diff options
Diffstat (limited to 'fs/btrfs/ioctl.c')
| -rw-r--r-- | fs/btrfs/ioctl.c | 3857 |
1 files changed, 1920 insertions, 1937 deletions
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4f4b13830b25..d5dd8bed1488 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -26,14 +26,17 @@ #include <linux/btrfs.h> #include <linux/uaccess.h> #include <linux/iversion.h> +#include <linux/fileattr.h> +#include <linux/fsverity.h> +#include <linux/sched/xacct.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 "inode-map.h" #include "backref.h" #include "rcu-string.h" #include "send.h" @@ -46,6 +49,7 @@ #include "space-info.h" #include "delalloc-space.h" #include "block-group.h" +#include "subpage.h" #ifdef CONFIG_64BIT /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI @@ -79,16 +83,31 @@ struct btrfs_ioctl_send_args_32 { compat_uptr_t clone_sources; /* in */ __u64 parent_root; /* in */ __u64 flags; /* in */ - __u64 reserved[4]; /* in */ + __u32 version; /* in */ + __u8 reserved[28]; /* in */ } __attribute__ ((__packed__)); #define BTRFS_IOC_SEND_32 _IOW(BTRFS_IOCTL_MAGIC, 38, \ struct btrfs_ioctl_send_args_32) -#endif -static int btrfs_clone(struct inode *src, struct inode *inode, - u64 off, u64 olen, u64 olen_aligned, u64 destoff, - int no_time_update); +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, @@ -106,9 +125,11 @@ 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(unsigned int flags) +static unsigned int btrfs_inode_flags_to_fsflags(struct btrfs_inode *binode) { unsigned int iflags = 0; + u32 flags = binode->flags; + u32 ro_flags = binode->ro_flags; if (flags & BTRFS_INODE_SYNC) iflags |= FS_SYNC_FL; @@ -124,6 +145,8 @@ static unsigned int btrfs_inode_flags_to_fsflags(unsigned int flags) iflags |= FS_DIRSYNC_FL; if (flags & BTRFS_INODE_NODATACOW) iflags |= FS_NOCOW_FL; + if (ro_flags & BTRFS_INODE_RO_VERITY) + iflags |= FS_VERITY_FL; if (flags & BTRFS_INODE_NOCOMPRESS) iflags |= FS_NOCOMP_FL; @@ -151,24 +174,19 @@ void btrfs_sync_inode_flags_to_i_flags(struct inode *inode) new_fl |= S_NOATIME; if (binode->flags & BTRFS_INODE_DIRSYNC) new_fl |= S_DIRSYNC; + if (binode->ro_flags & BTRFS_INODE_RO_VERITY) + new_fl |= S_VERITY; set_mask_bits(&inode->i_flags, - S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC, - new_fl); + S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC | + S_VERITY, new_fl); } -static int btrfs_ioctl_getflags(struct file *file, void __user *arg) -{ - struct btrfs_inode *binode = BTRFS_I(file_inode(file)); - unsigned int flags = btrfs_inode_flags_to_fsflags(binode->flags); - - if (copy_to_user(arg, &flags, sizeof(flags))) - return -EFAULT; - return 0; -} - -/* Check if @flags are a supported and valid set of FS_*_FL flags */ -static int check_fsflags(unsigned int flags) +/* + * Check if @flags are a supported and valid set of FS_*_FL flags and that + * the old and new flags are not conflicting + */ +static int check_fsflags(unsigned int old_flags, unsigned int flags) { if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NOATIME_FL | FS_NODUMP_FL | \ @@ -177,15 +195,47 @@ static int check_fsflags(unsigned int flags) FS_NOCOW_FL)) return -EOPNOTSUPP; + /* COMPR and NOCOMP on new/old are valid */ if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) return -EINVAL; + if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL)) + return -EINVAL; + + /* NOCOW and compression options are mutually exclusive */ + if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + return 0; } -static int btrfs_ioctl_setflags(struct file *file, void __user *arg) +static int check_fsflags_compatible(struct btrfs_fs_info *fs_info, + unsigned int flags) { - struct inode *inode = file_inode(file); + if (btrfs_is_zoned(fs_info) && (flags & FS_NOCOW_FL)) + return -EPERM; + + 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) +{ + struct btrfs_inode *binode = BTRFS_I(d_inode(dentry)); + + fileattr_fill_flags(fa, btrfs_inode_flags_to_fsflags(binode)); + return 0; +} + +int btrfs_fileattr_set(struct user_namespace *mnt_userns, + struct dentry *dentry, struct fileattr *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; @@ -193,33 +243,25 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; - u32 binode_flags = binode->flags; - - if (!inode_owner_or_capable(inode)) - return -EPERM; + u32 binode_flags; if (btrfs_root_readonly(root)) return -EROFS; - if (copy_from_user(&fsflags, arg, sizeof(fsflags))) - return -EFAULT; + if (fileattr_has_fsx(fa)) + return -EOPNOTSUPP; - ret = check_fsflags(fsflags); + fsflags = btrfs_mask_fsflags_for_type(inode, fa->flags); + old_fsflags = btrfs_inode_flags_to_fsflags(binode); + ret = check_fsflags(old_fsflags, fsflags); if (ret) return ret; - ret = mnt_want_write_file(file); + ret = check_fsflags_compatible(fs_info, fsflags); if (ret) return ret; - inode_lock(inode); - - fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); - old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); - ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); - if (ret) - goto out_unlock; - + binode_flags = binode->flags; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; else @@ -240,6 +282,16 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) binode_flags |= BTRFS_INODE_NOATIME; else binode_flags &= ~BTRFS_INODE_NOATIME; + + /* If coming from FS_IOC_FSSETXATTR then skip unconverted flags */ + if (!fa->flags_valid) { + /* 1 item for the inode */ + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + goto update_flags; + } + if (fsflags & FS_DIRSYNC_FL) binode_flags |= BTRFS_INODE_DIRSYNC; else @@ -280,10 +332,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) binode_flags |= BTRFS_INODE_NOCOMPRESS; } else if (fsflags & FS_COMPR_FL) { - if (IS_SWAPFILE(inode)) { - ret = -ETXTBSY; - goto out_unlock; - } + if (IS_SWAPFILE(inode)) + return -ETXTBSY; binode_flags |= BTRFS_INODE_COMPRESS; binode_flags &= ~BTRFS_INODE_NOCOMPRESS; @@ -300,10 +350,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) * 2 for properties */ trans = btrfs_start_transaction(root, 3); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - goto out_unlock; - } + if (IS_ERR(trans)) + return PTR_ERR(trans); if (comp) { ret = btrfs_set_prop(trans, inode, "btrfs.compression", comp, @@ -321,161 +369,98 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } } +update_flags: binode->flags = binode_flags; btrfs_sync_inode_flags_to_i_flags(inode); inode_inc_iversion(inode); inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); out_end_trans: btrfs_end_transaction(trans); - out_unlock: - inode_unlock(inode); - mnt_drop_write_file(file); return ret; } /* - * Translate btrfs internal inode flags to xflags as expected by the - * FS_IOC_FSGETXATT ioctl. Filter only the supported ones, unknown flags are - * silently dropped. + * Start exclusive operation @type, return true on success */ -static unsigned int btrfs_inode_flags_to_xflags(unsigned int flags) +bool btrfs_exclop_start(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type) { - unsigned int xflags = 0; + bool ret = false; - if (flags & BTRFS_INODE_APPEND) - xflags |= FS_XFLAG_APPEND; - if (flags & BTRFS_INODE_IMMUTABLE) - xflags |= FS_XFLAG_IMMUTABLE; - if (flags & BTRFS_INODE_NOATIME) - xflags |= FS_XFLAG_NOATIME; - if (flags & BTRFS_INODE_NODUMP) - xflags |= FS_XFLAG_NODUMP; - if (flags & BTRFS_INODE_SYNC) - xflags |= FS_XFLAG_SYNC; - - return xflags; -} + 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); -/* Check if @flags are a supported and valid set of FS_XFLAGS_* flags */ -static int check_xflags(unsigned int flags) -{ - if (flags & ~(FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE | FS_XFLAG_NOATIME | - FS_XFLAG_NODUMP | FS_XFLAG_SYNC)) - return -EOPNOTSUPP; - return 0; + return ret; } /* - * Set the xflags from the internal inode flags. The remaining items of fsxattr - * are zeroed. + * 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 */ -static int btrfs_ioctl_fsgetxattr(struct file *file, void __user *arg) +bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type) { - struct btrfs_inode *binode = BTRFS_I(file_inode(file)); - struct fsxattr fa; - - simple_fill_fsxattr(&fa, btrfs_inode_flags_to_xflags(binode->flags)); - if (copy_to_user(arg, &fa, sizeof(fa))) - return -EFAULT; + 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; - return 0; + spin_unlock(&fs_info->super_lock); + return false; } -static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg) +void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info) { - struct inode *inode = file_inode(file); - struct btrfs_inode *binode = BTRFS_I(inode); - struct btrfs_root *root = binode->root; - struct btrfs_trans_handle *trans; - struct fsxattr fa, old_fa; - unsigned old_flags; - unsigned old_i_flags; - int ret = 0; - - if (!inode_owner_or_capable(inode)) - return -EPERM; - - if (btrfs_root_readonly(root)) - return -EROFS; - - if (copy_from_user(&fa, arg, sizeof(fa))) - return -EFAULT; - - ret = check_xflags(fa.fsx_xflags); - if (ret) - return ret; - - if (fa.fsx_extsize != 0 || fa.fsx_projid != 0 || fa.fsx_cowextsize != 0) - return -EOPNOTSUPP; - - ret = mnt_want_write_file(file); - if (ret) - return ret; - - inode_lock(inode); - - old_flags = binode->flags; - old_i_flags = inode->i_flags; - - simple_fill_fsxattr(&old_fa, - btrfs_inode_flags_to_xflags(binode->flags)); - ret = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); - if (ret) - goto out_unlock; - - if (fa.fsx_xflags & FS_XFLAG_SYNC) - binode->flags |= BTRFS_INODE_SYNC; - else - binode->flags &= ~BTRFS_INODE_SYNC; - if (fa.fsx_xflags & FS_XFLAG_IMMUTABLE) - binode->flags |= BTRFS_INODE_IMMUTABLE; - else - binode->flags &= ~BTRFS_INODE_IMMUTABLE; - if (fa.fsx_xflags & FS_XFLAG_APPEND) - binode->flags |= BTRFS_INODE_APPEND; - else - binode->flags &= ~BTRFS_INODE_APPEND; - if (fa.fsx_xflags & FS_XFLAG_NODUMP) - binode->flags |= BTRFS_INODE_NODUMP; - else - binode->flags &= ~BTRFS_INODE_NODUMP; - if (fa.fsx_xflags & FS_XFLAG_NOATIME) - binode->flags |= BTRFS_INODE_NOATIME; - else - binode->flags &= ~BTRFS_INODE_NOATIME; - - /* 1 item for the inode */ - trans = btrfs_start_transaction(root, 1); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - goto out_unlock; - } - - btrfs_sync_inode_flags_to_i_flags(inode); - inode_inc_iversion(inode); - inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + spin_unlock(&fs_info->super_lock); +} - btrfs_end_transaction(trans); +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"); +} -out_unlock: - if (ret) { - binode->flags = old_flags; - inode->i_flags = old_i_flags; +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); } - - inode_unlock(inode); - mnt_drop_write_file(file); - - return ret; } -static int btrfs_ioctl_getversion(struct file *file, int __user *arg) +static int btrfs_ioctl_getversion(struct inode *inode, int __user *arg) { - struct inode *inode = file_inode(file); - return put_user(inode->i_generation, arg); } @@ -483,7 +468,6 @@ 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; @@ -493,6 +477,14 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, return -EPERM; /* + * btrfs_trim_block_group() depends on space cache, which is not + * available in zoned filesystem. So, disallow fitrim on a zoned + * filesystem for now. + */ + if (btrfs_is_zoned(fs_info)) + return -EOPNOTSUPP; + + /* * If the fs is mounted with nologreplay, which requires it to be * mounted in RO mode as well, we can not allow discard on free space * inside block groups, because log trees refer to extents that are not @@ -505,14 +497,11 @@ 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(); @@ -551,10 +540,35 @@ int __pure btrfs_is_empty_uuid(u8 *uuid) return 1; } -static noinline int create_subvol(struct inode *dir, - struct dentry *dentry, - const char *name, int namelen, - u64 *async_transid, +/* + * 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(struct btrfs_qgroup_inherit *inherit) +{ + /* + * 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; + + if (inherit) { + /* 2 to add qgroup relations for each inherited qgroup */ + num_items += 2 * inherit->num_qgroups; + } + return num_items; +} + +static noinline int create_subvol(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, struct btrfs_qgroup_inherit *inherit) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); @@ -567,21 +581,23 @@ static noinline int create_subvol(struct inode *dir, 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; - int err; + dev_t anon_dev; u64 objectid; - u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; - u64 index = 0; - uuid_le new_uuid; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) return -ENOMEM; - ret = btrfs_find_free_objectid(fs_info->tree_root, &objectid); + ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid); if (ret) - goto fail_free; + goto out_root_item; /* * Don't create subvolume whose level is not zero. Or qgroup will be @@ -589,35 +605,47 @@ static noinline int create_subvol(struct inode *dir, */ if (btrfs_qgroup_level(objectid)) { ret = -ENOSPC; - goto fail_free; + goto out_root_item; } + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto out_root_item; + + new_inode_args.inode = btrfs_new_subvol_inode(mnt_userns, 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; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_subvolume_release_metadata(fs_info, &block_rsv); - goto fail_free; + btrfs_subvolume_release_metadata(root, &block_rsv); + goto out_new_inode_args; } trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit); if (ret) - goto fail; + goto out; - leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0); + leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0, + BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); - goto fail; + goto out; } btrfs_mark_buffer_dirty(leaf); @@ -643,8 +671,7 @@ static noinline int create_subvol(struct inode *dir, btrfs_set_root_generation_v2(root_item, btrfs_root_generation(root_item)); - uuid_le_gen(&new_uuid); - memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE); + generate_random_guid(root_item->uuid); btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec); btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec); root_item->ctime = root_item->otime; @@ -652,118 +679,106 @@ static noinline int create_subvol(struct inode *dir, btrfs_set_root_otransid(root_item, trans->transid); btrfs_tree_unlock(leaf); - free_extent_buffer(leaf); - leaf = NULL; - btrfs_set_root_dirid(root_item, new_dirid); + btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID); key.objectid = objectid; key.offset = 0; key.type = BTRFS_ROOT_ITEM_KEY; ret = btrfs_insert_root(trans, fs_info->tree_root, &key, root_item); - if (ret) - goto fail; - - key.offset = (u64)-1; - new_root = btrfs_read_fs_root_no_name(fs_info, &key); - if (IS_ERR(new_root)) { - ret = PTR_ERR(new_root); - btrfs_abort_transaction(trans, ret); - goto fail; - } - - btrfs_record_root_in_trans(trans, new_root); - - ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid); if (ret) { - /* We potentially lose an unused inode item here */ - btrfs_abort_transaction(trans, ret); - goto fail; + /* + * Since we don't abort the transaction in this case, free the + * tree block so that we don't leak space and leave the + * filesystem in an inconsistent state (an extent item in the + * extent tree with a backreference for a root that does not + * exists). + */ + btrfs_tree_lock(leaf); + btrfs_clean_tree_block(leaf); + btrfs_tree_unlock(leaf); + btrfs_free_tree_block(trans, objectid, leaf, 0, 1); + free_extent_buffer(leaf); + goto out; } - mutex_lock(&new_root->objectid_mutex); - new_root->highest_objectid = new_dirid; - mutex_unlock(&new_root->objectid_mutex); + free_extent_buffer(leaf); + leaf = NULL; - /* - * insert the directory item - */ - ret = btrfs_set_inode_index(BTRFS_I(dir), &index); - if (ret) { + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + if (IS_ERR(new_root)) { + ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } + /* 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_insert_dir_item(trans, name, namelen, BTRFS_I(dir), &key, - BTRFS_FT_DIR, index); + ret = btrfs_record_root_in_trans(trans, new_root); if (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, dir); + ret = btrfs_uuid_tree_add(trans, root_item->uuid, + BTRFS_UUID_KEY_SUBVOL, objectid); if (ret) { btrfs_abort_transaction(trans, ret); - goto fail; + goto out; } - ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, - btrfs_ino(BTRFS_I(dir)), index, name, namelen); + ret = btrfs_create_new_inode(trans, &new_inode_args); if (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(fs_info, &block_rsv); - - if (async_transid) { - *async_transid = trans->transid; - err = btrfs_commit_transaction_async(trans, 1); - if (err) - err = btrfs_commit_transaction(trans); - } else { - err = btrfs_commit_transaction(trans); - } - if (err && !ret) - ret = err; + btrfs_subvolume_release_metadata(root, &block_rsv); - if (!ret) { - inode = btrfs_lookup_dentry(dir, dentry); - if (IS_ERR(inode)) - return PTR_ERR(inode); - d_instantiate(dentry, inode); - } - return ret; - -fail_free: + if (ret) + btrfs_end_transaction(trans); + else + ret = btrfs_commit_transaction(trans); +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); +out_root_item: kfree(root_item); return ret; } static int create_snapshot(struct btrfs_root *root, struct inode *dir, - struct dentry *dentry, - u64 *async_transid, bool readonly, + struct dentry *dentry, bool readonly, struct btrfs_qgroup_inherit *inherit) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct inode *inode; struct btrfs_pending_snapshot *pending_snapshot; + unsigned int trans_num_items; struct btrfs_trans_handle *trans; int ret; - bool snapshot_force_cow = false; - if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state)) + /* 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 (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL; if (atomic_read(&root->nr_swapfiles)) { @@ -776,6 +791,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -784,46 +802,19 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } - /* - * Force new buffered writes to reserve space even when NOCOW is - * possible. This is to avoid later writeback (running dealloc) to - * fallback to COW mode and unexpectedly fail with ENOSPC. - */ - atomic_inc(&root->will_be_snapshotted); - smp_mb__after_atomic(); - /* wait for no snapshot writes */ - wait_event(root->subv_writers->wait, - percpu_counter_sum(&root->subv_writers->counter) == 0); - - ret = btrfs_start_delalloc_snapshot(root); - if (ret) - goto dec_and_free; - - /* - * All previous writes have started writeback in NOCOW mode, so now - * we force future writes to fallback to COW mode during snapshot - * creation. - */ - atomic_inc(&root->snapshot_force_cow); - snapshot_force_cow = true; - - btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); - btrfs_init_block_rsv(&pending_snapshot->block_rsv, BTRFS_BLOCK_RSV_TEMP); /* - * 1 - parent dir inode - * 2 - dir entries - * 1 - root item - * 2 - root ref/backref - * 1 - root of snapshot - * 1 - UUID item + * 1 to add dir item + * 1 to add dir index + * 1 to update parent inode item */ + trans_num_items = create_subvol_num_items(inherit) + 3; ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, - &pending_snapshot->block_rsv, 8, - false); + &pending_snapshot->block_rsv, + trans_num_items, false); if (ret) - goto dec_and_free; + goto free_pending; pending_snapshot->dentry = dentry; pending_snapshot->root = root; @@ -837,18 +828,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto fail; } - spin_lock(&fs_info->trans_lock); - list_add(&pending_snapshot->list, - &trans->transaction->pending_snapshots); - spin_unlock(&fs_info->trans_lock); - if (async_transid) { - *async_transid = trans->transid; - ret = btrfs_commit_transaction_async(trans, 1); - if (ret) - ret = btrfs_commit_transaction(trans); - } else { - ret = btrfs_commit_transaction(trans); - } + trans->pending_snapshot = pending_snapshot; + + ret = btrfs_commit_transaction(trans); if (ret) goto fail; @@ -868,14 +850,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: - btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); -dec_and_free: - if (snapshot_force_cow) - atomic_dec(&root->snapshot_force_cow); - if (atomic_dec_and_test(&root->will_be_snapshotted)) - wake_up_var(&root->will_be_snapshotted); + /* Prevent double freeing of anon_dev */ + 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); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); @@ -903,7 +887,8 @@ free_pending: * nfs_async_unlink(). */ -static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) +static int btrfs_may_delete(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *victim, int isdir) { int error; @@ -913,13 +898,14 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) BUG_ON(d_inode(victim->d_parent) != dir); audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) || - IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim))) + if (check_sticky(mnt_userns, dir, d_inode(victim)) || + IS_APPEND(d_inode(victim)) || IS_IMMUTABLE(d_inode(victim)) || + IS_SWAPFILE(d_inode(victim))) return -EPERM; if (isdir) { if (!d_is_dir(victim)) @@ -936,13 +922,16 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) } /* copy of may_create in