); btrfs_free_path(path); - disk_super = &root->fs_info->super_copy; + disk_super = root->fs_info->super_copy; features = btrfs_super_incompat_flags(disk_super); if (!(features & BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL)) { features |= BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL; @@ -2836,6 +2917,147 @@ static long btrfs_ioctl_scrub_progress(struct btrfs_root *root, 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_SYS_ADMIN)) + return -EPERM; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + ipa = memdup_user(arg, sizeof(*ipa)); + if (IS_ERR(ipa)) { + ret = PTR_ERR(ipa); + ipa = NULL; + goto out; + } + + size = min_t(u32, ipa->size, 4096); + ipath = init_ipath(size, root, path); + if (IS_ERR(ipath)) { + ret = PTR_ERR(ipath); + ipath = NULL; + goto out; + } + + ret = paths_from_inode(ipa->inum, ipath); + if (ret < 0) + goto out; + + for (i = 0; i < ipath->fspath->elem_cnt; ++i) { + 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; + u64 extent_offset; + struct btrfs_ioctl_logical_ino_args *loi; + struct btrfs_data_container *inodes = NULL; + struct btrfs_path *path = NULL; + struct btrfs_key key; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + loi = memdup_user(arg, sizeof(*loi)); + if (IS_ERR(loi)) { + ret = PTR_ERR(loi); + loi = NULL; + goto out; + } + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + size = min_t(u32, loi->size, 4096); + inodes = init_data_container(size); + if (IS_ERR(inodes)) { + ret = PTR_ERR(inodes); + inodes = NULL; + goto out; + } + + ret = extent_from_logical(root->fs_info, loi->logical, path, &key); + + if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) + ret = -ENOENT; + if (ret < 0) + goto out; + + extent_offset = loi->logical - key.objectid; + ret = iterate_extent_inodes(root->fs_info, path, key.objectid, + extent_offset, build_ino_list, inodes); + + if (ret < 0) + goto out; + + ret = copy_to_user((void *)(unsigned long)loi->inodes, + (void *)(unsigned long)inodes, size); + if (ret) + ret = -EFAULT; + +out: + btrfs_free_path(path); + kfree(inodes); + kfree(loi); + + return ret; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2893,6 +3115,10 @@ long btrfs_ioctl(struct file *file, unsigned int 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_SYNC: |