diff options
Diffstat (limited to 'fs/btrfs/ioctl.c')
| -rw-r--r-- | fs/btrfs/ioctl.c | 3042 |
1 files changed, 1670 insertions, 1372 deletions
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a5bd6926f7ff..acb484546b1d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -28,16 +28,16 @@ #include <linux/iversion.h> #include <linux/fileattr.h> #include <linux/fsverity.h> +#include <linux/sched/xacct.h> +#include <linux/io_uring/cmd.h> #include "ctree.h" #include "disk-io.h" #include "export.h" #include "transaction.h" #include "btrfs_inode.h" -#include "print-tree.h" #include "volumes.h" #include "locking.h" #include "backref.h" -#include "rcu-string.h" #include "send.h" #include "dev-replace.h" #include "props.h" @@ -46,9 +46,18 @@ #include "tree-log.h" #include "compression.h" #include "space-info.h" -#include "delalloc-space.h" #include "block-group.h" -#include "subpage.h" +#include "fs.h" +#include "accessors.h" +#include "extent-tree.h" +#include "root-tree.h" +#include "defrag.h" +#include "dir-item.h" +#include "uuid-tree.h" +#include "ioctl.h" +#include "file.h" +#include "scrub.h" +#include "super.h" #ifdef CONFIG_64BIT /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI @@ -88,11 +97,29 @@ struct btrfs_ioctl_send_args_32 { #define BTRFS_IOC_SEND_32 _IOW(BTRFS_IOCTL_MAGIC, 38, \ struct btrfs_ioctl_send_args_32) + +struct btrfs_ioctl_encoded_io_args_32 { + compat_uptr_t iov; + compat_ulong_t iovcnt; + __s64 offset; + __u64 flags; + __u64 len; + __u64 unencoded_len; + __u64 unencoded_offset; + __u32 compression; + __u32 encryption; + __u8 reserved[64]; +}; + +#define BTRFS_IOC_ENCODED_READ_32 _IOR(BTRFS_IOCTL_MAGIC, 64, \ + struct btrfs_ioctl_encoded_io_args_32) +#define BTRFS_IOC_ENCODED_WRITE_32 _IOW(BTRFS_IOCTL_MAGIC, 64, \ + struct btrfs_ioctl_encoded_io_args_32) #endif /* Mask out flags that are inappropriate for the given type of inode. */ -static unsigned int btrfs_mask_fsflags_for_type(struct inode *inode, - unsigned int flags) +static unsigned int btrfs_mask_fsflags_for_type(const struct inode *inode, + unsigned int flags) { if (S_ISDIR(inode->i_mode)) return flags; @@ -106,11 +133,11 @@ static unsigned int btrfs_mask_fsflags_for_type(struct inode *inode, * Export internal inode flags to the format expected by the FS_IOC_GETFLAGS * ioctl. */ -static unsigned int btrfs_inode_flags_to_fsflags(struct btrfs_inode *binode) +static unsigned int btrfs_inode_flags_to_fsflags(const struct btrfs_inode *inode) { unsigned int iflags = 0; - u32 flags = binode->flags; - u32 ro_flags = binode->ro_flags; + u32 flags = inode->flags; + u32 ro_flags = inode->ro_flags; if (flags & BTRFS_INODE_SYNC) iflags |= FS_SYNC_FL; @@ -140,25 +167,24 @@ static unsigned int btrfs_inode_flags_to_fsflags(struct btrfs_inode *binode) /* * Update inode->i_flags based on the btrfs internal flags. */ -void btrfs_sync_inode_flags_to_i_flags(struct inode *inode) +void btrfs_sync_inode_flags_to_i_flags(struct btrfs_inode *inode) { - struct btrfs_inode *binode = BTRFS_I(inode); unsigned int new_fl = 0; - if (binode->flags & BTRFS_INODE_SYNC) + if (inode->flags & BTRFS_INODE_SYNC) new_fl |= S_SYNC; - if (binode->flags & BTRFS_INODE_IMMUTABLE) + if (inode->flags & BTRFS_INODE_IMMUTABLE) new_fl |= S_IMMUTABLE; - if (binode->flags & BTRFS_INODE_APPEND) + if (inode->flags & BTRFS_INODE_APPEND) new_fl |= S_APPEND; - if (binode->flags & BTRFS_INODE_NOATIME) + if (inode->flags & BTRFS_INODE_NOATIME) new_fl |= S_NOATIME; - if (binode->flags & BTRFS_INODE_DIRSYNC) + if (inode->flags & BTRFS_INODE_DIRSYNC) new_fl |= S_DIRSYNC; - if (binode->ro_flags & BTRFS_INODE_RO_VERITY) + if (inode->ro_flags & BTRFS_INODE_RO_VERITY) new_fl |= S_VERITY; - set_mask_bits(&inode->i_flags, + set_mask_bits(&inode->vfs_inode.i_flags, S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC | S_VERITY, new_fl); } @@ -192,7 +218,7 @@ static int check_fsflags(unsigned int old_flags, unsigned int flags) return 0; } -static int check_fsflags_compatible(struct btrfs_fs_info *fs_info, +static int check_fsflags_compatible(const struct btrfs_fs_info *fs_info, unsigned int flags) { if (btrfs_is_zoned(fs_info) && (flags & FS_NOCOW_FL)) @@ -201,30 +227,43 @@ static int check_fsflags_compatible(struct btrfs_fs_info *fs_info, return 0; } +int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args) +{ + if (memchr(vol_args->name, 0, sizeof(vol_args->name)) == NULL) + return -ENAMETOOLONG; + return 0; +} + +static int btrfs_check_ioctl_vol_args2_subvol_name(const struct btrfs_ioctl_vol_args_v2 *vol_args2) +{ + if (memchr(vol_args2->name, 0, sizeof(vol_args2->name)) == NULL) + return -ENAMETOOLONG; + return 0; +} + /* * Set flags/xflags from the internal inode flags. The remaining items of * fsxattr are zeroed. */ -int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) +int btrfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa) { - struct btrfs_inode *binode = BTRFS_I(d_inode(dentry)); + const struct btrfs_inode *inode = BTRFS_I(d_inode(dentry)); - fileattr_fill_flags(fa, btrfs_inode_flags_to_fsflags(binode)); + fileattr_fill_flags(fa, btrfs_inode_flags_to_fsflags(inode)); return 0; } -int btrfs_fileattr_set(struct user_namespace *mnt_userns, - struct dentry *dentry, struct fileattr *fa) +int btrfs_fileattr_set(struct mnt_idmap *idmap, + struct dentry *dentry, struct file_kattr *fa) { - struct inode *inode = d_inode(dentry); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_inode *binode = BTRFS_I(inode); - struct btrfs_root *root = binode->root; + struct btrfs_inode *inode = BTRFS_I(d_inode(dentry)); + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; - u32 binode_flags; + u32 inode_flags; if (btrfs_root_readonly(root)) return -EROFS; @@ -232,8 +271,8 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, if (fileattr_has_fsx(fa)) return -EOPNOTSUPP; - fsflags = btrfs_mask_fsflags_for_type(inode, fa->flags); - old_fsflags = btrfs_inode_flags_to_fsflags(binode); + fsflags = btrfs_mask_fsflags_for_type(&inode->vfs_inode, fa->flags); + old_fsflags = btrfs_inode_flags_to_fsflags(inode); ret = check_fsflags(old_fsflags, fsflags); if (ret) return ret; @@ -242,27 +281,27 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, if (ret) return ret; - binode_flags = binode->flags; + inode_flags = inode->flags; if (fsflags & FS_SYNC_FL) - binode_flags |= BTRFS_INODE_SYNC; + inode_flags |= BTRFS_INODE_SYNC; else - binode_flags &= ~BTRFS_INODE_SYNC; + inode_flags &= ~BTRFS_INODE_SYNC; if (fsflags & FS_IMMUTABLE_FL) - binode_flags |= BTRFS_INODE_IMMUTABLE; + inode_flags |= BTRFS_INODE_IMMUTABLE; else - binode_flags &= ~BTRFS_INODE_IMMUTABLE; + inode_flags &= ~BTRFS_INODE_IMMUTABLE; if (fsflags & FS_APPEND_FL) - binode_flags |= BTRFS_INODE_APPEND; + inode_flags |= BTRFS_INODE_APPEND; else - binode_flags &= ~BTRFS_INODE_APPEND; + inode_flags &= ~BTRFS_INODE_APPEND; if (fsflags & FS_NODUMP_FL) - binode_flags |= BTRFS_INODE_NODUMP; + inode_flags |= BTRFS_INODE_NODUMP; else - binode_flags &= ~BTRFS_INODE_NODUMP; + inode_flags &= ~BTRFS_INODE_NODUMP; if (fsflags & FS_NOATIME_FL) - binode_flags |= BTRFS_INODE_NOATIME; + inode_flags |= BTRFS_INODE_NOATIME; else - binode_flags &= ~BTRFS_INODE_NOATIME; + inode_flags &= ~BTRFS_INODE_NOATIME; /* If coming from FS_IOC_FSSETXATTR then skip unconverted flags */ if (!fa->flags_valid) { @@ -274,32 +313,32 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, } if (fsflags & FS_DIRSYNC_FL) - binode_flags |= BTRFS_INODE_DIRSYNC; + inode_flags |= BTRFS_INODE_DIRSYNC; else - binode_flags &= ~BTRFS_INODE_DIRSYNC; + inode_flags &= ~BTRFS_INODE_DIRSYNC; if (fsflags & FS_NOCOW_FL) { - if (S_ISREG(inode->i_mode)) { + if (S_ISREG(inode->vfs_inode.i_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) - binode_flags |= BTRFS_INODE_NODATACOW | - BTRFS_INODE_NODATASUM; + if (inode->vfs_inode.i_size == 0) + inode_flags |= BTRFS_INODE_NODATACOW | + BTRFS_INODE_NODATASUM; } else { - binode_flags |= BTRFS_INODE_NODATACOW; + inode_flags |= BTRFS_INODE_NODATACOW; } } else { /* * Revert back under same assumptions as above */ - if (S_ISREG(inode->i_mode)) { - if (inode->i_size == 0) - binode_flags &= ~(BTRFS_INODE_NODATACOW | - BTRFS_INODE_NODATASUM); + if (S_ISREG(inode->vfs_inode.i_mode)) { + if (inode->vfs_inode.i_size == 0) + inode_flags &= ~(BTRFS_INODE_NODATACOW | + BTRFS_INODE_NODATASUM); } else { - binode_flags &= ~BTRFS_INODE_NODATACOW; + inode_flags &= ~BTRFS_INODE_NODATACOW; } } @@ -309,21 +348,21 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, * things smaller. */ if (fsflags & FS_NOCOMP_FL) { - binode_flags &= ~BTRFS_INODE_COMPRESS; - binode_flags |= BTRFS_INODE_NOCOMPRESS; + inode_flags &= ~BTRFS_INODE_COMPRESS; + inode_flags |= BTRFS_INODE_NOCOMPRESS; } else if (fsflags & FS_COMPR_FL) { - if (IS_SWAPFILE(inode)) + if (IS_SWAPFILE(&inode->vfs_inode)) return -ETXTBSY; - binode_flags |= BTRFS_INODE_COMPRESS; - binode_flags &= ~BTRFS_INODE_NOCOMPRESS; + inode_flags |= BTRFS_INODE_COMPRESS; + inode_flags &= ~BTRFS_INODE_NOCOMPRESS; comp = btrfs_compress_type2str(fs_info->compress_type); if (!comp || comp[0] == 0) comp = btrfs_compress_type2str(BTRFS_COMPRESS_ZLIB); } else { - binode_flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); + inode_flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } /* @@ -335,115 +374,35 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, return PTR_ERR(trans); if (comp) { - ret = btrfs_set_prop(trans, inode, "btrfs.compression", comp, - strlen(comp), 0); - if (ret) { + ret = btrfs_set_prop(trans, inode, "btrfs.compression", + comp, strlen(comp), 0); + if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out_end_trans; } } else { - ret = btrfs_set_prop(trans, inode, "btrfs.compression", NULL, - 0, 0); - if (ret && ret != -ENODATA) { + ret = btrfs_set_prop(trans, inode, "btrfs.compression", NULL, 0, 0); + if (unlikely(ret && ret != -ENODATA)) { btrfs_abort_transaction(trans, ret); goto out_end_trans; } } update_flags: - binode->flags = binode_flags; + inode->flags = inode_flags; + btrfs_update_inode_mapping_flags(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, BTRFS_I(inode)); + inode_inc_iversion(&inode->vfs_inode); + inode_set_ctime_current(&inode->vfs_inode); + ret = btrfs_update_inode(trans, inode); out_end_trans: btrfs_end_transaction(trans); return ret; } -/* - * Start exclusive operation @type, return true on success - */ -bool btrfs_exclop_start(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation type) -{ - bool ret = false; - - spin_lock(&fs_info->super_lock); - if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) { - fs_info->exclusive_operation = type; - ret = true; - } - spin_unlock(&fs_info->super_lock); - - return ret; -} - -/* - * Conditionally allow to enter the exclusive operation in case it's compatible - * with the running one. This must be paired with btrfs_exclop_start_unlock and - * btrfs_exclop_finish. - * - * Compatibility: - * - the same type is already running - * - when trying to add a device and balance has been paused - * - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller - * must check the condition first that would allow none -> @type - */ -bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation type) -{ - spin_lock(&fs_info->super_lock); - if (fs_info->exclusive_operation == type || - (fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED && - type == BTRFS_EXCLOP_DEV_ADD)) - return true; - - spin_unlock(&fs_info->super_lock); - return false; -} - -void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info) +static int btrfs_ioctl_getversion(const struct inode *inode, int __user *arg) { - spin_unlock(&fs_info->super_lock); -} - -void btrfs_exclop_finish(struct btrfs_fs_info *fs_info) -{ - spin_lock(&fs_info->super_lock); - WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE); - spin_unlock(&fs_info->super_lock); - sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation"); -} - -void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation op) -{ - switch (op) { - case BTRFS_EXCLOP_BALANCE_PAUSED: - spin_lock(&fs_info->super_lock); - ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || - fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD); - fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED; - spin_unlock(&fs_info->super_lock); - break; - case BTRFS_EXCLOP_BALANCE: - spin_lock(&fs_info->super_lock); - ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); - fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE; - spin_unlock(&fs_info->super_lock); - break; - default: - btrfs_warn(fs_info, - "invalid exclop balance operation %d requested", op); - } -} - -static int btrfs_ioctl_getversion(struct file *file, int __user *arg) -{ - struct inode *inode = file_inode(file); - return put_user(inode->i_generation, arg); } @@ -451,7 +410,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, void __user *arg) { struct btrfs_device *device; - struct request_queue *q; struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; @@ -481,14 +439,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { - if (!device->bdev) + if (!device->bdev || !bdev_max_discard_sectors(device->bdev)) continue; - q = bdev_get_queue(device->bdev); - if (blk_queue_discard(q)) { - num_devices++; - minlen = min_t(u64, q->limits.discard_granularity, - minlen); - } + num_devices++; + minlen = min_t(u64, bdev_discard_granularity(device->bdev), + minlen); } rcu_read_unlock(); @@ -502,51 +457,69 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, * block group is in the logical address space, which can be any * sectorsize aligned bytenr in the range [0, U64_MAX]. */ - if (range.len < fs_info->sb->s_blocksize) + if (range.len < fs_info->sectorsize) return -EINVAL; range.minlen = max(range.minlen, minlen); ret = btrfs_trim_fs(fs_info, &range); - if (ret < 0) - return ret; if (copy_to_user(arg, &range, sizeof(range))) return -EFAULT; - return 0; + return ret; } -int __pure btrfs_is_empty_uuid(u8 *uuid) +/* + * Calculate the number of transaction items to reserve for creating a subvolume + * or snapshot, not including the inode, directory entries, or parent directory. + */ +static unsigned int create_subvol_num_items(const struct btrfs_qgroup_inherit *inherit) { - int i; + /* + * 1 to add root block + * 1 to add root item + * 1 to add root ref + * 1 to add root backref + * 1 to add UUID item + * 1 to add qgroup info + * 1 to add qgroup limit + * + * Ideally the last two would only be accounted if qgroups are enabled, + * but that can change between now and the time we would insert them. + */ + unsigned int num_items = 7; - for (i = 0; i < BTRFS_UUID_SIZE; i++) { - if (uuid[i]) - return 0; + if (inherit) { + /* 2 to add qgroup relations for each inherited qgroup */ + num_items += 2 * inherit->num_qgroups; } - return 1; + return num_items; } -static noinline int create_subvol(struct user_namespace *mnt_userns, +static noinline int create_subvol(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, - const char *name, int namelen, struct btrfs_qgroup_inherit *inherit) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct btrfs_trans_handle *trans; struct btrfs_key key; - struct btrfs_root_item *root_item; + struct btrfs_root_item