fs/namei.c() */ -static inline int btrfs_may_create(struct inode *dir, struct dentry *child) +static inline int btrfs_may_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *child) { if (d_really_is_positive(child)) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns)) + return -EOVERFLOW; + return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); } /* @@ -951,9 +940,10 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child) * 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, - u64 *async_transid, bool readonly, + bool readonly, struct btrfs_qgroup_inherit *inherit) { struct inode *dir = d_inode(parent->dentry); @@ -965,12 +955,12 @@ static noinline int btrfs_mksubvol(const struct path *parent, if (error == -EINTR) return error; - dentry = lookup_one_len(name, parent->dentry, namelen); + dentry = lookup_one(mnt_userns, name, parent->dentry, namelen); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_unlock; - error = btrfs_may_create(dir, dentry); + error = btrfs_may_create(mnt_userns, dir, dentry); if (error) goto out_dput; @@ -989,13 +979,11 @@ static noinline int btrfs_mksubvol(const struct path *parent, if (btrfs_root_refs(&BTRFS_I(dir)->root->root_item) == 0) goto out_up_read; - if (snap_src) { - error = create_snapshot(snap_src, dir, dentry, - async_transid, readonly, inherit); - } else { - error = create_subvol(dir, dentry, name, namelen, - async_transid, inherit); - } + if (snap_src) + error = create_snapshot(snap_src, dir, dentry, readonly, inherit); + else + error = create_subvol(mnt_userns, dir, dentry, inherit); + if (!error) fsnotify_mkdir(dir, dentry); out_up_read: @@ -1003,133 +991,237 @@ out_up_read: out_dput: dput(dentry); out_unlock: - inode_unlock(dir); + btrfs_inode_unlock(dir, 0); return error; } -/* - * When we're defragging a range, we don't want to kick it off again - * if it is really just waiting for delalloc to send it down. - * If we find a nice big extent or delalloc range for the bytes in the - * file you want to defrag, we return 0 to let you know to skip this - * part of the file - */ -static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh) +static noinline int btrfs_mksnapshot(const struct path *parent, + struct user_namespace *mnt_userns, + const char *name, int namelen, + struct btrfs_root *root, + bool readonly, + struct btrfs_qgroup_inherit *inherit) { - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; - struct extent_map *em = NULL; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; - u64 end; + int ret; + bool snapshot_force_cow = false; - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, offset, PAGE_SIZE); - read_unlock(&em_tree->lock); + /* + * Force new buffered writes to reserve space even when NOCOW is + * possible. This is to avoid later writeback (running dealloc) to + * fallback to COW mode and unexpectedly fail with ENOSPC. + */ + btrfs_drew_read_lock(&root->snapshot_lock); - if (em) { - end = extent_map_end(em); - free_extent_map(em); - if (end - offset > thresh) - return 0; - } - /* if we already have a nice delalloc here, just stop */ - thresh /= 2; - end = count_range_bits(io_tree, &offset, offset + thresh, - thresh, EXTENT_DELALLOC, 1); - if (end >= thresh) - return 0; - return 1; + ret = btrfs_start_delalloc_snapshot(root, false); + if (ret) + goto out; + + /* + * All previous writes have started writeback in NOCOW mode, so now + * we force future writes to fallback to COW mode during snapshot + * 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; } /* - * helper function to walk through a file and find extents - * newer than a specific transid, and smaller than thresh. + * Defrag specific helper to get an extent map. + * + * Differences between this and btrfs_get_extent() are: + * + * - No extent_map will be added to inode->extent_tree + * To reduce memory usage in the long run. * - * This is used by the defragging code to find new and small - * extents + * - Extra optimization to skip file extents older than @newer_than + * By using btrfs_search_forward() we can skip entire file ranges that + * have extents created in past transactions, because btrfs_search_forward() + * will not visit leaves and nodes with a generation smaller than given + * minimal generation threshold (@newer_than). + * + * Return valid em if we find a file extent matching the requirement. + * Return NULL if we can not find a file extent matching the requirement. + * + * Return ERR_PTR() for error. */ -static int find_new_extents(struct btrfs_root *root, - struct inode *inode, u64 newer_than, - u64 *off, u32 thresh) +static struct extent_map *defrag_get_extent(struct btrfs_inode *inode, + u64 start, u64 newer_than) { - struct btrfs_path *path; - struct btrfs_key min_key; - struct extent_buffer *leaf; - struct btrfs_file_extent_item *extent; - int type; + struct btrfs_root *root = inode->root; + struct btrfs_file_extent_item *fi; + struct btrfs_path path = { 0 }; + struct extent_map *em; + struct btrfs_key key; + u64 ino = btrfs_ino(inode); int ret; - u64 ino = btrfs_ino(BTRFS_I(inode)); - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + em = alloc_extent_map(); + if (!em) { + ret = -ENOMEM; + goto err; + } - min_key.objectid = ino; - min_key.type = BTRFS_EXTENT_DATA_KEY; - min_key.offset = *off; + key.objectid = ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = start; - while (1) { - ret = btrfs_search_forward(root, &min_key, path, newer_than); - if (ret != 0) - goto none; -process_slot: - if (min_key.objectid != ino) - goto none; - if (min_key.type != BTRFS_EXTENT_DATA_KEY) - goto none; + if (newer_than) { + ret = btrfs_search_forward(root, &key, &path, newer_than); + if (ret < 0) + goto err; + /* Can't find anything newer */ + if (ret > 0) + goto not_found; + } else { + ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0); + if (ret < 0) + goto err; + } + if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) { + /* + * If btrfs_search_slot() makes path to point beyond nritems, + * we should not have an empty leaf, as this inode must at + * least have its INODE_ITEM. + */ + ASSERT(btrfs_header_nritems(path.nodes[0])); + path.slots[0] = btrfs_header_nritems(path.nodes[0]) - 1; + } + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + /* Perfect match, no need to go one slot back */ + if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY && + key.offset == start) + goto iterate; - leaf = path->nodes[0]; - extent = btrfs_item_ptr(leaf, path->slots[0], - struct btrfs_file_extent_item); - - type = btrfs_file_extent_type(leaf, extent); - if (type == BTRFS_FILE_EXTENT_REG && - btrfs_file_extent_num_bytes(leaf, extent) < thresh && - check_defrag_in_cache(inode, min_key.offset, thresh)) { - *off = min_key.offset; - btrfs_free_path(path); - return 0; - } + /* We didn't find a perfect match, needs to go one slot back */ + if (path.slots[0] > 0) { + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) + path.slots[0]--; + } + +iterate: + /* Iterate through the path to find a file extent covering @start */ + while (true) { + u64 extent_end; + + if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) + goto next; + + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + + /* + * We may go one slot back to INODE_REF/XATTR item, then + * need to go forward until we reach an EXTENT_DATA. + * But we should still has the correct ino as key.objectid. + */ + if (WARN_ON(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY) + goto next; + + /* It's beyond our target range, definitely not extent found */ + if (key.objectid > ino || key.type > BTRFS_EXTENT_DATA_KEY) + goto not_found; - path->slots[0]++; - if (path->slots[0] < btrfs_header_nritems(leaf)) { - btrfs_item_key_to_cpu(leaf, &min_key, path->slots[0]); - goto process_slot; + /* + * | |<- File extent ->| + * \- start + * + * This means there is a hole between start and key.offset. + */ + if (key.offset > start) { + em->start = start; + em->orig_start = start; + em->block_start = EXTENT_MAP_HOLE; + em->len = key.offset - start; + break; } - if (min_key.offset == (u64)-1) - goto none; + fi = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_file_extent_item); + extent_end = btrfs_file_extent_end(&path); - min_key.offset++; - btrfs_release_path(path); + /* + * |<- file extent ->| | + * \- start + * + * We haven't reached start, search next slot. + */ + if (extent_end <= start) + goto next; + + /* Now this extent covers @start, convert it to em */ + btrfs_extent_item_to_extent_map(inode, &path, fi, false, em); + break; +next: + ret = btrfs_next_item(root, &path); + if (ret < 0) + goto err; + if (ret > 0) + goto not_found; } -none: - btrfs_free_path(path); - return -ENOENT; + btrfs_release_path(&path); + return em; + +not_found: + btrfs_release_path(&path); + free_extent_map(em); + return NULL; + +err: + btrfs_release_path(&path); + free_extent_map(em); + return ERR_PTR(ret); } -static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start) +static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, + u64 newer_than, 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; - u64 len = PAGE_SIZE; + 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, len); + em = lookup_extent_mapping(em_tree, start, sectorsize); read_unlock(&em_tree->lock); + /* + * We can get a merged extent, in that case, we need to re-search + * tree to get the original em for defrag. + * + * If @newer_than is 0 or em::generation < newer_than, we can trust + * this em, as either we don't care about the generation, or the + * merged extent map will be rejected anyway. + */ + if (em && test_bit(EXTENT_FLAG_MERGED, &em->flags) && + newer_than && em->generation >= newer_than) { + free_extent_map(em); + em = NULL; + } + if (!em) { struct extent_state *cached = NULL; - u64 end = start + len - 1; + u64 end = start + sectorsize - 1; /* get the big lock and read metadata off disk */ - lock_extent_bits(io_tree, start, end, &cached); - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len); - unlock_extent_cached(io_tree, start, end, &cached); + if (!locked) + lock_extent(io_tree, start, end, &cached); + em = defrag_get_extent(BTRFS_I(inode), start, newer_than); + if (!locked) + unlock_extent(io_tree, start, end, &cached); if (IS_ERR(em)) return NULL; @@ -1138,274 +1230,586 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start) return em; } -static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em) +static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info, + const struct extent_map *em) +{ + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) + return BTRFS_MAX_COMPRESSED; + return fs_info->max_extent_size; +} + +static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, + u32 extent_thresh, u64 newer_than, bool locked) { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *next; - bool ret = true; + bool ret = false; /* 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); + /* + * Here we need to pass @newer_then when checking the next extent, or + * we will hit a case we mark current extent for defrag, but the next + * one will not be a target. + * This will just cause extra IO without really reducing the fragments. + */ + next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked); + /* No more em or hole */ 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; + goto out; + if (test_bit(EXTENT_FLAG_PREALLOC, &next->flags)) + goto out; + /* + * If the next extent is at its max capacity, defragging current extent + * makes no sense, as the total number of extents won't change. + */ + if (next->len >= get_extent_max_capacity(fs_info, em)) + goto out; + /* Skip older extent */ + if (next->generation < newer_than) + goto out; + /* Also check extent size */ + if (next->len >= extent_thresh) + goto out; + ret = true; +out: free_extent_map(next); return ret; } -static int should_defrag_range(struct inode *inode, u64 start, u32 thresh, - u64 *last_len, u64 *skip, u64 *defrag_end, - int compress) +/* + * 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 extent_map *em; - int ret = 1; - bool next_mergeable = true; - bool prev_mergeable = true; + 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); /* - * make sure that once we start defragging an extent, we keep on - * defragging it + * 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 (start < *defrag_end) - return 1; + if (PageCompound(page)) { + unlock_page(page); + put_page(page); + return ERR_PTR(-ETXTBSY); + } - *skip = 0; + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + return ERR_PTR(ret); + } - em = defrag_lookup_extent(inode, start); - if (!em) - return 0; + /* Wait for any existing ordered extent in the range */ + while (1) { + struct btrfs_ordered_extent *ordered; - /* this will cover holes, and inline extents */ - if (em->block_start >= EXTENT_MAP_LAST_BYTE) { - ret = 0; - goto out; - } + lock_extent(&inode->io_tree, page_start, page_end, &cached_state); + ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE); + unlock_extent(&inode->io_tree, page_start, page_end, + &cached_state); + if (!ordered) + break; - if (!*defrag_end) - prev_mergeable = false; + 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; + } + } - next_mergeable = defrag_check_next_extent(inode, em); - /* - * we hit a real extent, if it is big or the next extent is not a - * real extent, don't bother defragging it - */ - if (!compress && (*last_len == 0 || *last_len >= thresh) && - (em->len >= thresh || (!next_mergeable && !prev_mergeable))) - ret = 0; -out: /* - * last_len ends up being a counter of how many bytes we've defragged. - * every time we choose not to defrag an extent, we reset *last_len - * so that the next tiny extent will force a defrag. - * - * The end result of this is that tiny extents before a single big - * extent will force at least part of that big extent to be defragged. + * Now the page range has no ordered extent any more. Read the page to + * make it uptodate. */ - if (ret) { - *defrag_end = extent_map_end(em); - } else { - *last_len = 0; - *skip = extent_map_end(em); - *defrag_end = 0; + if (!PageUptodate(page)) { + btrfs_read_folio(NULL, page_folio(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); + } } - - free_extent_map(em); - return ret; + return page; } +struct defrag_target_range { + struct list_head list; + u64 start; + u64 len; +}; + /* - * it doesn't do much good to defrag one or two pages - * at a time. This pulls in a nice chunk of pages - * to COW and defrag. - * - * It also makes sure the delalloc code has enough - * dirty data to avoid making new small extents as part - * of the defrag + * Collect all valid target extents. * - * It's a good idea to start RA on this range - * before calling this. + * @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 cluster_pages_for_defrag(struct inode *inode, - struct page **pages, - unsigned long start_index, - unsigned long num_pages) +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 *last_scanned_ret) { - unsigned long file_end; - u64 isize = i_size_read(inode); - u64 page_start; - u64 page_end; - u64 page_cnt; - int ret; - int i; - int i_done; - struct btrfs_ordered_extent *ordered; - struct extent_state *cached_state = NULL; - struct extent_io_tree *tree; - struct extent_changeset *data_reserved = NULL; - gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + bool last_is_target = false; + u64 cur = start; + int ret = 0; - file_end = (isize - 1) >> PAGE_SHIFT; - if (!isize || start_index > file_end) - return 0; + while (cur < start + len) { + struct extent_map *em; + struct defrag_target_range *new; + bool next_mergeable = true; + u64 range_len; - page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); + last_is_target = false; + em = defrag_lookup_extent(&inode->vfs_inode, cur, + newer_than, locked); + if (!em) + break; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT); - if (ret) - return ret; - i_done = 0; - tree = &BTRFS_I(inode)->io_tree; + /* + * If the file extent is an inlined one, we may still want to + * defrag it (fallthrough) if it will cause a regular extent. + * This is for users who want to convert inline extents to + * regular ones through max_inline= mount option. + */ + if (em->block_start == EXTENT_MAP_INLINE && + em->len <= inode->root->fs_info->max_inline) + goto next; - /* step one, lock all the pages */ - for (i = 0; i < page_cnt; i++) { - struct page *page; -again: - page = find_or_create_page(inode->i_mapping, - start_index + i, mask); - if (!page) - break; + /* Skip hole/delalloc/preallocated extents */ + if (em->block_start == EXTENT_MAP_HOLE || + em->block_start == EXTENT_MAP_DELALLOC || + test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + goto next; - page_start = page_offset(page); - page_end = page_start + PAGE_SIZE - 1; - while (1) { - lock_extent_bits(tree, page_start, page_end, - &cached_state); - ordered = btrfs_lookup_ordered_extent(inode, - page_start); - unlock_extent_cached(tree, page_start, page_end, - &cached_state); - if (!ordered) - break; + /* Skip older extent */ + if (em->generation < newer_than) + goto next; - unlock_page(page); - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); - lock_page(page); - /* - * we unlocked the page above, so we need check if - * it was released or not. - */ - if (page->mapping != inode->i_mapping) { - unlock_page(page); - put_page(page); - goto again; - } + /* This em is under writeback, no need to defrag */ + if (em->generation == (u64)-1) + goto next; + + /* + * Our start offset might be in the middle of an existing extent + * map, so take that into account. + */ + range_len = em->len - (cur - em->start); + /* + * If this range of the extent map is already flagged for delalloc, + * skip it, because: + * + * 1) We could deadlock later, when trying to reserve space for + * delalloc, because in case we can't immediately reserve space + * the flusher can start delalloc and wait for the respective + * ordered extents to complete. The deadlock would happen + * because we do the space reservation while holding the range + * locked, and starting writeback, or finishing an ordered + * extent, requires locking the range; + * + * 2) If there's delalloc there, it means there's dirty pages for + * which writeback has not started yet (we clean the delalloc + * flag when starting writeback and after creating an ordered + * extent). If we mark pages in an adjacent range for defrag, + * then we will have a larger contiguous range for delalloc, + * very likely resulting in a larger extent after writeback is + * triggered (except in a case of free space fragmentation). + */ + if (test_range_bit(&inode->io_tree, cur, cur + range_len - 1, + EXTENT_DELALLOC, 0, NULL)) + 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 (range_len >= extent_thresh) + goto next; + + /* + * Skip extents already at its max capacity, this is mostly for + * compressed extents, which max cap is only 128K. + */ + if (em->len >= get_extent_max_capacity(fs_info, em)) + goto next; + + /* + * Normally there are no more extents after an inline one, thus + * @next_mergeable will normally be false and not defragged. + * So if an inline extent passed all above checks, just add it + * for defrag, and be converted to regular extents. + */ + if (em->block_start == EXTENT_MAP_INLINE) + goto add; + + next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, + extent_thresh, newer_than, 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. */ } - if (!PageUptodate(page)) { - btrfs_readpage(NULL, page); - lock_page(page); - if (!PageUptodate(page)) { - unlock_page(page); - put_page(page); - ret = -EIO; - break; +add: + last_is_target = true; + 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 */ } - if (page->mapping != inode->i_mapping) { - unlock_page(page); - put_page(page); - goto again; + /* 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); - pages[i] = page; - i_done++; +next: + cur = extent_map_end(em); + free_extent_map(em); } - if (!i_done || ret) - goto out; + if (ret < 0) { + struct defrag_target_range *entry; + struct defrag_target_range *tmp; - if (!(inode->i_sb->s_flags & SB_ACTIVE)) - goto out; + list_for_each_entry_safe(entry, tmp, target_list, list) { + list_del_init(&entry->list); + kfree(entry); + } + } + if (!ret && last_scanned_ret) { + /* + * If the last extent is not a target, the caller can skip to + * the end of that extent. + * Otherwise, we can only go the end of the specified range. + */ + if (!last_is_target) + *last_scanned_ret = max(cur, *last_scanned_ret); + else + *last_scanned_ret = max(start + len, *last_scanned_ret); + } + return ret; +} - /* - * so now we have a nice long stream of locked - * and up to date pages, lets wait on them - */ - for (i = 0; i < i_done; i++) +#define CLUSTER_SIZE (SZ_256K) +static_assert(IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE)); + +/* + * 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, 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, + u64 *last_scanned_ret) +{ + 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]); - page_start = page_offset(pages[0]); - page_end = page_offset(pages[i_done - 1]) + PAGE_SIZE; + /* Lock the pages range */ + lock_extent(&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, last_scanned_ret); + if (ret < 0) + goto