AUTO_KFREE(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 timespec64 cur_time = current_time(dir); - struct inode *inode; + struct btrfs_new_inode_args new_inode_args = { + .dir = dir, + .dentry = dentry, + .subvol = true, + }; + unsigned int trans_num_items; int ret; - dev_t anon_dev = 0; + dev_t anon_dev; u64 objectid; - u64 index = 0; + u64 qgroup_reserved = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) @@ -554,51 +527,58 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid); if (ret) - goto fail_free; - - ret = get_anon_bdev(&anon_dev); - if (ret < 0) - goto fail_free; + return ret; /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. */ - if (btrfs_qgroup_level(objectid)) { - ret = -ENOSPC; - goto fail_free; + if (btrfs_qgroup_level(objectid)) + return -ENOSPC; + + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + return ret; + + new_inode_args.inode = btrfs_new_subvol_inode(idmap, dir); + if (!new_inode_args.inode) { + ret = -ENOMEM; + goto out_anon_dev; } + ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items); + if (ret) + goto out_inode; + trans_num_items += create_subvol_num_items(inherit); 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, false); + ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, + trans_num_items, false); if (ret) - goto fail_free; + goto out_new_inode_args; + qgroup_reserved = block_rsv.qgroup_rsv_reserved; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_subvolume_release_metadata(root, &block_rsv); - goto fail_free; + goto out_release_rsv; } + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; - ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit); + ret = btrfs_qgroup_inherit(trans, 0, objectid, btrfs_root_id(root), inherit); if (ret) - goto fail; + goto out; leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0, - BTRFS_NESTING_NORMAL); + 0, BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); - goto fail; + goto out; } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); inode_item = &root_item->inode; btrfs_set_stack_inode_generation(inode_item, 1); @@ -633,11 +613,13 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID); key.objectid = objectid; - key.offset = 0; key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = 0; ret = btrfs_insert_root(trans, fs_info->tree_root, &key, root_item); if (ret) { + int ret2; + /* * Since we don't abort the transaction in this case, free the * tree block so that we don't leak space and leave the @@ -646,100 +628,69 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, * exists). */ btrfs_tree_lock(leaf); - btrfs_clean_tree_block(leaf); + btrfs_clear_buffer_dirty(trans, leaf); btrfs_tree_unlock(leaf); - btrfs_free_tree_block(trans, objectid, leaf, 0, 1); + ret2 = btrfs_free_tree_block(trans, objectid, leaf, 0, 1); + if (unlikely(ret2 < 0)) + btrfs_abort_transaction(trans, ret2); free_extent_buffer(leaf); - goto fail; + goto out; } free_extent_buffer(leaf); leaf = NULL; - key.offset = (u64)-1; - new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev); if (IS_ERR(new_root)) { - free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - /* Freeing will be done in btrfs_put_root() of new_root */ + /* anon_dev is owned by new_root now. */ anon_dev = 0; + BTRFS_I(new_inode_args.inode)->root = new_root; + /* ... and new_root is owned by new_inode_args.inode now. */ ret = btrfs_record_root_in_trans(trans, new_root); - if (ret) { - btrfs_put_root(new_root); + if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto fail; - } - - ret = btrfs_create_subvol_root(trans, new_root, root, mnt_userns); - btrfs_put_root(new_root); - if (ret) { - /* We potentially lose an unused inode item here */ - btrfs_abort_transaction(trans, ret); - goto fail; - } - - /* - * insert the directory item - */ - ret = btrfs_set_inode_index(BTRFS_I(dir), &index); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - ret = btrfs_insert_dir_item(trans, name, namelen, BTRFS_I(dir), &key, - BTRFS_FT_DIR, index); - if (ret) { + ret = btrfs_uuid_tree_add(trans, root_item->uuid, + BTRFS_UUID_KEY_SUBVOL, objectid); + if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); - ret = btrfs_update_inode(trans, root, BTRFS_I(dir)); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } + btrfs_record_new_subvolume(trans, BTRFS_I(dir)); - ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, - btrfs_ino(BTRFS_I(dir)), index, name, namelen); - if (ret) { + ret = btrfs_create_new_inode(trans, &new_inode_args); + if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - ret = btrfs_uuid_tree_add(trans, root_item->uuid, - BTRFS_UUID_KEY_SUBVOL, objectid); - if (ret) - btrfs_abort_transaction(trans, ret); + d_instantiate_new(dentry, new_inode_args.inode); + new_inode_args.inode = NULL; -fail: - kfree(root_item); +out: trans->block_rsv = NULL; trans->bytes_reserved = 0; - btrfs_subvolume_release_metadata(root, &block_rsv); - - if (ret) - btrfs_end_transaction(trans); - else - ret = btrfs_commit_transaction(trans); - - if (!ret) { - inode = btrfs_lookup_dentry(dir, dentry); - if (IS_ERR(inode)) - return PTR_ERR(inode); - d_instantiate(dentry, inode); - } - return ret; - -fail_free: + btrfs_end_transaction(trans); +out_release_rsv: + btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); +out_new_inode_args: + btrfs_new_inode_args_destroy(&new_inode_args); +out_inode: + iput(new_inode_args.inode); +out_anon_dev: if (anon_dev) free_anon_bdev(anon_dev); - kfree(root_item); + return ret; } @@ -747,12 +698,25 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct dentry *dentry, bool readonly, struct btrfs_qgroup_inherit *inherit) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct inode *inode; struct btrfs_pending_snapshot *pending_snapshot; + unsigned int trans_num_items; struct btrfs_trans_handle *trans; + struct btrfs_block_rsv *block_rsv; + u64 qgroup_reserved = 0; int ret; + /* We do not support snapshotting right now. */ + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { + btrfs_warn(fs_info, + "extent tree v2 doesn't support snapshotting yet"); + return -EOPNOTSUPP; + } + + if (btrfs_root_refs(&root->root_item) == 0) + return -ENOENT; + if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL; @@ -777,26 +741,24 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } - btrfs_init_block_rsv(&pending_snapshot->block_rsv, - BTRFS_BLOCK_RSV_TEMP); + block_rsv = &pending_snapshot->block_rsv; + btrfs_init_block_rsv(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 + * 1 to add dir item + * 1 to add dir index + * 1 to update parent inode item */ - ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, - &pending_snapshot->block_rsv, 8, - false); + trans_num_items = create_subvol_num_items(inherit) + 3; + ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv, + trans_num_items, false); if (ret) goto free_pending; + qgroup_reserved = block_rsv->qgroup_rsv_reserved; pending_snapshot->dentry = dentry; pending_snapshot->root = root; pending_snapshot->readonly = readonly; - pending_snapshot->dir = dir; + pending_snapshot->dir = BTRFS_I(dir); pending_snapshot->inherit = inherit; trans = btrfs_start_transaction(root, 0); @@ -804,11 +766,15 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, ret = PTR_ERR(trans); goto fail; } + ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root); + if (ret) { + btrfs_end_transaction(trans); + goto fail; + } + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; - spin_lock(&fs_info->trans_lock); - list_add(&pending_snapshot->list, - &trans->transaction->pending_snapshots); - spin_unlock(&fs_info->trans_lock); + trans->pending_snapshot = pending_snapshot; ret = btrfs_commit_transaction(trans); if (ret) @@ -836,7 +802,9 @@ fail: if (ret && pending_snapshot->snap) pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); - btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv); + btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); free_pending: if (pending_snapshot->anon_dev) free_anon_bdev(pending_snapshot->anon_dev); @@ -867,23 +835,25 @@ free_pending: * nfs_async_unlink(). */ -static int btrfs_may_delete(struct user_namespace *mnt_userns, +static int btrfs_may_delete(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, int isdir) { - int error; + int ret; if (d_really_is_negative(victim)) return -ENOENT; - BUG_ON(d_inode(victim->d_parent) != dir); + /* The @victim is not inside @dir. */ + if (d_inode(victim->d_parent) != dir) + return -EINVAL; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); - if (error) - return error; + ret = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); + if (ret) + return ret; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(mnt_userns, dir, d_inode(victim)) || + if (check_sticky(idmap, dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) || IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim))) return -EPERM; @@ -902,16 +872,16 @@ static int btrfs_may_delete(struct user_namespace *mnt_userns, } /* copy of may_create in fs/namei.c() */ -static inline int btrfs_may_create(struct user_namespace *mnt_userns, - struct inode *dir, struct dentry *child) +static inline int btrfs_may_create(struct mnt_idmap *idmap, + struct inode *dir, const struct dentry *child) { if (d_really_is_positive(child)) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns)) + if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; - return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); + return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } /* @@ -919,39 +889,32 @@ static inline int btrfs_may_create(struct user_namespace *mnt_userns, * 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(const struct path *parent, - struct user_namespace *mnt_userns, - const char *name, int namelen, - struct btrfs_root *snap_src, +static noinline int btrfs_mksubvol(struct dentry *parent, + struct mnt_idmap *idmap, + struct qstr *qname, struct btrfs_root *snap_src, bool readonly, struct btrfs_qgroup_inherit *inherit) { - struct inode *dir = d_inode(parent->dentry); - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct inode *dir = d_inode(parent); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct dentry *dentry; - int error; - - error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); - if (error == -EINTR) - return error; + struct fscrypt_str name_str = FSTR_INIT((char *)qname->name, qname->len); + int ret; - dentry = lookup_one(mnt_userns, name, parent->dentry, namelen); - error = PTR_ERR(dentry); + dentry = start_creating_killable(idmap, parent, qname); if (IS_ERR(dentry)) - goto out_unlock; + return PTR_ERR(dentry); - error = btrfs_may_create(mnt_userns, dir, dentry); - if (error) + ret = btrfs_may_create(idmap, dir, dentry); + if (ret) 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) + ret = btrfs_check_dir_item_collision(BTRFS_I(dir)->root, dir->i_ino, &name_str); + if (ret) goto out_dput; down_read(&fs_info->subvol_sem); @@ -960,34 +923,31 @@ static noinline int btrfs_mksubvol(const struct path *parent, goto out_up_read; if (snap_src) - error = create_snapshot(snap_src, dir, dentry, readonly, inherit); + ret = create_snapshot(snap_src, dir, dentry, readonly, inherit); else - error = create_subvol(mnt_userns, dir, dentry, name, namelen, inherit); + ret = create_subvol(idmap, dir, dentry, inherit); - if (!error) + if (!ret) fsnotify_mkdir(dir, dentry); out_up_read: up_read(&fs_info->subvol_sem); out_dput: - dput(dentry); -out_unlock: - btrfs_inode_unlock(dir, 0); - return error; + end_creating(dentry); + return ret; } -static noinline int btrfs_mksnapshot(const struct path *parent, - struct user_namespace *mnt_userns, - const char *name, int namelen, +static noinline int btrfs_mksnapshot(struct dentry *parent, + struct mnt_idmap *idmap, + struct qstr *qname, struct btrfs_root *root, bool readonly, struct btrfs_qgroup_inherit *inherit) { int ret; - bool snapshot_force_cow = false; /* * Force new buffered writes to reserve space even when NOCOW is - * possible. This is to avoid later writeback (running dealloc) to + * possible. This is to avoid later writeback (running delalloc) to * fallback to COW mode and unexpectedly fail with ENOSPC. */ btrfs_drew_read_lock(&root->snapshot_lock); @@ -1002,601 +962,14 @@ static noinline int btrfs_mksnapshot(const struct path *parent, * creation. */ atomic_inc(&root->snapshot_force_cow); - snapshot_force_cow = true; - - btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); - - ret = btrfs_mksubvol(parent, mnt_userns, name, namelen, - root, readonly, inherit); -out: - if (snapshot_force_cow) - atomic_dec(&root->snapshot_force_cow); - btrfs_drew_read_unlock(&root->snapshot_lock); - return ret; -} - -static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, - bool locked) -{ - 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; - const u32 sectorsize = BTRFS_I(inode)->root->fs_info->sectorsize; - - /* - * 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, sectorsize); - read_unlock(&em_tree->lock); - - if (!em) { - struct extent_state *cached = NULL; - u64 end = start + sectorsize - 1; - - /* get the big lock and read metadata off disk */ - if (!locked) - lock_extent_bits(io_tree, start, end, &cached); - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, sectorsize); - if (!locked) - unlock_extent_cached(io_tree, start, end, &cached); - - if (IS_ERR(em)) - return NULL; - } - - return em; -} - -static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, - bool locked) -{ - 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, locked); - if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) - ret = false; - else if ((em->block_start + em->block_len == next->block_start) && - (em->block_len > SZ_128K && next->block_len > SZ_128K)) - ret = false; - - free_extent_map(next); - return ret; -} - -/* - * Prepare one page to be defragged. - * - * This will ensure: - * - * - Returned page is locked and has been set up properly. - * - No ordered extent exists in the page. - * - The page is uptodate. - * - * NOTE: Caller should also wait for page writeback after the cluster is - * prepared, here we don't do writeback wait for each page. - */ -static struct page *defrag_prepare_one_page(struct btrfs_inode *inode, - pgoff_t index) -{ - struct address_space *mapping = inode->vfs_inode.i_mapping; - gfp_t mask = btrfs_alloc_write_mask(mapping); - u64 page_start = (u64)index << PAGE_SHIFT; - u64 page_end = page_start + PAGE_SIZE - 1; - struct extent_state *cached_state = NULL; - struct page *page; - int ret; - -again: - page = find_or_create_page(mapping, index, mask); - if (!page) - return ERR_PTR(-ENOMEM); - - /* - * Since we can defragment files opened read-only, we can encounter - * transparent huge pages here (see CONFIG_READ_ONLY_THP_FOR_FS). We - * can't do I/O using huge pages yet, so return an error for now. - * Filesystem transparent huge pages are typically only used for - * executables that explicitly enable them, so this isn't very - * restrictive. - */ - if (PageCompound(page)) { - unlock_page(page); - put_page(page); - return ERR_PTR(-ETXTBSY); - } - - ret = set_page_extent_mapped(page); - if (ret < 0) { - unlock_page(page); - put_page(page); - return ERR_PTR(ret); - } - - /* Wait for any existing