unlock_extent; - lock_extent_bits(&BTRFS_I(inode)->io_tree, - page_start, page_end - 1, &cached_state); - clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, - page_end - 1, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | - EXTENT_DEFRAG, 0, 0, &cached_state); + list_for_each_entry(entry, &target_list, list) { + ret = defrag_one_locked_target(inode, entry, pages, nr_pages, + &cached_state); + if (ret < 0) + break; + } - if (i_done != page_cnt) { - spin_lock(&BTRFS_I(inode)->lock); - btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); - spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, data_reserved, - start_index << PAGE_SHIFT, - (page_cnt - i_done) << PAGE_SHIFT, true); + list_for_each_entry_safe(entry, tmp, &target_list, list) { + list_del_init(&entry->list); + kfree(entry); } +unlock_extent: + unlock_extent(&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, + u64 *last_scanned_ret) +{ + const u32 sectorsize = inode->root->fs_info->sectorsize; + struct defrag_target_range *entry; + struct defrag_target_range *tmp; + LIST_HEAD(target_list); + int ret; - set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, - &cached_state); + ret = defrag_collect_targets(inode, start, len, extent_thresh, + newer_than, do_compress, false, + &target_list, NULL); + if (ret < 0) + goto out; - unlock_extent_cached(&BTRFS_I(inode)->io_tree, - page_start, page_end - 1, &cached_state); + list_for_each_entry(entry, &target_list, list) { + u32 range_len = entry->len; - for (i = 0; i < i_done; i++) { - clear_page_dirty_for_io(pages[i]); - ClearPageChecked(pages[i]); - set_page_extent_mapped(pages[i]); - set_page_dirty(pages[i]); - unlock_page(pages[i]); - put_page(pages[i]); + /* Reached or beyond the limit */ + if (max_sectors && *sectors_defragged >= max_sectors) { + ret = 1; + break; + } + + if (max_sectors) + range_len = min_t(u32, range_len, + (max_sectors - *sectors_defragged) * sectorsize); + + /* + * If defrag_one_range() has updated last_scanned_ret, + * our range may already be invalid (e.g. hole punched). + * Skip if our range is before last_scanned_ret, as there is + * no need to defrag the range anymore. + */ + if (entry->start + range_len <= *last_scanned_ret) + continue; + + 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, + last_scanned_ret); + if (ret < 0) + break; + *sectors_defragged += range_len >> + inode->root->fs_info->sectorsize_bits; } - btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); - extent_changeset_free(data_reserved); - return i_done; out: - for (i = 0; i < i_done; i++) { - unlock_page(pages[i]); - put_page(pages[i]); - } - btrfs_delalloc_release_space(inode, data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); - extent_changeset_free(data_reserved); + list_for_each_entry_safe(entry, tmp, &target_list, list) { + list_del_init(&entry->list); + kfree(entry); + } + if (ret >= 0) + *last_scanned_ret = max(*last_scanned_ret, start + len); return ret; - } -int btrfs_defrag_file(struct inode *inode, struct file *file, +/* + * 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. + * + * Return <0 for error. + * Return >=0 for the number of sectors defragged, and range->start will be updated + * to indicate the file offset where next defrag should be started at. + * (Mostly for autodefrag, which sets @max_to_defrag thus we may exit early without + * defragging all the range). + */ +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); - struct btrfs_root *root = BTRFS_I(inode)->root; - struct file_ra_state *ra = NULL; - unsigned long last_index; + unsigned long sectors_defragged = 0; u64 isize = i_size_read(inode); - u64 last_len = 0; - u64 skip = 0; - u64 defrag_end = 0; - u64 newer_off = range->start; - unsigned long i; - unsigned long ra_index = 0; - int ret; - int defrag_count = 0; + 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; - unsigned long max_cluster = SZ_256K >> PAGE_SHIFT; - unsigned long cluster = max_cluster; - u64 new_align = ~((u64)SZ_128K - 1); - struct page **pages = NULL; - bool do_compress = range->flags & BTRFS_DEFRAG_RANGE_COMPRESS; + pgoff_t start_index; if (isize == 0) return 0; @@ -1423,178 +1827,162 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, 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); + } else { + /* Defrag until file end */ + last_byte = isize; + } + + /* Align the range */ + cur = round_down(range->start, fs_info->sectorsize); + last_byte = round_up(last_byte, fs_info->sectorsize) - 1; + /* - * If we were not given a file, allocate a readahead context. As + * 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 (!file) { + if (!ra) { + ra_allocated = true; ra = kzalloc(sizeof(*ra), GFP_KERNEL); if (ra) file_ra_state_init(ra, inode->i_mapping); - } else { - ra = &file->f_ra; - } - - pages = kmalloc_array(max_cluster, sizeof(struct page *), GFP_KERNEL); - if (!pages) { - ret = -ENOMEM; - goto out_ra; - } - - /* find the last page to defrag */ - if (range->start + range->len > range->start) { - last_index = min_t(u64, isize - 1, - range->start + range->len - 1) >> PAGE_SHIFT; - } else { - last_index = (isize - 1) >> PAGE_SHIFT; } - if (newer_than) { - ret = find_new_extents(root, inode, newer_than, - &newer_off, SZ_64K); - if (!ret) { - range->start = newer_off; - /* - * we always align our defrag to help keep - * the extents in the file evenly spaced - */ - i = (newer_off & new_align) >> PAGE_SHIFT; - } else - goto out_ra; - } else { - i = range->start >> PAGE_SHIFT; - } - if (!max_to_defrag) - max_to_defrag = last_index - i + 1; - /* - * make writeback starts from i, so the defrag range can be - * written sequentially. + * Make writeback start from the beginning of the range, so that the + * defrag range can be written sequentially. */ - if (i < inode->i_mapping->writeback_index) - inode->i_mapping->writeback_index = i; + start_index = cur >> PAGE_SHIFT; + if (start_index < inode->i_mapping->writeback_index) + inode->i_mapping->writeback_index = start_index; - while (i <= last_index && defrag_count < max_to_defrag && - (i < DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE))) { - /* - * make sure we stop running if someone unmounts - * the FS - */ - if (!