ordered extent in the range */ - while (1) { - struct btrfs_ordered_extent *ordered; - - lock_extent_bits(&inode->io_tree, page_start, page_end, &cached_state); - ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE); - unlock_extent_cached(&inode->io_tree, page_start, page_end, - &cached_state); - if (!ordered) - break; - - unlock_page(page); - btrfs_start_ordered_extent(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 != mapping || !PagePrivate(page)) { - unlock_page(page); - put_page(page); - goto again; - } - } - - /* - * Now the page range has no ordered extent any more. Read the page to - * make it uptodate. - */ - if (!PageUptodate(page)) { - btrfs_readpage(NULL, page); - lock_page(page); - if (page->mapping != mapping || !PagePrivate(page)) { - unlock_page(page); - put_page(page); - goto again; - } - if (!PageUptodate(page)) { - unlock_page(page); - put_page(page); - return ERR_PTR(-EIO); - } - } - return page; -} - -struct defrag_target_range { - struct list_head list; - u64 start; - u64 len; -}; -/* - * Collect all valid target extents. - * - * @start: file offset to lookup - * @len: length to lookup - * @extent_thresh: file extent size threshold, any extent size >= this value - * will be ignored - * @newer_than: only defrag extents newer than this value - * @do_compress: whether the defrag is doing compression - * if true, @extent_thresh will be ignored and all regular - * file extents meeting @newer_than will be targets. - * @locked: if the range has already held extent lock - * @target_list: list of targets file extents - */ -static int defrag_collect_targets(struct btrfs_inode *inode, - u64 start, u64 len, u32 extent_thresh, - u64 newer_than, bool do_compress, - bool locked, struct list_head *target_list) -{ - u64 cur = start; - int ret = 0; - - while (cur < start + len) { - struct extent_map *em; - struct defrag_target_range *new; - bool next_mergeable = true; - u64 range_len; - - em = defrag_lookup_extent(&inode->vfs_inode, cur, locked); - if (!em) - break; - - /* Skip hole/inline/preallocated extents */ - if (em->block_start >= EXTENT_MAP_LAST_BYTE || - test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - goto next; - - /* Skip older extent */ - if (em->generation < newer_than) - goto next; - - /* - * For do_compress case, we want to compress all valid file - * extents, thus no @extent_thresh or mergeable check. - */ - if (do_compress) - goto add; - - /* Skip too large extent */ - if (em->len >= extent_thresh) - goto next; - - next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, - locked); - if (!next_mergeable) { - struct defrag_target_range *last; - - /* Empty target list, no way to merge with last entry */ - if (list_empty(target_list)) - goto next; - last = list_entry(target_list->prev, - struct defrag_target_range, list); - /* Not mergeable with last entry */ - if (last->start + last->len != cur) - goto next; - - /* Mergeable, fall through to add it to @target_list. */ - } - -add: - range_len = min(extent_map_end(em), start + len) - cur; - /* - * This one is a good target, check if it can be merged into - * last range of the target list. - */ - if (!list_empty(target_list)) { - struct defrag_target_range *last; - - last = list_entry(target_list->prev, - struct defrag_target_range, list); - ASSERT(last->start + last->len <= cur); - if (last->start + last->len == cur) { - /* Mergeable, enlarge the last entry */ - last->len += range_len; - goto next; - } - /* Fall through to allocate a new entry */ - } - - /* Allocate new defrag_target_range */ - new = kmalloc(sizeof(*new), GFP_NOFS); - if (!new) { - free_extent_map(em); - ret = -ENOMEM; - break; - } - new->start = cur; - new->len = range_len; - list_add_tail(&new->list, target_list); - -next: - cur = extent_map_end(em); - free_extent_map(em); - } - if (ret < 0) { - struct defrag_target_range *entry; - struct defrag_target_range *tmp; - - list_for_each_entry_safe(entry, tmp, target_list, list) { - list_del_init(&entry->list); - kfree(entry); - } - } - return ret; -} + btrfs_wait_ordered_extents(root, U64_MAX, NULL); -#define CLUSTER_SIZE (SZ_256K) + ret = btrfs_mksubvol(parent, idmap, qname, root, readonly, inherit); -/* - * Defrag one contiguous target range. - * - * @inode: target inode - * @target: target range to defrag - * @pages: locked pages covering the defrag range - * @nr_pages: number of locked pages - * - * Caller should ensure: - * - * - Pages are prepared - * Pages should be locked, no ordered extent in the pages range, - * no writeback. - * - * - Extent bits are locked - */ -static int defrag_one_locked_target(struct btrfs_inode *inode, - struct defrag_target_range *target, - struct page **pages, int nr_pages, - struct extent_state **cached_state) -{ - struct btrfs_fs_info *fs_info = inode->root->fs_info; - struct extent_changeset *data_reserved = NULL; - const u64 start = target->start; - const u64 len = target->len; - unsigned long last_index = (start + len - 1) >> PAGE_SHIFT; - unsigned long start_index = start >> PAGE_SHIFT; - unsigned long first_index = page_index(pages[0]); - int ret = 0; - int i; - - ASSERT(last_index - first_index + 1 <= nr_pages); - - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, start, len); - if (ret < 0) - return ret; - clear_extent_bit(&inode->io_tree, start, start + len - 1, - EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | - EXTENT_DEFRAG, 0, 0, cached_state); - set_extent_defrag(&inode->io_tree, start, start + len - 1, cached_state); - - /* Update the page status */ - for (i = start_index - first_index; i <= last_index - first_index; i++) { - ClearPageChecked(pages[i]); - btrfs_page_clamp_set_dirty(fs_info, pages[i], start, len); - } - btrfs_delalloc_release_extents(inode, len); - extent_changeset_free(data_reserved); - - return ret; -} - -static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len, - u32 extent_thresh, u64 newer_than, bool do_compress) -{ - struct extent_state *cached_state = NULL; - struct defrag_target_range *entry; - struct defrag_target_range *tmp; - LIST_HEAD(target_list); - struct page **pages; - const u32 sectorsize = inode->root->fs_info->sectorsize; - u64 last_index = (start + len - 1) >> PAGE_SHIFT; - u64 start_index = start >> PAGE_SHIFT; - unsigned int nr_pages = last_index - start_index + 1; - int ret = 0; - int i; - - ASSERT(nr_pages <= CLUSTER_SIZE / PAGE_SIZE); - ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(len, sectorsize)); - - pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); - if (!pages) - return -ENOMEM; - - /* Prepare all pages */ - for (i = 0; i < nr_pages; i++) { - pages[i] = defrag_prepare_one_page(inode, start_index + i); - if (IS_ERR(pages[i])) { - ret = PTR_ERR(pages[i]); - pages[i] = NULL; - goto free_pages; - } - } - for (i = 0; i < nr_pages; i++) - wait_on_page_writeback(pages[i]); - - /* Lock the pages range */ - lock_extent_bits(&inode->io_tree, start_index << PAGE_SHIFT, - (last_index << PAGE_SHIFT) + PAGE_SIZE - 1, - &cached_state); - /* - * Now we have a consistent view about the extent map, re-check - * which range really needs to be defragged. - * - * And this time we have extent locked already, pass @locked = true - * so that we won't relock the extent range and cause deadlock. - */ - ret = defrag_collect_targets(inode, start, len, extent_thresh, - newer_than, do_compress, true, - &target_list); - if (ret < 0) - goto unlock_extent; - - list_for_each_entry(entry, &target_list, list) { - ret = defrag_one_locked_target(inode, entry, pages, nr_pages, - &cached_state); - if (ret < 0) - break; - } - - list_for_each_entry_safe(entry, tmp, &target_list, list) { - list_del_init(&entry->list); - kfree(entry); - } -unlock_extent: - unlock_extent_cached(&inode->io_tree, start_index << PAGE_SHIFT, - (last_index << PAGE_SHIFT) + PAGE_SIZE - 1, - &cached_state); -free_pages: - for (i = 0; i < nr_pages; i++) { - if (pages[i]) { - unlock_page(pages[i]); - put_page(pages[i]); - } - } - kfree(pages); - return ret; -} - -static int defrag_one_cluster(struct btrfs_inode *inode, - struct file_ra_state *ra, - u64 start, u32 len, u32 extent_thresh, - u64 newer_than, bool do_compress, - unsigned long *sectors_defragged, - unsigned long max_sectors) -{ - const u32 sectorsize = inode->root->fs_info->sectorsize; - struct defrag_target_range *entry; - struct defrag_target_range *tmp; - LIST_HEAD(target_list); - int ret; - - BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE)); - ret = defrag_collect_targets(inode, start, len, extent_thresh, - newer_than, do_compress, false, - &target_list); - if (ret < 0) - goto out; - - list_for_each_entry(entry, &target_list, list) { - u32 range_len = entry->len; - - /* Reached the limit */ - if (max_sectors && max_sectors == *sectors_defragged) - break; - - if (max_sectors) - range_len = min_t(u32, range_len, - (max_sectors - *sectors_defragged) * sectorsize); - - if (ra) - page_cache_sync_readahead(inode->vfs_inode.i_mapping, - ra, NULL, entry->start >> PAGE_SHIFT, - ((entry->start + range_len - 1) >> PAGE_SHIFT) - - (entry->start >> PAGE_SHIFT) + 1); - /* - * Here we may not defrag any range if holes are punched before - * we locked the pages. - * But that's fine, it only affects the @sectors_defragged - * accounting. - */ - ret = defrag_one_range(inode, entry->start, range_len, - extent_thresh, newer_than, do_compress); - if (ret < 0) - break; - *sectors_defragged += range_len; - } + atomic_dec(&root->snapshot_force_cow); out: - list_for_each_entry_safe(entry, tmp, &target_list, list) { - list_del_init(&entry->list); - kfree(entry); - } - return ret; -} - -/* - * Entry point to file defragmentation. - * - * @inode: inode to be defragged - * @ra: readahead state (can be NUL) - * @range: defrag options including range and flags - * @newer_than: minimum transid to defrag - * @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode - * will be defragged. - */ -int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, - struct btrfs_ioctl_defrag_range_args *range, - u64 newer_than, unsigned long max_to_defrag) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - unsigned long sectors_defragged = 0; - u64 isize = i_size_read(inode); - u64 cur; - u64 last_byte; - bool do_compress = range->flags & BTRFS_DEFRAG_RANGE_COMPRESS; - bool ra_allocated = false; - int compress_type = BTRFS_COMPRESS_ZLIB; - int ret = 0; - u32 extent_thresh = range->extent_thresh; - - if (isize == 0) - return 0; - - if (range->start >= isize) - return -EINVAL; - - if (do_compress) { - if (range->compress_type >= BTRFS_NR_COMPRESS_TYPES) - return -EINVAL; - if (range->compress_type) - compress_type = range->compress_type; - } - - if (extent_thresh == 0) - extent_thresh = SZ_256K; - - if (range->start + range->len > range->start) { - /* Got a specific range */ - last_byte = min(isize, range->start + range->len) - 1; - } else { - /* Defrag until file end */ - last_byte = isize - 1; - } - - /* - * If we were not given a ra, allocate a readahead context. As - * readahead is just an optimization, defrag will work without it so - * we don't error out. - */ - if (!ra) { - ra_allocated = true; - ra = kzalloc(sizeof(*ra), GFP_KERNEL); - if (ra) - file_ra_state_init(ra, inode->i_mapping); - } - - /* Align the range */ - cur = round_down(range->start, fs_info->sectorsize); - last_byte = round_up(last_byte, fs_info->sectorsize) - 1; - - while (cur < last_byte) { - u64 cluster_end; - - /* The cluster size 256K should always be page aligned */ - BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE)); - - /* We want the cluster end at page boundary when possible */ - cluster_end = (((cur >> PAGE_SHIFT) + - (SZ_256K >> PAGE_SHIFT)) << PAGE_SHIFT) - 1; - cluster_end = min(cluster_end, last_byte); - - btrfs_inode_lock(inode, 0); - if (IS_SWAPFILE(inode)) { - ret = -ETXTBSY; - btrfs_inode_unlock(inode, 0); - break; - } - if (!(inode->i_sb->s_flags & SB_ACTIVE)) { - btrfs_inode_unlock(inode, 0); - break; - } - if (do_compress) - BTRFS_I(inode)->defrag_compress = compress_type; - ret = defrag_one_cluster(BTRFS_I(inode), ra, cur, - cluster_end + 1 - cur, extent_thresh, - newer_than, do_compress, - §ors_defragged, max_to_defrag); - btrfs_inode_unlock(inode, 0); - if (ret < 0) - break; - cur = cluster_end + 1; - } - - if (ra_allocated) - kfree(ra); - if (sectors_defragged) { - /* - * We have defragged some sectors, for compression case they - * need to be written back immediately. - */ - if (range->flags & BTRFS_DEFRAG_RANGE_START_IO) { - filemap_flush(inode->i_mapping); - if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, - &BTRFS_I(inode)->runtime_flags)) - filemap_flush(inode->i_mapping); - } - if (range->compress_type == BTRFS_COMPRESS_LZO) - btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); - else if (range->compress_type == BTRFS_COMPRESS_ZSTD) - btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); - ret = sectors_defragged; - } - if (do_compress) { - btrfs_inode_lock(inode, 0); - BTRFS_I(inode)->defrag_compress = BTRFS_COMPRESS_NONE; - btrfs_inode_unlock(inode, 0); - } + btrfs_drew_read_unlock(&root->snapshot_lock); return ret; } @@ -1646,17 +1019,14 @@ static noinline int btrfs_ioctl_resize(struct file *file, void __user *arg) { BTRFS_DEV_LOOKUP_ARGS(args); - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_root *root = BTRFS_I(file_inode(file))->root; + struct btrfs_fs_info *fs_info = root->fs_info; u64 new_size; u64 old_size; u64 devid = 1; - struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_ioctl_vol_args *vol_args; - struct btrfs_trans_handle *trans; struct btrfs_device *device = NULL; char *sizestr; - char *retptr; char *devstr = NULL; int ret = 0; int mod = 0; @@ -1678,7 +1048,10 @@ static noinline int btrfs_ioctl_resize(struct file *file, ret = PTR_ERR(vol_args); goto out_drop; } - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + ret = btrfs_check_ioctl_vol_args_path(vol_args); + if (ret < 0) + goto out_free; + sizestr = vol_args->name; cancel = (strcmp("cancel", sizestr) == 0); ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_RESIZE, cancel); @@ -1721,6 +1094,8 @@ static noinline int btrfs_ioctl_resize(struct file *file, if (!strcmp(sizestr, "max")) new_size = bdev_nr_bytes(device->bdev); else { + char *retptr; + if (sizestr[0] == '-') { mod = -1; sizestr++; @@ -1768,6 +1143,8 @@ static noinline int btrfs_ioctl_resize(struct file *file, new_size = round_down(new_size, fs_info->sectorsize); if (new_size > old_size) { + struct btrfs_trans_handle *trans; + trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -1780,9 +1157,9 @@ static noinline int btrfs_ioctl_resize(struct file *file, } /* equal, nothing need to do */ if (ret == 0 && new_size != old_size) - btrfs_info_in_rcu(fs_info, + btrfs_info(fs_info, "resize device %s (devid %llu) from %llu to %llu", - rcu_str_deref(device->name), device->devid, + btrfs_dev_name(device), device->devid, old_size, new_size); out_finish: btrfs_exclop_finish(fs_info); @@ -1794,13 +1171,13 @@ out_drop: } static noinline int __btrfs_ioctl_snap_create(struct file *file, - struct user_namespace *mnt_userns, - const char *name, unsigned long fd, int subvol, + struct mnt_idmap *idmap, + const char *name, unsigned long fd, bool subvol, bool readonly, struct btrfs_qgroup_inherit *inherit) { - int namelen; int ret = 0; + struct qstr qname = QSTR_INIT(name, strlen(name)); if (!S_ISDIR(file_inode(file)->i_mode)) return -ENOTDIR; @@ -1809,47 +1186,53 @@ static noinline int __btrfs_ioctl_snap_create(struct 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))) { + if (qname.name[0] == '.' && + (qname.len == 1 || (qname.name[1] == '.' && qname.len == 2))) { ret = -EEXIST; goto out_drop_write; } if (subvol) { - ret = btrfs_mksubvol(&file->f_path, mnt_userns, name, - namelen, NULL, readonly, inherit); + ret = btrfs_mksubvol(file_dentry(file), idmap, &qname, NULL, + readonly, inherit); } else { - struct fd src = fdget(fd); + CLASS(fd, src)(fd); struct inode *src_inode; - if (!src.file) { + if (fd_empty(src)) { ret = -EINVAL; goto out_drop_write; } - src_inode = file_inode(src.file); + src_inode = file_inode(fd_file(src)); if (src_inode->i_sb != file_inode(file)->i_sb) { btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); ret = -EXDEV; - } else if (!inode_owner_or_capable(mnt_userns, src_inode)) { + } else if (!inode_owner_or_capable(idmap, src_inode)) { /* * Subvolume creation is not restricted, but snapshots * are limited to own subvolumes only */ ret = -EPERM; + } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) { + /* + * Snapshots must be made with the src_inode referring + * to the subvolume inode, otherwise the permission + * checking above is useless because we may have + * permission on a lower directory but not the subvol + * itself. + */ + ret = -EINVAL; } else { - ret = btrfs_mksnapshot(&file->f_path, mnt_userns, - name, namelen, + ret = btrfs_mksnapshot(file_dentry(file), idmap, &qname, BTRFS_I(src_inode)->root, readonly, inherit); } - fdput(src); } out_drop_write: mnt_drop_write_file(file); @@ -1858,7 +1241,7 @@ out: } static noinline int btrfs_ioctl_snap_create(struct file *file, - void __user *arg, int subvol) + void __user *arg, bool subvol) { struct btrfs_ioctl_vol_args *vol_args; int ret; @@ -1869,18 +1252,21 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, 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_check_ioctl_vol_args_path(vol_args); + if (ret < 0) + goto out; - ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file), + ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), vol_args->name, vol_args->fd, subvol, false, NULL); +out: kfree(vol_args); return ret; } static noinline int btrfs_ioctl_snap_create_v2(struct file *file, - void __user *arg, int subvol) + void __user *arg, bool subvol) { struct btrfs_ioctl_vol_args_v2 *vol_args; int ret; @@ -1893,7 +1279,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, 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'; + ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args); + if (ret < 0) + goto free_args; if (vol_args->flags & ~BTRFS_SUBVOL_CREATE_ARGS_MASK) { ret = -EOPNOTSUPP; @@ -1903,7 +1291,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - u64 nums; + struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file)); if (vol_args->size < sizeof(*inherit) || vol_args->size > PAGE_SIZE) { @@ -1916,22 +1304,12 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, goto free_args; } - if (inherit->num_qgroups > PAGE_SIZE || - inherit->num_ref_copies > PAGE_SIZE || - inherit->num_excl_copies > PAGE_SIZE) { - ret = -EINVAL; - goto free_inherit; - } - - nums = inherit->num_qgroups + 2 * inherit->num_ref_copies + - 2 * inherit->num_excl_copies; - if (vol_args->size != struct_size(inherit, qgroups, nums)) { - ret = -EINVAL; + ret = btrfs_qgroup_check_inherit(fs_info, inherit, vol_args->size); + if (ret < 0) goto free_inherit; - } } - ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file), + ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), vol_args->name, vol_args->fd, subvol, readonly, inherit); if (ret) @@ -1943,16 +1321,15 @@ free_args: return ret; } -static noinline int btrfs_ioctl_subvol_getflags(struct file *file, +static noinline int btrfs_ioctl_subvol_getflags(struct btrfs_inode *inode, void __user *arg) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; u64 flags = 0; - if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) + if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) return -EINVAL; down_read(&fs_info->subvol_sem); @@ -1970,14 +1347,14 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; u64 root_flags; u64 flags; int ret = 0; - if (!inode_owner_or_capable(file_mnt_user_ns(file), inode)) + if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -2023,7 +1400,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, spin_unlock(&root->root_item_lock); btrfs_warn(fs_info, "Attempt to set subvolume %llu read-write during send", - root->root_key.objectid); + btrfs_root_id(root)); ret = -EPERM; goto out_drop_sem; } @@ -2055,8 +1432,8 @@ out: return ret; } -static noinline int key_in_sk(struct btrfs_key *key, - struct btrfs_ioctl_search_key *sk) +static noinline bool key_in_sk(const struct btrfs_key *key, + const struct btrfs_ioctl_search_key *sk) { struct btrfs_key test; int ret; @@ -2067,7 +1444,7 @@ static noinline int key_in_sk(struct btrfs_key *key, ret = btrfs_comp_cpu_keys(key, &test); if (ret < 0) - return 0; + return false; test.objectid = sk->max_objectid; test.type = sk->max_type; @@ -2075,14 +1452,14 @@ static noinline int key_in_sk(struct btrfs_key *key, ret = btrfs_comp_cpu_keys(key, &test); if (ret > 0) - return 0; - return 1; + return false; + return true; } static noinline int copy_to_sk(struct btrfs_path *path, struct btrfs_key *key, - struct btrfs_ioctl_search_key *sk, - size_t *buf_size, + const struct btrfs_ioctl_search_key *sk, + u64 *buf_size, char __user *ubuf, unsigned long *sk_offset, int *num_found) @@ -2138,8 +1515,8 @@ static noinline int copy_to_sk(struct btrfs_path *path, } sh.objectid = key->objectid; - sh.offset = key->offset; sh.type = key->type; + sh.offset = key->offset; sh.len = item_len; sh.transid = found_transid; @@ -2212,15 +1589,14 @@ out: return ret; } -static noinline int search_ioctl(struct inode *inode, +static noinline int search_ioctl(struct btrfs_root *root, struct btrfs_ioctl_search_key *sk, - size_t *buf_size, + u64 *buf_size, char __user *ubuf) { - struct btrfs_fs_info *info = btrfs_sb(inode->i_sb); - struct btrfs_root *root; + struct btrfs_fs_info *info = root->fs_info; struct btrfs_key key; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); int ret; int num_found = 0; unsigned long sk_offset = 0; @@ -2235,14 +1611,13 @@ static noinline int search_ioctl(struct inode *inode, return -ENOMEM; if (sk->tree_id == 0) { - /* search the root of the inode that was passed */ - root = btrfs_grab_root(BTRFS_I(inode)->root); + /* Search the root that we got passed. */ + root = btrfs_grab_root(root); } else { + /* Look up the root from the arguments. */ root = btrfs_get_fs_root(info, sk->tree_id, true); - if (IS_ERR(root)) { - btrfs_free_path(path); + if (IS_ERR(root)) return PTR_ERR(root); - } } key.objectid = sk->min_objectid; @@ -2250,16 +1625,19 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { - ret = -EFAULT; - if (fault_in_writeable(ubuf + sk_offset, *buf_size - sk_offset)) + /* + * Ensure that the whole user buffer is faulted in at sub-page + * granularity, otherwise the loop may live-lock. + */ + if (fault_in_subpage_writeable(ubuf + sk_offset, *buf_size - sk_offset)) { + ret = -EFAULT; break; + } ret = btrfs_search_forward(root, &key, path, sk->min_transid); - if (ret != 0) { - if (ret > 0) - ret = 0; - goto err; - } + if (ret) + break; + ret = copy_to_sk(path, &key, sk, buf_size, ubuf, &sk_offset, &num_found); btrfs_release_path(path); @@ -2267,36 +1645,32 @@ static noinline int search_ioctl(struct inode *inode, break; } + /* Normalize return values from btrfs_search_forward() and copy_to_sk(). */ if (ret > 0) ret = 0; -err: + sk->nr_items = num_found; btrfs_put_root(root); - btrfs_free_path(path); return ret; } -static noinline int btrfs_ioctl_tree_search(struct file *file, - void __user *argp) +static noinline int btrfs_ioctl_tree_search(struct btrfs_root *root, + void __user *argp) { - struct btrfs_ioctl_search_args __user *uargs; + struct btrfs_ioctl_search_args __user *uargs = argp; struct btrfs_ioctl_search_key sk; - struct inode *inode; int ret; - size_t buf_size; + u64 buf_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - uargs = (struct btrfs_ioctl_search_args __user *)argp; - if (copy_from_user(&sk, &uargs->key, sizeof(sk))) return -EFAULT; buf_size = sizeof(uargs->buf); - inode = file_inode(file); - ret = search_ioctl(inode, &sk, &buf_size, uargs->buf); + ret = search_ioctl(root, &sk, &buf_size, uargs->buf); /* * In the origin implementation an overflow is handled by returning a @@ -2310,21 +1684,19 @@ static noinline int btrfs_ioctl_tree_search(struct file *file, return ret; } -static noinline int btrfs_ioctl_tree_search_v2(struct file *file, +static noinline int btrfs_ioctl_tree_search_v2(struct btrfs_root *root, void __user *argp) { - struct btrfs_ioctl_search_args_v2 __user *uarg; + struct btrfs_ioctl_search_args_v2 __user *uarg = argp; struct btrfs_ioctl_search_args_v2 args; - struct inode *inode; int ret; - size_t buf_size; - const size_t buf_limit = SZ_16M; + u64 buf_size; + const u64 buf_limit = SZ_16M; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* copy search header and buffer size */ - uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp; if (copy_from_user(&args, uarg, sizeof(args))) return -EFAULT; @@ -2334,8 +1706,7 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file, if (buf_size > buf_limit) buf_size = buf_limit; - inode = file_inode(file); - ret = search_ioctl(inode, &args.key, &buf_size, + ret = search_ioctl(root, &args.key, &buf_size, (char __user *)(&uarg->buf[0])); if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key))) ret = -EFAULT; @@ -2362,7 +1733,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, int total_len = 0; struct btrfs_inode_ref *iref; struct extent_buffer *l; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); if (dirid == BTRFS_FIRST_FREE_OBJECTID) { name[0]='\0'; @@ -2423,28 +1794,25 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, ret = 0; out: btrfs_put_root(root); - btrfs_free_path(path); return ret; } -static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, +static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, struct inode *inode, struct btrfs_ioctl_ino_lookup_user_args *args) { struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; - struct super_block *sb = inode->i_sb; - struct btrfs_key upper_limit = BTRFS_I(inode)->location; - u64 treeid = BTRFS_I(inode)->root->root_key.objectid; + u64 upper_limit = btrfs_ino(BTRFS_I(inode)); + u64 treeid = btrfs_root_id(BTRFS_I(inode)->root); u64 dirid = args->dirid; unsigned long item_off; unsigned long item_len; struct btrfs_inode_ref *iref; struct btrfs_root_ref *rref; struct btrfs_root *root = NULL; - struct btrfs_path *path; - struct btrfs_key key, key2; + BTRFS_PATH_AUTO_FREE(path); + struct btrfs_key key; struct extent_buffer *leaf; - struct inode *temp_inode; char *ptr; int slot; int len; @@ -2459,19 +1827,19 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, * If the bottom subvolume does not exist directly under upper_limit, * construct the path in from the bottom up. */ - if (dirid != upper_limit.objectid) { + if (dirid != upper_limit) { ptr = &args->path[BTRFS_INO_LOOKUP_USER_PATH_MAX - 1]; root = btrfs_get_fs_root(fs_info, treeid, true); - if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; - } + if (IS_ERR(root)) + return PTR_ERR(root); key.objectid = dirid; key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; while (1) { + struct btrfs_inode *temp_inode; + ret = btrfs_search_backwards(root, &key, path); if (ret < 0) goto out_put; @@ -2496,45 +1864,32 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, read_extent_buffer(leaf, ptr, (unsigned long)(iref + 1), len); - /* Check the read+exec permission of this directory */ - ret = btrfs_previous_item(root, path, dirid, - BTRFS_INODE_ITEM_KEY); - if (ret < 0) { - goto out_put; - } else if (ret > 0) { - ret = -ENOENT; - goto out_put; - } - - leaf = path->nodes[0]; - slot = path->slots[0]; - btrfs_item_key_to_cpu(leaf, &key2, slot); - if (key2.objectid != dirid) { - ret = -ENOENT; - goto out_put; - } - - temp_inode = btrfs_iget(sb, key2.objectid, root); + /* + * We don't need the path anymore, so release it and + * avoid deadlocks and lockdep warnings in case + * btrfs_iget() needs to lookup the inode from its root + * btree and lock the same leaf. + */ + btrfs_release_path(path); + temp_inode = btrfs_iget(key.offset, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); goto out_put; } - ret = inode_permission(mnt_userns, temp_inode, + /* Check the read+exec permission of this directory. */ + ret = inode_permission(idmap, &temp_inode->vfs_inode, MAY_READ | MAY_EXEC); - iput(temp_inode); - if (ret) { - ret = -EACCES; + iput(&temp_inode->vfs_inode); + if (ret) goto out_put; - } - if (key.offset == upper_limit.objectid) + if (key.offset == upper_limit) break; if (key.objectid == BTRFS_FIRST_FREE_OBJECTID) { ret = -EACCES; goto out_put; } - btrfs_release_path(path); key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid; @@ -2552,12 +1907,10 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, key.type = BTRFS_ROOT_REF_KEY; key.offset = args->treeid; ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = -ENOENT; - goto out; - } + if (ret < 0) + return ret; + else if (ret > 0) + return -ENOENT; leaf = path->nodes[0]; slot = path->slots[0]; @@ -2567,10 +1920,8 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, item_len = btrfs_item_size(leaf, slot); /* Check if dirid in ROOT_REF corresponds to passed dirid */ rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref); - if (args->dirid != btrfs_root_ref_dirid(leaf, rref)) { - ret = -EINVAL; - goto out; - } + if (args->dirid != btrfs_root_ref_dirid(leaf, rref)) + return -EINVAL; /* Copy subvolume's name */ item_off += sizeof(struct btrfs_root_ref); @@ -2580,30 +1931,26 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, out_put: btrfs_put_root(root); -out: - btrfs_free_path(path); + return ret; } -static noinline int btrfs_ioctl_ino_lookup(struct file *file, +static noinline int btrfs_ioctl_ino_lookup(struct btrfs_root *root, void __user *argp) { struct btrfs_ioctl_ino_lookup_args *args; - struct inode *inode; int ret = 0; args = memdup_user(argp, sizeof(*args)); if (IS_ERR(args)) return PTR_ERR(args); - inode = file_inode(file); - /* * Unprivileged query to obtain the containing subvolume root id. The * path is reset so it's consistent with btrfs_search_path_in_tree. */ if (args->treeid == 0) - args->treeid = BTRFS_I(inode)->root->root_key.objectid; + args->treeid = btrfs_root_id(root); if (args->objectid == BTRFS_FIRST_FREE_OBJECTID) { args->name[0] = 0; @@ -2615,7 +1962,7 @@ static noinline int btrfs_ioctl_ino_lookup(struct file *file, goto out; } - ret = btrfs_search_path_in_tree(BTRFS_I(inode)->root->fs_info, + ret = btrfs_search_path_in_tree(root->fs_info, args->treeid, args->objectid, args->name); @@ -2652,7 +1999,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp) inode = file_inode(file); if (args->dirid == BTRFS_FIRST_FREE_OBJECTID && - BTRFS_I(inode)->location.objectid != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) { /* * The subvolume does not exist under fd with which this is * called @@ -2661,7 +2008,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp) return -EACCES; } - ret = btrfs_search_path_in_tree_user(file_mnt_user_ns(file), inode, args); + ret = btrfs_search_path_in_tree_user(file_mnt_idmap(file), inode, args); if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) ret = -EFAULT; @@ -2671,7 +2018,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp) } /* Get the subvolume information in BTRFS_ROOT_ITEM and BTRFS_ROOT_BACKREF */ -static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) +static int btrfs_ioctl_get_subvol_info(struct inode *inode, void __user *argp) { struct btrfs_ioctl_get_subvol_info_args *subvol_info; struct btrfs_fs_info *fs_info; @@ -2683,7 +2030,6 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) struct extent_buffer *leaf; unsigned long item_off; unsigned long item_len; - struct inode *inode; int slot; int ret = 0; @@ -2697,11 +2043,10 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) return -ENOMEM; } - inode = file_inode(file); fs_info = BTRFS_I(inode)->root->fs_info; /* Get root_item of inode's subvolume */ - key.objectid = BTRFS_I(inode)->root->root_key.objectid; + key.objectid = btrfs_root_id(BTRFS_I(inode)->root); root = btrfs_get_fs_root(fs_info, key.objectid, true); if (IS_ERR(root)) { ret = PTR_ERR(root); @@ -2748,7 +2093,7 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) ret = btrfs_next_leaf(fs_info->tree_root, path); if (ret < 0) { goto out; - } else if (ret > 0) { + } else if (unlikely(ret > 0)) { ret = -EUCLEAN; goto out; } @@ -2776,6 +2121,8 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) } } + btrfs_free_path(path); + path = NULL; if (copy_to_user(argp, subvol_info, sizeof(*subvol_info))) ret = -EFAULT; @@ -2791,15 +2138,14 @@ out_free: * Return ROOT_REF information of the subvolume containing this inode * except the subvolume name. */ -static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp) +static int btrfs_ioctl_get_subvol_rootref(struct btrfs_root *root, + void __user *argp) { struct btrfs_ioctl_get_subvol_rootref_args *rootrefs; struct btrfs_root_ref *rref; - struct btrfs_root *root; struct btrfs_path *path; struct btrfs_key key; struct extent_buffer *leaf; - struct inode *inode; u64 objectid; int slot; int ret; @@ -2815,15 +2161,13 @@ static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp) return PTR_ERR(rootrefs); } - inode = file_inode(file); - root = BTRFS_I(inode)->root->fs_info->tree_root; - objectid = BTRFS_I(inode)->root->root_key.objectid; - + objectid = btrfs_root_id(root); key.objectid = objectid; key.type = BTRFS_ROOT_REF_KEY; key.offset = rootrefs->min_treeid; found = 0; + root = root->fs_info->tree_root; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) { goto out; @@ -2832,7 +2176,7 @@ static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp) ret = btrfs_next_leaf(root, path); if (ret < 0) { goto out; - } else if (ret > 0) { + } else if (unlikely(ret > 0)) { ret = -EUCLEAN; goto out; } @@ -2861,13 +2205,15 @@ static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp) ret = btrfs_next_item(root, path); if (ret < 0) { goto out; - } else if (ret > 0) { + } else if (unlikely(ret > 0)) { ret = -EUCLEAN; goto out; } } out: + btrfs_free_path(path); + if (!ret || ret == -EOVERFLOW) { rootrefs->num_items = found; /* update min_treeid for next search */ @@ -2879,7 +2225,6 @@ out: } kfree(rootrefs); - btrfs_free_path(path); return ret; } @@ -2889,27 +2234,33 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, bool destroy_v2) { struct dentry *parent = file->f_path.dentry; - struct btrfs_fs_info *fs_info = btrfs_sb(parent->d_sb); struct dentry *dentry; struct inode *dir = d_inode(parent); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct inode *inode; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *dest = NULL; struct btrfs_ioctl_vol_args *vol_args = NULL; struct btrfs_ioctl_vol_args_v2 *vol_args2 = NULL; - struct user_namespace *mnt_userns = file_mnt_user_ns(file); + struct mnt_idmap *idmap = file_mnt_idmap(file); char *subvol_name, *subvol_name_ptr = NULL; - int subvol_namelen; - int err = 0; + int ret = 0; bool destroy_parent = false; + /* We don't support snapshots with extent tree v2 yet. */ + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { + btrfs_err(fs_info, + "extent tree v2 doesn't support snapshot deletion yet"); + return -EOPNOTSUPP; + } + if (destroy_v2) { vol_args2 = memdup_user(arg, sizeof(*vol_args2)); if (IS_ERR(vol_args2)) return PTR_ERR(vol_args2); if (vol_args2->flags & ~BTRFS_SUBVOL_DELETE_ARGS_MASK) { - err = -EOPNOTSUPP; + ret = -EOPNOTSUPP; goto out; } @@ -2918,29 +2269,31 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, * name, same as v1 currently does. */ if (!(vol_args2->flags & BTRFS_SUBVOL_SPEC_BY_ID)) { - vol_args2->name[BTRFS_SUBVOL_NAME_MAX] = 0; + ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args2); + if (ret < 0) + goto out; subvol_name = vol_args2->name; - err = mnt_want_write_file(file); - if (err) + ret = mnt_want_write_file(file); + if (ret) goto out; } else { struct inode *old_dir; if (vol_args2->subvolid < BTRFS_FIRST_FREE_OBJECTID) { - err = -EINVAL; + ret = -EINVAL; goto out; } - err = mnt_want_write_file(file); - if (err) + ret = mnt_want_write_file(file); + if (ret) goto out; dentry = btrfs_get_dentry(fs_info->sb, BTRFS_FIRST_FREE_OBJECTID, - vol_args2->subvolid, 0, 0); + vol_args2->subvolid, 0); if (IS_ERR(dentry)) { - err = PTR_ERR(dentry); + ret = PTR_ERR(dentry); goto out_drop_write; } @@ -2960,7 +2313,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, */ dput(dentry); if (IS_ERR(parent)) { - err = PTR_ERR(parent); + ret = PTR_ERR(parent); goto out_drop_write; } old_dir = dir; @@ -2983,15 +2336,15 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, * anywhere in the filesystem the user wouldn't be able * to delete without an idmapped mount. */ - if (old_dir != dir && mnt_userns != &init_user_ns) { - err = -EOPNOTSUPP; + if (old_dir != dir && idmap != &nop_mnt_idmap) { + ret = -EOPNOTSUPP; goto free_parent; } subvol_name_ptr = btrfs_get_subvol_name_from_objectid( fs_info, vol_args2->subvolid); if (IS_ERR(subvol_name_ptr)) { - err = PTR_ERR(subvol_name_ptr); + ret = PTR_ERR(subvol_name_ptr); goto free_parent; } /* subvol_name_ptr is already nul terminated */ @@ -3002,39 +2355,32 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, if (IS_ERR(vol_args)) return PTR_ERR(vol_args); - vol_args->name[BTRFS_PATH_NAME_MAX] = 0; + ret = btrfs_check_ioctl_vol_args_path(vol_args); + if (ret < 0) + goto out; + subvol_name = vol_args->name; - err = mnt_want_write_file(file); - if (err) + ret = mnt_want_write_file(file); + if (ret) goto out; } - subvol_namelen = strlen(subvol_name); - if (strchr(subvol_name, '/') || - strncmp(subvol_name, "..", subvol_namelen) == 0) { - err = -EINVAL; + strcmp(subvol_name, "..") == 0) { + ret = -EINVAL; goto free_subvol_name; } if (!S_ISDIR(dir->i_mode)) { - err = -ENOTDIR; + ret = -ENOTDIR; goto free_subvol_name; } - err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); - if (err == -EINTR) - goto free_subvol_name; - dentry = lookup_one(mnt_userns, subvol_name, parent, subvol_namelen); + dentry = start_removing_killable(idmap, parent, &QSTR(subvol_name)); if (IS_ERR(dentry)) { - err = PTR_ERR(dentry); - goto out_unlock_dir; - } - - if (d_really_is_negative(dentry)) { - err = -ENOENT; - goto out_dput; + ret = PTR_ERR(dentry); + goto out_end_removing; } inode = d_inode(dentry); @@ -3053,9 +2399,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, * Users who want to delete empty subvols should try * rmdir(2). */ - err = -EPERM; + ret = -EPERM; if (!btrfs_test_opt(fs_info, USER_SUBVOL_RM_ALLOWED)) - goto out_dput; + goto out_end_removing; /* * Do not allow deletion if the parent dir is the same @@ -3064,37 +2410,33 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, * of the subvol, not a random directory contained * within it. */ - err = -EINVAL; + ret = -EINVAL; if (root == dest) - goto out_dput; + goto out_end_removing; - err = inode_permission(mnt_userns, inode, MAY_WRITE | MAY_EXEC); - if (err) - goto out_dput; + ret = inode_permission(idmap, inode, MAY_WRITE | MAY_EXEC); + if (ret) + goto out_end_removing; } /* check if subvolume may be deleted by a user */ - err = btrfs_may_delete(mnt_userns, dir, dentry, 1); - if (err) - goto out_dput; + ret = btrfs_may_delete(idmap, dir, dentry, 1); + if (ret) + goto out_end_removing; if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) { - err = -EINVAL; - goto out_dput; + ret = -EINVAL; + goto out_end_removing; } - btrfs_inode_lock(inode, 0); - err = btrfs_delete_subvolume(dir, dentry); - btrfs_inode_unlock(inode, 0); - if (!err) { - fsnotify_rmdir(dir, dentry); - d_delete(dentry); - } + btrfs_inode_lock(BTRFS_I(inode), 0); + ret = btrfs_delete_subvolume(BTRFS_I(dir), dentry); + btrfs_inode_unlock(BTRFS_I(inode), 0); + if (!ret) + d_delete_notify(dir, dentry); -out_dput: - dput(dentry); -out_unlock_dir: - btrfs_inode_unlock(dir, 0); +out_end_removing: + end_removing(dentry); free_subvol_name: kfree(subvol_name_ptr); free_parent: @@ -3105,7 +2447,7 @@ out_drop_write: out: kfree(vol_args2); kfree(vol_args); - return err; + return ret; } static int btrfs_ioctl_defrag(struct file *file, void __user *argp) @@ -3139,18 +2481,37 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) * running and allows defrag on files open in read-only mode. */ if (!capable(CAP_SYS_ADMIN) && - inode_permission(&init_user_ns, inode, MAY_WRITE)) { + inode_permission(&nop_mnt_idmap, inode, MAY_WRITE)) { ret = -EPERM; goto out; } + /* + * Don't allow defrag on pre-content watched files, as it could + * populate the page cache with 0's via readahead. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + ret = -EINVAL; + goto out; + } + if (argp) { if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; goto out; } - /* compression requires us to start the IO */ - if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) { + ret = -EOPNOTSUPP; + goto out; + } + if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS) && + (range.flags & BTRFS_DEFRAG_RANGE_NOCOMPRESS)) { + ret = -EINVAL; + goto out; + } + /* Compression or no-compression require to start the IO. */ + if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS) || + (range.flags & BTRFS_DEFRAG_RANGE_NOCOMPRESS)) { range.flags |= BTRFS_DEFRAG_RANGE_START_IO; range.extent_thresh = (u32)-1; } @@ -3158,7 +2519,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) /* the rest are all set to zero by kzalloc */ range.len = (u64)-1; } - ret = btrfs_defrag_file(file_inode(file), &file->f_ra, + ret = btrfs_defrag_file(BTRFS_I(file_inode(file)), &file->f_ra, &range, BTRFS_OLDEST_GENERATION, 0); if (ret > 0) ret = 0; @@ -3180,6 +2541,17 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { + btrfs_err(fs_info, "device add not supported on extent tree v2 yet"); + return -EINVAL; + } + + if (fs_info->fs_devices->temp_fsid) { + btrfs_err(fs_info, + "device add not supported on cloned temp-fsid mount"); + return -EINVAL; + } + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_ADD)) { if (!btrfs_exclop_start_try_lock(fs_info, BTRFS_EXCLOP_DEV_ADD)) return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; @@ -3200,12 +2572,16 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg) goto out; } - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + ret = btrfs_check_ioctl_vol_args_path(vol_args); + if (ret < 0) + goto out_free; + ret = btrfs_init_new_device(fs_info, vol_args->name); if (!ret) btrfs_info(fs_info, "disk added %s", vol_args->name); +out_free: kfree(vol_args); out: if (restore_op) @@ -3219,10 +2595,9 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) { BTRFS_DEV_LOOKUP_ARGS(args); struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_vol_args_v2 *vol_args; - struct block_device *bdev = NULL; - fmode_t mode; + struct file *bdev_file = NULL; int ret; bool cancel = false; @@ -3238,7 +2613,10 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) goto out; } - vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0'; + ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args); + if (ret < 0) + goto out; + if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) { args.devid = vol_args->devid; } else if (!strcmp("cancel", vol_args->name)) { @@ -3259,7 +2637,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) goto err_drop; /* Exclusive operation is now claimed */ - ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + ret = btrfs_rm_device(fs_info, &args, &bdev_file); btrfs_exclop_finish(fs_info); @@ -3273,8 +2651,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) } err_drop: mnt_drop_write_file(file); - if (bdev) - blkdev_put(bdev, mode); + if (bdev_file) + bdev_fput(bdev_file); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -3285,12 +2663,11 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) { BTRFS_DEV_LOOKUP_ARGS(args); struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_vol_args *vol_args; - struct block_device *bdev = NULL; - fmode_t mode; + struct file *bdev_file = NULL; int ret; - bool cancel; + bool cancel = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -3299,7 +2676,10 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) if (IS_ERR(vol_args)) return PTR_ERR(vol_args); - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + ret = btrfs_check_ioctl_vol_args_path(vol_args); + if (ret < 0) + goto out_free; + if (!strcmp("cancel", vol_args->name)) { cancel = true; } else { @@ -3315,22 +2695,23 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE, cancel); if (ret == 0) { - ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + ret = btrfs_rm_device(fs_info, &args, &bdev_file); if (!ret) btrfs_info(fs_info, "disk deleted %s", vol_args->name); btrfs_exclop_finish(fs_info); } mnt_drop_write_file(file); - if (bdev) - blkdev_put(bdev, mode); + if (bdev_file) + bdev_fput(bdev_file); out: btrfs_put_dev_args_from_path(&args); +out_free: kfree(vol_args); return ret; } -static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, +static long btrfs_ioctl_fs_info(const struct btrfs_fs_info *fs_info, void __user *arg) { struct btrfs_ioctl_fs_info_args *fi_args; @@ -3367,7 +2748,7 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, } if (flags_in & BTRFS_FS_INFO_FLAG_GENERATION) { - fi_args->generation = fs_info->generation; + fi_args->generation = btrfs_get_fs_generation(fs_info); fi_args->flags |= BTRFS_FS_INFO_FLAG_GENERATION; } @@ -3384,7 +2765,7 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, return ret; } -static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, +static long btrfs_ioctl_dev_info(const struct btrfs_fs_info *fs_info, void __user *arg) { BTRFS_DEV_LOOKUP_ARGS(args); @@ -3411,13 +2792,11 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, di_args->bytes_used = btrfs_device_get_bytes_used(dev); di_args->total_bytes = btrfs_device_get_total_bytes(dev); memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); - if (dev->name) { - strncpy(di_args->path, rcu_str_deref(dev->name), - sizeof(di_args->path) - 1); - di_args->path[sizeof(di_args->path) - 1] = 0; - } else { + memcpy(di_args->fsid, dev->fs_devices->fsid, BTRFS_UUID_SIZE); + if (dev->name) + strscpy(di_args->path, btrfs_dev_name(dev), sizeof(di_args->path)); + else di_args->path[0] = '\0'; - } out: rcu_read_unlock(); @@ -3431,13 +2810,14 @@ out: static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_root *new_root; struct btrfs_dir_item *di; struct btrfs_trans_handle *trans; struct btrfs_path *path = NULL; struct btrfs_disk_key disk_key; + struct fscrypt_str name = FSTR_INIT("default", 7); u64 objectid = 0; u64 dir_id; int ret; @@ -3462,7 +2842,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } - if (!is_fstree(new_root->root_key.objectid)) { + if (!btrfs_is_fstree(btrfs_root_id(new_root))) { ret = -ENOENT; goto out_free; } @@ -3481,7 +2861,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) dir_id = btrfs_super_root_dir(fs_info->super_copy); di = btrfs_lookup_dir_item(trans, fs_info->tree_root, path, - dir_id, "default", 7, 1); + dir_id, &name, 1); if (IS_ERR_OR_NULL(di)) { btrfs_release_path(path); btrfs_end_transaction(trans); @@ -3493,7 +2873,6 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) 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_release_path(path); btrfs_set_fs_incompat(fs_info, DEFAULT_SUBVOL); @@ -3524,10 +2903,10 @@ static void get_block_group_info(struct list_head *groups_list, static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, void __user *arg) { - struct btrfs_ioctl_space_args space_args; + struct btrfs_ioctl_space_args space_args = { 0 }; struct btrfs_ioctl_space_info space; struct btrfs_ioctl_space_info *dest; - struct btrfs_ioctl_space_info *dest_orig; + struct btrfs_ioctl_space_info AUTO_KFREE(dest_orig); struct btrfs_ioctl_space_info __user *user_dest; struct btrfs_space_info *info; static const u64 types[] = { @@ -3648,9 +3027,8 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, (arg + sizeof(struct btrfs_ioctl_space_args)); if (copy_to_user(user_dest, dest_orig, alloc_size)) - ret = -EFAULT; + return -EFAULT; - kfree(dest_orig); out: if (ret == 0 && copy_to_user(arg, &space_args, sizeof(space_args))) ret = -EFAULT; @@ -3664,13 +3042,20 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root, struct btrfs_trans_handle *trans; u64 transid; + /* + * Start orphan cleanup here for the given root in case it hasn't been + * started already by other means. Errors are handled in the other + * functions during transaction commit. + */ + btrfs_orphan_cleanup(root); + 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; + transid = btrfs_get_last_trans_committed(root->fs_info); goto out; } transid = trans->transid; @@ -3685,30 +3070,39 @@ out: static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info, void __user *argp) { - u64 transid; + /* By default wait for the current transaction. */ + u64 transid = 0; - if (argp) { + if (argp) if (copy_from_user(&transid, argp, sizeof(transid))) return -EFAULT; - } else { - transid = 0; /* current trans */ - } + return btrfs_wait_for_commit(fs_info, transid); } static long btrfs_ioctl_scrub(struct file *file, void __user *arg) { - struct btrfs_fs_info *fs_info = btrfs_sb(file_inode(file)->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file)); struct btrfs_ioctl_scrub_args *sa; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { + btrfs_err(fs_info, "scrub: extent tree v2 not yet supported"); + return -EINVAL; + } + sa = memdup_user(arg, sizeof(*sa)); if (IS_ERR(sa)) return PTR_ERR(sa); + if (sa->flags & ~BTRFS_SCRUB_SUPPORTED_FLAGS) { + ret = -EOPNOTSUPP; + goto out; + } + if (!(sa->flags & BTRFS_SCRUB_READONLY)) { ret = mnt_want_write_file(file); if (ret) @@ -3804,6 +3198,11 @@ static long btrfs_ioctl_dev_replace(struct btrfs_fs_info *fs_info, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { + btrfs_err(fs_info, "device replace not supported on extent tree v2 yet"); + return -EINVAL; + } + p = memdup_user(arg, sizeof(*p)); if (IS_ERR(p)) return PTR_ERR(p); @@ -3848,7 +3247,7 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) u64 rel_ptr; int size; struct btrfs_ioctl_ino_path_args *ipa = NULL; - struct inode_fs_paths *ipath = NULL; + struct inode_fs_paths *ipath __free(inode_fs_paths) = NULL; struct btrfs_path *path; if (!capable(CAP_DAC_READ_SEARCH)) @@ -3885,6 +3284,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) ipath->fspath->val[i] = rel_ptr; } + btrfs_free_path(path); + path = NULL; ret = copy_to_user((void __user *)(unsigned long)ipa->fspath, ipath->fspath, size); if (ret) { @@ -3894,32 +3295,11 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) 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_fs_info *fs_info, void __user *arg, int version) { @@ -3927,7 +3307,6 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, int size; struct btrfs_ioctl_logical_ino_args *loi; struct btrfs_data_container *inodes = NULL; - struct btrfs_path *path = NULL; bool ignore_offset; if (!capable(CAP_SYS_ADMIN)) @@ -3955,21 +3334,13 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, size = min_t(u32, loi->size, SZ_16M); } - path = btrfs_alloc_path(); - if (!path) { - ret = -ENOMEM; - goto out; - } - inodes = init_data_container(size); if (IS_ERR(inodes)) { ret = PTR_ERR(inodes); - inodes = NULL; - goto out; + goto out_loi; } - ret = iterate_inodes_from_logical(loi->logical, fs_info, path, - build_ino_list, inodes, ignore_offset); + ret = iterate_inodes_from_logical(loi->logical, fs_info, inodes, ignore_offset); if (ret == -EINVAL) ret = -ENOENT; if (ret < 0) @@ -3981,7 +3352,6 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, ret = -EFAULT; out: - btrfs_free_path(path); kvfree(inodes); out_loi: kfree(loi); @@ -4012,19 +3382,81 @@ void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info, spin_unlock(&fs_info->balance_lock); } +/* + * Try to acquire fs_info::balance_mutex as well as set BTRFS_EXLCOP_BALANCE as + * required. + * + * @fs_info: the filesystem + * @excl_acquired: ptr to boolean value which is set to false in case balance + * is being resumed + * + * Return 0 on success in which case both fs_info::balance is acquired as well + * as exclusive ops are blocked. In case of failure return an error code. + */ +static int btrfs_try_lock_balance(struct btrfs_fs_info *fs_info, bool *excl_acquired) +{ + int ret; + + /* + * Exclusive operation is locked. Three possibilities: + * (1) some other op is running + * (2) balance is running + * (3) balance is paused -- special case (think resume) + */ + while (1) { + if (btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { + *excl_acquired = true; + mutex_lock(&fs_info->balance_mutex); + return 0; + } + + mutex_lock(&fs_info->balance_mutex); + if (fs_info->balance_ctl) { + /* This is either (2) or (3) */ + if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) { + /* This is (2) */ + ret = -EINPROGRESS; + goto out_failure; + + } else { + mutex_unlock(&fs_info->balance_mutex); + /* + * 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 && + !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) { + /* This is (3) */ + *excl_acquired = false; + return 0; + } + } + } else { + /* This is (1) */ + ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; + goto out_failure; + } + + mutex_unlock(&fs_info->balance_mutex); + } + +out_failure: + mutex_unlock(&fs_info->balance_mutex); + *excl_acquired = false; + return ret; +} + 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 */ + bool need_unlock = true; int ret; - if (!arg) - btrfs_warn(fs_info, - "IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18"); - if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -4032,106 +3464,55 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) if (ret) return ret; -again: - if (btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { - mutex_lock(&fs_info->balance_mutex); - need_unlock = true; - goto locked; + bargs = memdup_user(arg, sizeof(*bargs)); + if (IS_ERR(bargs)) { + ret = PTR_ERR(bargs); + bargs = NULL; + goto out; } - /* - * mut. excl. ops lock is locked. Three possibilities: - * (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 (!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) { - mutex_unlock(&fs_info->balance_mutex); - /* - * 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 && - !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) { - /* this is (3) */ - need_unlock = false; - goto locked; - } - - mutex_unlock(&fs_info->balance_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; + ret = btrfs_try_lock_balance(fs_info, &need_unlock); + if (ret) goto out; - } -locked: + lockdep_assert_held(&fs_info->balance_mutex); - if (arg) { - bargs = memdup_user(arg, sizeof(*bargs)); - if (IS_ERR(bargs)) { - ret = PTR_ERR(bargs); + if (bargs->flags & BTRFS_BALANCE_RESUME) { + if (!fs_info->balance_ctl) { + ret = -ENOTCONN; 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); + btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE); - bctl = fs_info->balance_ctl; - spin_lock(&fs_info->balance_lock); - bctl->flags |= BTRFS_BALANCE_RESUME; - spin_unlock(&fs_info->balance_lock); - btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE); + goto do_balance; + } - goto do_balance; - } - } else { - bargs = NULL; + if (bargs->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_unlock; } if (fs_info->balance_ctl) { ret = -EINPROGRESS; - goto out_bargs; + goto out_unlock; } bctl = kzalloc(sizeof(*bctl), GFP_KERNEL); if (!bctl) { ret = -ENOMEM; - goto out_bargs; - } - - 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; + goto out_unlock; } - if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { - ret = -EINVAL; - goto out_bctl; - } + 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; do_balance: /* * Ownership of bctl and exclusive operation goes to btrfs_balance. @@ -4144,21 +3525,19 @@ do_balance: ret = btrfs_balance(fs_info, bctl, bargs); bctl = NULL; - if ((ret == 0 || ret == -ECANCELED) && arg) { + if (ret == 0 || ret == -ECANCELED) { if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; } -out_bctl: kfree(bctl); -out_bargs: - kfree(bargs); out_unlock: mutex_unlock(&fs_info->balance_mutex); if (need_unlock) btrfs_exclop_finish(fs_info); out: mnt_drop_write_file(file); + kfree(bargs); return ret; } @@ -4180,7 +3559,7 @@ static long btrfs_ioctl_balance_ctl(struct btrfs_fs_info *fs_info, int cmd) static long btrfs_ioctl_balance_progress(struct btrfs_fs_info *fs_info, void __user *arg) { - struct btrfs_ioctl_balance_args *bargs; + struct btrfs_ioctl_balance_args AUTO_KFREE(bargs); int ret = 0; if (!capable(CAP_SYS_ADMIN)) @@ -4202,8 +3581,6 @@ static long btrfs_ioctl_balance_progress(struct btrfs_fs_info *fs_info, if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; - - kfree(bargs); out: mutex_unlock(&fs_info->balance_mutex); return ret; @@ -4212,7 +3589,7 @@ out: static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_quota_ctl_args *sa; int ret; @@ -4229,14 +3606,43 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) goto drop_write; } - down_write(&fs_info->subvol_sem); - switch (sa->cmd) { case BTRFS_QUOTA_CTL_ENABLE: - ret = btrfs_quota_enable(fs_info); + case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA: + down_write(&fs_info->subvol_sem); + ret = btrfs_quota_enable(fs_info, sa); + up_write(&fs_info->subvol_sem); break; case BTRFS_QUOTA_CTL_DISABLE: + /* + * Lock the cleaner mutex to prevent races with concurrent + * relocation, because relocation may be building backrefs for + * blocks of the quota root while we are deleting the root. This + * is like dropping fs roots of deleted snapshots/subvolumes, we + * need the same protection. + * + * This also prevents races between concurrent tasks trying to + * disable quotas, because we will unlock and relock + * qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes. + * + * We take this here because we have the dependency of + * + * inode_lock -> subvol_sem + * + * because of rename. With relocation we can prealloc extents, + * so that makes the dependency chain + * + * cleaner_mutex -> inode_lock -> subvol_sem + * + * so we must take the cleaner_mutex here before we take the + * subvol_sem. The deadlock can't actually happen, but this + * quiets lockdep. + */ + mutex_lock(&fs_info->cleaner_mutex); + down_write(&fs_info->subvol_sem); ret = btrfs_quota_disable(fs_info); + up_write(&fs_info->subvol_sem); + mutex_unlock(&fs_info->cleaner_mutex); break; default: ret = -EINVAL; @@ -4244,7 +3650,6 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) } kfree(sa); - up_write(&fs_info->subvol_sem); drop_write: mnt_drop_write_file(file); return ret; @@ -4253,9 +3658,10 @@ drop_write: static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_ioctl_qgroup_assign_args *sa; + struct btrfs_qgroup_list *prealloc = NULL; struct btrfs_trans_handle *trans; int ret; int err; @@ -4263,6 +3669,9 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!btrfs_qgroup_enabled(fs_info)) + return -ENOTCONN; + ret = mnt_want_write_file(file); if (ret) return ret; @@ -4273,28 +3682,45 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) goto drop_write; } + if (sa->assign) { + prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); + if (!prealloc) { + ret = -ENOMEM; + goto out; + } + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out; } + /* + * Prealloc ownership is moved to the relation handler, there it's used + * or freed on error. + */ if (sa->assign) { - ret = btrfs_add_qgroup_relation(trans, sa->src, sa->dst); + ret = btrfs_add_qgroup_relation(trans, sa->src, sa->dst, prealloc); + prealloc = NULL; } else { ret = btrfs_del_qgroup_relation(trans, sa->src, sa->dst); } /* update qgroup status and info */ + mutex_lock(&fs_info->qgroup_ioctl_lock); err = btrfs_run_qgroups(trans); + mutex_unlock(&fs_info->qgroup_ioctl_lock); if (err < 0) - btrfs_handle_fs_error(fs_info, err, - "failed to update qgroup status and info"); + btrfs_warn(fs_info, + "qgroup status update failed after %s relation, marked as inconsistent", + sa->assign ? "adding" : "deleting"); err = btrfs_end_transaction(trans); if (err && !ret) ret = err; out: + kfree(prealloc); kfree(sa); drop_write: mnt_drop_write_file(file); @@ -4313,6 +3739,9 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!btrfs_qgroup_enabled(root->fs_info)) + return -ENOTCONN; + ret = mnt_want_write_file(file); if (ret) return ret; @@ -4328,6 +3757,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && btrfs_is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -4364,6 +3798,9 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!btrfs_qgroup_enabled(root->fs_info)) + return -ENOTCONN; + ret = mnt_want_write_file(file); if (ret) return ret; @@ -4383,7 +3820,7 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg) qgroupid = sa->qgroupid; if (!qgroupid) { /* take the current subvol as qgroup */ - qgroupid = root->root_key.objectid; + qgroupid = btrfs_root_id(root); } ret = btrfs_limit_qgroup(trans, qgroupid, &sa->lim); @@ -4402,13 +3839,16 @@ drop_write: static long btrfs_ioctl_quota_rescan(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_quota_rescan_args *qsa; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!btrfs_qgroup_enabled(fs_info)) + return -ENOTCONN; + ret = mnt_want_write_file(file); if (ret) return ret; @@ -4452,8 +3892,7 @@ static long btrfs_ioctl_quota_rescan_status(struct btrfs_fs_info *fs_info, return 0; } -static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info, - void __user *arg) +static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -4462,11 +3901,11 @@ static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info, } static long _btrfs_ioctl_set_received_subvol(struct file *file, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct btrfs_ioctl_received_subvol_args *sa) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_root_item *root_item = &root->root_item; struct btrfs_trans_handle *trans; @@ -4474,7 +3913,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, int ret = 0; int received_uuid_changed; - if (!inode_owner_or_capable(mnt_userns, inode)) + if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -4514,8 +3953,8 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, !btrfs_is_empty_uuid(root_item->received_uuid)) { ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, - root->root_key.objectid); - if (ret && ret != -ENOENT) { + btrfs_root_id(root)); + if (unlikely(ret && ret != -ENOENT)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; @@ -4538,8 +3977,8 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) { ret = btrfs_uuid_tree_add(trans, sa->uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, - root->root_key.objectid); - if (ret < 0 && ret != -EEXIST) { + btrfs_root_id(root)); + if (unlikely(ret < 0 && ret != -EEXIST)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; @@ -4579,7 +4018,7 @@ static long btrfs_ioctl_set_received_subvol_32(struct file *file, args64->rtime.nsec = args32->rtime.nsec; args64->flags = args32->flags; - ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_user_ns(file), args64); + ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_idmap(file), args64); if (ret) goto out; @@ -4613,7 +4052,7 @@ static long btrfs_ioctl_set_received_subvol(struct file *file, if (IS_ERR(sa)) return PTR_ERR(sa); - ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_user_ns(file), sa); + ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_idmap(file), sa); if (ret) goto out; @@ -4654,7 +4093,7 @@ static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info, static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_super_block *super_block = fs_info->super_copy; struct btrfs_trans_handle *trans; @@ -4685,7 +4124,7 @@ static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg) } spin_lock(&fs_info->super_lock); - strcpy(super_block->label, label); + strscpy(super_block->label, label); spin_unlock(&fs_info->super_lock); ret = btrfs_commit_transaction(trans); @@ -4729,13 +4168,13 @@ static int btrfs_ioctl_get_features(struct btrfs_fs_info *fs_info, return 0; } -static int check_feature_bits(struct btrfs_fs_info *fs_info, +static int check_feature_bits(const struct btrfs_fs_info *fs_info, 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_name(set); - char *names; + const char AUTO_KFREE(names); u64 disallowed, unsupported; u64 set_mask = flags & change_mask; u64 clear_mask = ~flags & change_mask; @@ -4743,12 +4182,11 @@ static int check_feature_bits(struct btrfs_fs_info *fs_info, unsupported = set_mask & ~supported_flags; if (unsupported) { names = btrfs_printable_features(set, unsupported); - if (names) { + if (names) btrfs_warn(fs_info, "this kernel does not support the %s feature bit%s", names, strchr(names, ',') ? "s" : ""); - kfree(names); - } else + else btrfs_warn(fs_info, "this kernel does not support %s bits 0x%llx", type, unsupported); @@ -4758,12 +4196,11 @@ static int check_feature_bits(struct btrfs_fs_info *fs_info, disallowed = set_mask & ~safe_set; if (disallowed) { names = btrfs_printable_features(set, disallowed); - if (names) { + if (names) btrfs_warn(fs_info, "can't set the %s feature bit%s while mounted", names, strchr(names, ',') ? "s" : ""); - kfree(names); - } else + else btrfs_warn(fs_info, "can't set %s bits 0x%llx while mounted", type, disallowed); @@ -4773,12 +4210,11 @@ static int check_feature_bits(struct btrfs_fs_info *fs_info, disallowed = clear_mask & ~safe_clear; if (disallowed) { names = btrfs_printable_features(set, disallowed); - if (names) { + if (names) btrfs_warn(fs_info, "can't clear the %s feature bit%s while mounted", names, strchr(names, ',') ? "s" : ""); - kfree(names); - } else + else btrfs_warn(fs_info, "can't clear %s bits 0x%llx while mounted", type, disallowed); @@ -4797,7 +4233,7 @@ check_feature_bits(fs_info, FEAT_##mask_base, change_mask, flags, \ static int btrfs_ioctl_set_features(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_super_block *super_block = fs_info->super_copy; struct btrfs_ioctl_feature_flags flags[2]; @@ -4865,14 +4301,14 @@ out_drop_write: return ret; } -static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat) +static int _btrfs_ioctl_send(struct btrfs_root *root, void __user *argp, bool compat) { struct btrfs_ioctl_send_args *arg; int ret; if (compat) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_send_args_32 args32; + struct btrfs_ioctl_send_args_32 args32 = { 0 }; ret = copy_from_user(&args32, argp, sizeof(args32)); if (ret) @@ -4885,6 +4321,7 @@ static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat) arg->clone_sources = compat_ptr(args32.clone_sources); arg->parent_root = args32.parent_root; arg->flags = args32.flags; + arg->version = args32.version; memcpy(arg->reserved, args32.reserved, sizeof(args32.reserved)); #else @@ -4895,22 +4332,868 @@ static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat) if (IS_ERR(arg)) return PTR_ERR(arg); } - ret = btrfs_ioctl_send(file, arg); + ret = btrfs_ioctl_send(root, arg); kfree(arg); return ret; } +static int btrfs_ioctl_encoded_read(struct file *file, void __user *argp, + bool compat) +{ + struct btrfs_ioctl_encoded_io_args args = { 0 }; + size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, + flags); + size_t copy_end; + struct btrfs_inode *inode = BTRFS_I(file_inode(file)); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct extent_io_tree *io_tree = &inode->io_tree; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + loff_t pos; + struct kiocb kiocb; + ssize_t ret; + u64 disk_bytenr, disk_io_size; + struct extent_state *cached_state = NULL; + + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_acct; + } + + if (compat) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, + flags); + if (copy_from_user(&args32, argp, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + args.iov = compat_ptr(args32.iov); + args.iovcnt = args32.iovcnt; + args.offset = args32.offset; + args.flags = args32.flags; +#else + return -ENOTTY; +#endif + } else { + copy_end = copy_end_kernel; + if (copy_from_user(&args, argp, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + if (args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), + &iov, &iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&iter) == 0) { + ret = 0; + goto out_iov; + } + pos = args.offset; + ret = rw_verify_area(READ, file, &pos, args.len); + if (ret < 0) + goto out_iov; + + init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = pos; + + ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state, + &disk_bytenr, &disk_io_size); + + if (ret == -EIOCBQUEUED) { + bool unlocked = false; + u64 start, lockend, count; + + start = ALIGN_DOWN(kiocb.ki_pos, fs_info->sectorsize); + lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; + + if (args.compression) + count = disk_io_size; + else + count = args.len; + + ret = btrfs_encoded_read_regular(&kiocb, &iter, start, lockend, + &cached_state, disk_bytenr, + disk_io_size, count, + args.compression, &unlocked); + + if (!unlocked) { + btrfs_unlock_extent(io_tree, start, lockend, &cached_state); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); + } + } + + if (ret >= 0) { + fsnotify_access(file); + if (copy_to_user(argp + copy_end, + (char *)&args + copy_end_kernel, + sizeof(args) - copy_end_kernel)) + ret = -EFAULT; + } + +out_iov: + kfree(iov); +out_acct: + if (ret > 0) + add_rchar(current, ret); + inc_syscr(current); + return ret; +} + +static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool compat) +{ + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + loff_t pos; + struct kiocb kiocb; + ssize_t ret; + + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_acct; + } + + if (!(file->f_mode & FMODE_WRITE)) { + ret = -EBADF; + goto out_acct; + } + + if (compat) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + if (copy_from_user(&args32, argp, sizeof(args32))) { + ret = -EFAULT; + goto out_acct; + } + args.iov = compat_ptr(args32.iov); + args.iovcnt = args32.iovcnt; + args.offset = args32.offset; + args.flags = args32.flags; + args.len = args32.len; + args.unencoded_len = args32.unencoded_len; + args.unencoded_offset = args32.unencoded_offset; + args.compression = args32.compression; + args.encryption = args32.encryption; + memcpy(args.reserved, args32.reserved, sizeof(args.reserved)); +#else + return -ENOTTY; +#endif + } else { + if (copy_from_user(&args, argp, sizeof(args))) { + ret = -EFAULT; + goto out_acct; + } + } + + ret = -EINVAL; + if (args.flags != 0) + goto out_acct; + if (memchr_inv(args.reserved, 0, sizeof(args.reserved))) + goto out_acct; + if (args.compression == BTRFS_ENCODED_IO_COMPRESSION_NONE && + args.encryption == BTRFS_ENCODED_IO_ENCRYPTION_NONE) + goto out_acct; + if (args.compression >= BTRFS_ENCODED_IO_COMPRESSION_TYPES || + args.encryption >= BTRFS_ENCODED_IO_ENCRYPTION_TYPES) + goto out_acct; + if (args.unencoded_offset > args.unencoded_len) + goto out_acct; + if (args.len > args.unencoded_len - args.unencoded_offset) + goto out_acct; + + ret = import_iovec(ITER_SOURCE, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), + &iov, &iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&iter) == 0) { + ret = 0; + goto out_iov; + } + pos = args.offset; + ret = rw_verify_area(WRITE, file, &pos, args.len); + if (ret < 0) + goto out_iov; + + init_sync_kiocb(&kiocb, file); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); + if (ret) + goto out_iov; + kiocb.ki_pos = pos; + + file_start_write(file); + + ret = btrfs_do_write_iter(&kiocb, &iter, &args); + if (ret > 0) + fsnotify_modify(file); + + file_end_write(file); +out_iov: + kfree(iov); +out_acct: + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + +struct btrfs_uring_encoded_data { + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov; + struct iov_iter iter; +}; + +/* + * Context that's attached to an encoded read io_uring command, in cmd->pdu. It + * contains the fields in btrfs_uring_read_extent that are necessary to finish + * off and cleanup the I/O in btrfs_uring_read_finished. + */ +struct btrfs_uring_priv { + struct io_uring_cmd *cmd; + struct page **pages; + unsigned long nr_pages; + struct kiocb iocb; + struct iovec *iov; + struct iov_iter iter; + struct extent_state *cached_state; + u64 count; + u64 start; + u64 lockend; + int err; + bool compressed; +}; + +struct io_btrfs_cmd { + struct btrfs_uring_encoded_data *data; + struct btrfs_uring_priv *priv; +}; + +static void btrfs_uring_read_finished(struct io_tw_req tw_req, io_tw_token_t tw) +{ + struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req); + struct io_btrfs_cmd *bc = io_uring_cmd_to_pdu(cmd, struct io_btrfs_cmd); + struct btrfs_uring_priv *priv = bc->priv; + struct btrfs_inode *inode = BTRFS_I(file_inode(priv->iocb.ki_filp)); + struct extent_io_tree *io_tree = &inode->io_tree; + pgoff_t index; + u64 cur; + size_t page_offset; + ssize_t ret; + + /* The inode lock has already been acquired in btrfs_uring_read_extent. */ + btrfs_lockdep_inode_acquire(inode, i_rwsem); + + if (priv->err) { + ret = priv->err; + goto out; + } + + if (priv->compressed) { + index = 0; + page_offset = 0; + } else { + index = (priv->iocb.ki_pos - priv->start) >> PAGE_SHIFT; + page_offset = offset_in_page(priv->iocb.ki_pos - priv->start); + } + cur = 0; + while (cur < priv->count) { + size_t bytes = min_t(size_t, priv->count - cur, PAGE_SIZE - page_offset); + + if (copy_page_to_iter(priv->pages[index], page_offset, bytes, + &priv->iter) != bytes) { + ret = -EFAULT; + goto out; + } + + index++; + cur += bytes; + page_offset = 0; + } + ret = priv->count; + +out: + btrfs_unlock_extent(io_tree, priv->start, priv->lockend, &priv->cached_state); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); + + io_uring_cmd_done(cmd, ret, IO_URING_CMD_TASK_WORK_ISSUE_FLAGS); + add_rchar(current, ret); + + for (index = 0; index < priv->nr_pages; index++) + __free_page(priv->pages[index]); + + kfree(priv->pages); + kfree(priv->iov); + kfree(priv); + kfree(bc->data); +} + +void btrfs_uring_read_extent_endio(void *ctx, int err) +{ + struct btrfs_uring_priv *priv = ctx; + struct io_btrfs_cmd *bc = io_uring_cmd_to_pdu(priv->cmd, struct io_btrfs_cmd); + + priv->err = err; + bc->priv = priv; + + io_uring_cmd_complete_in_task(priv->cmd, btrfs_uring_read_finished); +} + +static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter, + u64 start, u64 lockend, + struct extent_state *cached_state, + u64 disk_bytenr, u64 disk_io_size, + size_t count, bool compressed, + struct iovec *iov, struct io_uring_cmd *cmd) +{ + struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp)); + struct extent_io_tree *io_tree = &inode->io_tree; + struct page **pages; + struct btrfs_uring_priv *priv = NULL; + unsigned long nr_pages; + int ret; + + nr_pages = DIV_ROUND_UP(disk_io_size, PAGE_SIZE); + pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); + if (!pages) + return -ENOMEM; + ret = btrfs_alloc_page_array(nr_pages, pages, 0); + if (ret) { + ret = -ENOMEM; + goto out_fail; + } + + priv = kmalloc(sizeof(*priv), GFP_NOFS); + if (!priv) { + ret = -ENOMEM; + goto out_fail; + } + + priv->iocb = *iocb; + priv->iov = iov; + priv->iter = *iter; + priv->count = count; + priv->cmd = cmd; + priv->cached_state = cached_state; + priv->compressed = compressed; + priv->nr_pages = nr_pages; + priv->pages = pages; + priv->start = start; + priv->lockend = lockend; + priv->err = 0; + + ret = btrfs_encoded_read_regular_fill_pages(inode, disk_bytenr, + disk_io_size, pages, priv); + if (ret && ret != -EIOCBQUEUED) + goto out_fail; + + /* + * If we return -EIOCBQUEUED, we're deferring the cleanup to + * btrfs_uring_read_finished(), which will handle unlocking the extent + * and inode and freeing the allocations. + */ + + /* + * We're returning to userspace with the inode lock held, and that's + * okay - it'll get unlocked in a worker thread. Call + * btrfs_lockdep_inode_release() to avoid confusing lockdep. + */ + btrfs_lockdep_inode_release(inode, i_rwsem); + + return -EIOCBQUEUED; + +out_fail: + btrfs_unlock_extent(io_tree, start, lockend, &cached_state); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); + kfree(priv); + return ret; +} + +static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct file *file = cmd->file; + struct btrfs_inode *inode = BTRFS_I(file->f_inode); + struct extent_io_tree *io_tree = &inode->io_tree; + struct btrfs_fs_info *fs_info = inode->root->fs_info; + size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags); + size_t copy_end; + int ret; + u64 disk_bytenr, disk_io_size; + loff_t pos; + struct kiocb kiocb; + struct extent_state *cached_state = NULL; + u64 start, lockend; + void __user *sqe_addr; + struct io_btrfs_cmd *bc = io_uring_cmd_to_pdu(cmd, struct io_btrfs_cmd); + struct btrfs_uring_encoded_data *data = NULL; + + if (cmd->flags & IORING_URING_CMD_REISSUE) + data = bc->data; + + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_acct; + } + sqe_addr = u64_to_user_ptr(READ_ONCE(cmd->sqe->addr)); + + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); +#else + ret = -ENOTTY; + goto out_acct; +#endif + } else { + copy_end = copy_end_kernel; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; + goto out_acct; + } + + bc->data = data; + + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + if (copy_from_user(&args32, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + + if (data->args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + data->iov = data->iovstack; + ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_free; + } + } + + pos = data->args.offset; + ret = rw_verify_area(READ, file, &pos, data->args.len); + if (ret < 0) + goto out_free; + + init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = pos; + + if (issue_flags & IO_URING_F_NONBLOCK) + kiocb.ki_flags |= IOCB_NOWAIT; + + start = ALIGN_DOWN(pos, fs_info->sectorsize); + lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; + + ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state, + &disk_bytenr, &disk_io_size); + if (ret == -EAGAIN) + goto out_acct; + if (ret < 0 && ret != -EIOCBQUEUED) + goto out_free; + + file_accessed(file); + + if (copy_to_user(sqe_addr + copy_end, + (const char *)&data->args + copy_end_kernel, + sizeof(data->args) - copy_end_kernel)) { + if (ret == -EIOCBQUEUED) { + btrfs_unlock_extent(io_tree, start, lockend, &cached_state); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); + } + ret = -EFAULT; + goto out_free; + } + + if (ret == -EIOCBQUEUED) { + u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size); + + /* Match ioctl by not returning past EOF if uncompressed. */ + if (!data->args.compression) + count = min_t(u64, count, data->args.len); + + ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend, + cached_state, disk_bytenr, disk_io_size, + count, data->args.compression, + data->iov, cmd); + + goto out_acct; + } + +out_free: + kfree(data->iov); + +out_acct: + if (ret > 0) + add_rchar(current, ret); + inc_syscr(current); + + if (ret != -EIOCBQUEUED && ret != -EAGAIN) + kfree(data); + + return ret; +} + +static int btrfs_uring_encoded_write(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct file *file = cmd->file; + loff_t pos; + struct kiocb kiocb; + ssize_t ret; + void __user *sqe_addr; + struct io_btrfs_cmd *bc = io_uring_cmd_to_pdu(cmd, struct io_btrfs_cmd); + struct btrfs_uring_encoded_data *data = NULL; + + if (cmd->flags & IORING_URING_CMD_REISSUE) + data = bc->data; + + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_acct; + } + sqe_addr = u64_to_user_ptr(READ_ONCE(cmd->sqe->addr)); + + if (!(file->f_mode & FMODE_WRITE)) { + ret = -EBADF; + goto out_acct; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; + goto out_acct; + } + + bc->data = data; + + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + if (copy_from_user(&args32, sqe_addr, sizeof(args32))) { + ret = -EFAULT; + goto out_acct; + } + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; + data->args.len = args32.len; + data->args.unencoded_len = args32.unencoded_len; + data->args.unencoded_offset = args32.unencoded_offset; + data->args.compression = args32.compression; + data->args.encryption = args32.encryption; + memcpy(data->args.reserved, args32.reserved, + sizeof(data->args.reserved)); +#else + ret = -ENOTTY; + goto out_acct; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, sizeof(data->args))) { + ret = -EFAULT; + goto out_acct; + } + } + + ret = -EINVAL; + if (data->args.flags != 0) + goto out_acct; + if (memchr_inv(data->args.reserved, 0, sizeof(data->args.reserved))) + goto out_acct; + if (data->args.compression == BTRFS_ENCODED_IO_COMPRESSION_NONE && + data->args.encryption == BTRFS_ENCODED_IO_ENCRYPTION_NONE) + goto out_acct; + if (data->args.compression >= BTRFS_ENCODED_IO_COMPRESSION_TYPES || + data->args.encryption >= BTRFS_ENCODED_IO_ENCRYPTION_TYPES) + goto out_acct; + if (data->args.unencoded_offset > data->args.unencoded_len) + goto out_acct; + if (data->args.len > data->args.unencoded_len - data->args.unencoded_offset) + goto out_acct; + + data->iov = data->iovstack; + ret = import_iovec(ITER_SOURCE, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_iov; + } + } + + if (issue_flags & IO_URING_F_NONBLOCK) { + ret = -EAGAIN; + goto out_acct; + } + + pos = data->args.offset; + ret = rw_verify_area(WRITE, file, &pos, data->args.len); + if (ret < 0) + goto out_iov; + + init_sync_kiocb(&kiocb, file); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); + if (ret) + goto out_iov; + kiocb.ki_pos = pos; + + file_start_write(file); + + ret = btrfs_do_write_iter(&kiocb, &data->iter, &data->args); + if (ret > 0) + fsnotify_modify(file); + + file_end_write(file); +out_iov: + kfree(data->iov); +out_acct: + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + + if (ret != -EAGAIN) + kfree(data); + return ret; +} + +int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + if (unlikely(btrfs_is_shutdown(inode_to_fs_info(file_inode(cmd->file))))) + return -EIO; + + switch (cmd->cmd_op) { + case BTRFS_IOC_ENCODED_READ: +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + case BTRFS_IOC_ENCODED_READ_32: +#endif + return btrfs_uring_encoded_read(cmd, issue_flags); + + case BTRFS_IOC_ENCODED_WRITE: +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + case BTRFS_IOC_ENCODED_WRITE_32: +#endif + return btrfs_uring_encoded_write(cmd, issue_flags); + } + + return -EINVAL; +} + +static int btrfs_ioctl_subvol_sync(struct btrfs_fs_info *fs_info, void __user *argp) +{ + struct btrfs_root *root; + struct btrfs_ioctl_subvol_wait args = { 0 }; + signed long sched_ret; + int refs; + u64 root_flags; + bool wait_for_deletion = false; + bool found = false; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + switch (args.mode) { + case BTRFS_SUBVOL_SYNC_WAIT_FOR_QUEUED: + /* + * Wait for the first one deleted that waits until all previous + * are cleaned. + */ + spin_lock(&fs_info->trans_lock); + if (!list_empty(&fs_info->dead_roots)) { + root = list_last_entry(&fs_info->dead_roots, + struct btrfs_root, root_list); + args.subvolid = btrfs_root_id(root); + found = true; + } + spin_unlock(&fs_info->trans_lock); + if (!found) + return -ENOENT; + + fallthrough; + case BTRFS_SUBVOL_SYNC_WAIT_FOR_ONE: + if ((0 < args.subvolid && args.subvolid < BTRFS_FIRST_FREE_OBJECTID) || + BTRFS_LAST_FREE_OBJECTID < args.subvolid) + return -EINVAL; + break; + case BTRFS_SUBVOL_SYNC_COUNT: + spin_lock(&fs_info->trans_lock); + args.count = list_count_nodes(&fs_info->dead_roots); + spin_unlock(&fs_info->trans_lock); + if (copy_to_user(argp, &args, sizeof(args))) + return -EFAULT; + return 0; + case BTRFS_SUBVOL_SYNC_PEEK_FIRST: + spin_lock(&fs_info->trans_lock); + /* Last in the list was deleted first. */ + if (!list_empty(&fs_info->dead_roots)) { + root = list_last_entry(&fs_info->dead_roots, + struct btrfs_root, root_list); + args.subvolid = btrfs_root_id(root); + } else { + args.subvolid = 0; + } + spin_unlock(&fs_info->trans_lock); + if (copy_to_user(argp, &args, sizeof(args))) + return -EFAULT; + return 0; + case BTRFS_SUBVOL_SYNC_PEEK_LAST: + spin_lock(&fs_info->trans_lock); + /* First in the list was deleted last. */ + if (!list_empty(&fs_info->dead_roots)) { + root = list_first_entry(&fs_info->dead_roots, + struct btrfs_root, root_list); + args.subvolid = btrfs_root_id(root); + } else { + args.subvolid = 0; + } + spin_unlock(&fs_info->trans_lock); + if (copy_to_user(argp, &args, sizeof(args))) + return -EFAULT; + return 0; + default: + return -EINVAL; + } + + /* 32bit limitation: fs_roots_radix key is not wide enough. */ + if (sizeof(unsigned long) != sizeof(u64) && args.subvolid > U32_MAX) + return -EOVERFLOW; + + while (1) { + /* Wait for the specific one. */ + if (down_read_interruptible(&fs_info->subvol_sem) == -EINTR) + return -EINTR; + refs = -1; + spin_lock(&fs_info->fs_roots_radix_lock); + root = radix_tree_lookup(&fs_info->fs_roots_radix, + (unsigned long)args.subvolid); + if (root) { + spin_lock(&root->root_item_lock); + refs = btrfs_root_refs(&root->root_item); + root_flags = btrfs_root_flags(&root->root_item); + spin_unlock(&root->root_item_lock); + } + spin_unlock(&fs_info->fs_roots_radix_lock); + up_read(&fs_info->subvol_sem); + + /* Subvolume does not exist. */ + if (!root) + return -ENOENT; + + /* Subvolume not deleted at all. */ + if (refs > 0) + return -EEXIST; + /* We've waited and now the subvolume is gone. */ + if (wait_for_deletion && refs == -1) { + /* Return the one we waited for as the last one. */ + if (copy_to_user(argp, &args, sizeof(args))) + return -EFAULT; + return 0; + } + + /* Subvolume not found on the first try (deleted or never existed). */ + if (refs == -1) + return -ENOENT; + + wait_for_deletion = true; + ASSERT(root_flags & BTRFS_ROOT_SUBVOL_DEAD); + sched_ret = schedule_timeout_interruptible(HZ); + /* Early wake up or error. */ + if (sched_ret != 0) + return -EINTR; + } + + return 0; +} + +#ifdef CONFIG_BTRFS_EXPERIMENTAL +static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg) +{ + int ret = 0; + u32 flags; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(flags, (u32 __user *)arg)) + return -EFAULT; + + if (flags >= BTRFS_SHUTDOWN_FLAGS_LAST) + return -EINVAL; + + if (btrfs_is_shutdown(fs_info)) + return 0; + + switch (flags) { + case BTRFS_SHUTDOWN_FLAGS_LOGFLUSH: + case BTRFS_SHUTDOWN_FLAGS_DEFAULT: + ret = freeze_super(fs_info->sb, FREEZE_HOLDER_KERNEL, NULL); + if (ret) + return ret; + btrfs_force_shutdown(fs_info); + ret = thaw_super(fs_info->sb, FREEZE_HOLDER_KERNEL, NULL); + if (ret) + return ret; + break; + case BTRFS_SHUTDOWN_FLAGS_NOLOGFLUSH: + btrfs_force_shutdown(fs_info); + break; + } + return ret; +} +#endif + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; void __user *argp = (void __user *)arg; switch (cmd) { case FS_IOC_GETVERSION: - return btrfs_ioctl_getversion(file, argp); + return btrfs_ioctl_getversion(inode, argp); case FS_IOC_GETFSLABEL: return btrfs_ioctl_get_fslabel(fs_info, argp); case FS_IOC_SETFSLABEL: @@ -4918,19 +5201,19 @@ long btrfs_ioctl(struct file *file, unsigned int case FITRIM: return btrfs_ioctl_fitrim(fs_info, argp); case BTRFS_IOC_SNAP_CREATE: - return btrfs_ioctl_snap_create(file, argp, 0); + return btrfs_ioctl_snap_create(file, argp, false); case BTRFS_IOC_SNAP_CREATE_V2: - return btrfs_ioctl_snap_create_v2(file, argp, 0); + return btrfs_ioctl_snap_create_v2(file, argp, false); case BTRFS_IOC_SUBVOL_CREATE: - return btrfs_ioctl_snap_create(file, argp, 1); + return btrfs_ioctl_snap_create(file, argp, true); case BTRFS_IOC_SUBVOL_CREATE_V2: - return btrfs_ioctl_snap_create_v2(file, argp, 1); + return btrfs_ioctl_snap_create_v2(file, argp, true); case BTRFS_IOC_SNAP_DESTROY: return btrfs_ioctl_snap_destroy(file, argp, false); case BTRFS_IOC_SNAP_DESTROY_V2: return btrfs_ioctl_snap_destroy(file, argp, true); case BTRFS_IOC_SUBVOL_GETFLAGS: - return btrfs_ioctl_subvol_getflags(file, argp); + return btrfs_ioctl_subvol_getflags(BTRFS_I(inode), argp); case BTRFS_IOC_SUBVOL_SETFLAGS: return btrfs_ioctl_subvol_setflags(file, argp); case BTRFS_IOC_DEFAULT_SUBVOL: @@ -4951,14 +5234,12 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_fs_info(fs_info, argp); case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(fs_info, argp); - case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_TREE_SEARCH: - return btrfs_ioctl_tree_search(file, argp); + return btrfs_ioctl_tree_search(root, argp); case BTRFS_IOC_TREE_SEARCH_V2: - return btrfs_ioctl_tree_search_v2(file, argp); + return btrfs_ioctl_tree_search_v2(root, argp); case BTRFS_IOC_INO_LOOKUP: - return btrfs_ioctl_ino_lookup(file, argp); + return btrfs_ioctl_ino_lookup(root, argp); case BTRFS_IOC_INO_PATHS: return btrfs_ioctl_ino_to_path(root, argp); case BTRFS_IOC_LOGICAL_INO: @@ -4975,11 +5256,10 @@ long btrfs_ioctl(struct file *file, unsigned int return ret; ret = btrfs_sync_fs(inode->i_sb, 1); /* - * The transaction thread may want to do more work, - * namely it pokes the cleaner kthread that will start - * processing uncleaned subvols. + * There may be work for the cleaner kthread to do (subvolume + * deletion, delayed iputs, defrag inodes, etc), so wake it up. */ - wake_up_process(fs_info->transaction_kthread); + wake_up_process(fs_info->cleaner_kthread); return ret; } case BTRFS_IOC_START_SYNC: @@ -5005,10 +5285,10 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_set_received_subvol_32(file, argp); #endif case BTRFS_IOC_SEND: - return _btrfs_ioctl_send(file, argp, false); + return _btrfs_ioctl_send(root, argp, false); #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) case BTRFS_IOC_SEND_32: - return _btrfs_ioctl_send(file, argp, true); + return _btrfs_ioctl_send(root, argp, true); #endif case BTRFS_IOC_GET_DEV_STATS: return btrfs_ioctl_get_dev_stats(fs_info, argp); @@ -5025,7 +5305,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_QUOTA_RESCAN_STATUS: return btrfs_ioctl_quota_rescan_status(fs_info, argp); case BTRFS_IOC_QUOTA_RESCAN_WAIT: - return btrfs_ioctl_quota_rescan_wait(fs_info, argp); + return btrfs_ioctl_quota_rescan_wait(fs_info); case BTRFS_IOC_DEV_REPLACE: return btrfs_ioctl_dev_replace(fs_info, argp); case BTRFS_IOC_GET_SUPPORTED_FEATURES: @@ -5035,15 +5315,33 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SET_FEATURES: return btrfs_ioctl_set_features(file, argp); case BTRFS_IOC_GET_SUBVOL_INFO: - return btrfs_ioctl_get_subvol_info(file, argp); + return btrfs_ioctl_get_subvol_info(inode, argp); case BTRFS_IOC_GET_SUBVOL_ROOTREF: - return btrfs_ioctl_get_subvol_rootref(file, argp); + return btrfs_ioctl_get_subvol_rootref(root, argp); case BTRFS_IOC_INO_LOOKUP_USER: return btrfs_ioctl_ino_lookup_user(file, argp); case FS_IOC_ENABLE_VERITY: return fsverity_ioctl_enable(file, (const void __user *)argp); case FS_IOC_MEASURE_VERITY: return fsverity_ioctl_measure(file, argp); + case FS_IOC_READ_VERITY_METADATA: + return fsverity_ioctl_read_metadata(file, argp); + case BTRFS_IOC_ENCODED_READ: + return btrfs_ioctl_encoded_read(file, argp, false); + case BTRFS_IOC_ENCODED_WRITE: + return btrfs_ioctl_encoded_write(file, argp, false); +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + case BTRFS_IOC_ENCODED_READ_32: + return btrfs_ioctl_encoded_read(file, argp, true); + case BTRFS_IOC_ENCODED_WRITE_32: + return btrfs_ioctl_encoded_write(file, argp, true); +#endif + case BTRFS_IOC_SUBVOL_SYNC_WAIT: + return btrfs_ioctl_subvol_sync(fs_info, argp); +#ifdef CONFIG_BTRFS_EXPERIMENTAL + case BTRFS_IOC_SHUTDOWN: + return btrfs_ioctl_shutdown(fs_info, arg); +#endif } return -ENOTTY; |