(inode->i_sb->s_flags & SB_ACTIVE)) - break; + while (cur < last_byte) { + const unsigned long prev_sectors_defragged = sectors_defragged; + u64 last_scanned = cur; + u64 cluster_end; if (btrfs_defrag_cancelled(fs_info)) { - btrfs_debug(fs_info, "defrag_file cancelled"); ret = -EAGAIN; break; } - if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT, - extent_thresh, &last_len, &skip, - &defrag_end, do_compress)){ - unsigned long next; - /* - * the should_defrag function tells us how much to skip - * bump our counter by the suggested amount - */ - next = DIV_ROUND_UP(skip, PAGE_SIZE); - i = max(i + 1, next); - continue; - } - - if (!newer_than) { - cluster = (PAGE_ALIGN(defrag_end) >> - PAGE_SHIFT) - i; - cluster = min(cluster, max_cluster); - } else { - cluster = max_cluster; - } - - if (i + cluster > ra_index) { - ra_index = max(i, ra_index); - if (ra) - page_cache_sync_readahead(inode->i_mapping, ra, - file, ra_index, cluster); - ra_index += cluster; - } + /* 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); - inode_lock(inode); + btrfs_inode_lock(inode, 0); if (IS_SWAPFILE(inode)) { ret = -ETXTBSY; - } else { - if (do_compress) - BTRFS_I(inode)->defrag_compress = compress_type; - ret = cluster_pages_for_defrag(inode, pages, i, cluster); + btrfs_inode_unlock(inode, 0); + break; } - if (ret < 0) { - inode_unlock(inode); - goto out_ra; + 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, &last_scanned); - defrag_count += ret; - balance_dirty_pages_ratelimited(inode->i_mapping); - inode_unlock(inode); - - if (newer_than) { - if (newer_off == (u64)-1) - break; + if (sectors_defragged > prev_sectors_defragged) + balance_dirty_pages_ratelimited(inode->i_mapping); - if (ret > 0) - i += ret; - - newer_off = max(newer_off + 1, - (u64)i << PAGE_SHIFT); - - ret = find_new_extents(root, inode, newer_than, - &newer_off, SZ_64K); - if (!ret) { - range->start = newer_off; - i = (newer_off & new_align) >> PAGE_SHIFT; - } else { - break; - } - } else { - if (ret > 0) { - i += ret; - last_len += ret << PAGE_SHIFT; - } else { - i++; - last_len = 0; - } + btrfs_inode_unlock(inode, 0); + if (ret < 0) + break; + cur = max(cluster_end + 1, last_scanned); + if (ret > 0) { + ret = 0; + break; } + cond_resched(); } - 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)) + if (ra_allocated) + kfree(ra); + /* + * Update range.start for autodefrag, this will indicate where to start + * in next run. + */ + range->start = cur; + 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); + } + return ret; +} - 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); +/* + * Try to start exclusive operation @type or cancel it if it's running. + * + * Return: + * 0 - normal mode, newly claimed op started + * >0 - normal mode, something else is running, + * return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS to user space + * ECANCELED - cancel mode, successful cancel + * ENOTCONN - cancel mode, operation not running anymore + */ +static int exclop_start_or_cancel_reloc(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type, bool cancel) +{ + if (!cancel) { + /* Start normal op */ + if (!btrfs_exclop_start(fs_info, type)) + return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; + /* Exclusive operation is now claimed */ + return 0; } - ret = defrag_count; + /* Cancel running op */ + if (btrfs_exclop_start_try_lock(fs_info, type)) { + /* + * This blocks any exclop finish from setting it to NONE, so we + * request cancellation. Either it runs and we will wait for it, + * or it has finished and no waiting will happen. + */ + atomic_inc(&fs_info->reloc_cancel_req); + btrfs_exclop_start_unlock(fs_info); + + if (test_bit(BTRFS_FS_RELOC_RUNNING, &fs_info->flags)) + wait_on_bit(&fs_info->flags, BTRFS_FS_RELOC_RUNNING, + TASK_INTERRUPTIBLE); -out_ra: - if (do_compress) { - inode_lock(inode); - BTRFS_I(inode)->defrag_compress = BTRFS_COMPRESS_NONE; - inode_unlock(inode); + return -ECANCELED; } - if (!file) - kfree(ra); - kfree(pages); - return ret; + + /* Something else is running or none */ + return -ENOTCONN; } 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); u64 new_size; @@ -1609,6 +1997,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, char *devstr = NULL; int ret = 0; int mod = 0; + bool cancel; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1617,20 +2006,23 @@ static noinline int btrfs_ioctl_resize(struct file *file, if (ret) return ret; - if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) { - mnt_drop_write_file(file); - return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; - } - + /* + * Read the arguments before checking exclusivity to be able to + * distinguish regular resize and cancel + */ vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) { ret = PTR_ERR(vol_args); - goto out; + goto out_drop; } - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - sizestr = vol_args->name; + cancel = (strcmp("cancel", sizestr) == 0); + ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_RESIZE, cancel); + if (ret) + goto out_free; + /* Exclusive operation is now claimed */ + devstr = strchr(sizestr, ':'); if (devstr) { sizestr = devstr + 1; @@ -1638,20 +2030,21 @@ static noinline int btrfs_ioctl_resize(struct file *file, devstr = vol_args->name; ret = kstrtoull(devstr, 10, &devid); if (ret) - goto out_free; + goto out_finish; if (!devid) { ret = -EINVAL; - goto out_free; + goto out_finish; } btrfs_info(fs_info, "resizing devid %llu", devid); } - device = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); + args.devid = devid; + device = btrfs_find_device(fs_info->fs_devices, &args); if (!device) { btrfs_info(fs_info, "resizer unable to find device %llu", devid); ret = -ENODEV; - goto out_free; + goto out_finish; } if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { @@ -1659,11 +2052,11 @@ static noinline int btrfs_ioctl_resize(struct file *file, "resizer unable to apply on readonly device %llu", devid); ret = -EPERM; - goto out_free; + goto out_finish; } if (!strcmp(sizestr, "max")) - new_size = device->bdev->bd_inode->i_size; + new_size = bdev_nr_bytes(device->bdev); else { if (sizestr[0] == '-') { mod = -1; @@ -1675,13 +2068,13 @@ static noinline int btrfs_ioctl_resize(struct file *file, new_size = memparse(sizestr, &retptr); if (*retptr != '\0' || new_size == 0) { ret = -EINVAL; - goto out_free; + goto out_finish; } } if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { ret = -EPERM; - goto out_free; + goto out_finish; } old_size = btrfs_device_get_total_bytes(device); @@ -1689,36 +2082,33 @@ static noinline int btrfs_ioctl_resize(struct file *file, if (mod < 0) { if (new_size > old_size) { ret = -EINVAL; - goto out_free; + goto out_finish; } new_size = old_size - new_size; } else if (mod > 0) { if (new_size > ULLONG_MAX - old_size) { ret = -ERANGE; - goto out_free; + goto out_finish; } new_size = old_size + new_size; } if (new_size < SZ_256M) { ret = -EINVAL; - goto out_free; + goto out_finish; } - if (new_size > device->bdev->bd_inode->i_size) { + if (new_size > bdev_nr_bytes(device->bdev)) { ret = -EFBIG; - goto out_free; + goto out_finish; } new_size = round_down(new_size, fs_info->sectorsize); - btrfs_info_in_rcu(fs_info, "new size for %s is %llu", - rcu_str_deref(device->name), new_size); - if (new_size > old_size) { trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - goto out_free; + goto out_finish; } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans); @@ -1726,17 +2116,24 @@ static noinline int btrfs_ioctl_resize(struct file *file, ret = btrfs_shrink_device(device, new_size); } /* equal, nothing need to do */ + if (ret == 0 && new_size != old_size) + btrfs_info_in_rcu(fs_info, + "resize device %s (devid %llu) from %llu to %llu", + rcu_str_deref(device->name), device->devid, + old_size, new_size); +out_finish: + btrfs_exclop_finish(fs_info); out_free: kfree(vol_args); -out: - clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); +out_drop: mnt_drop_write_file(file); return ret; } -static noinline int btrfs_ioctl_snap_create_transid(struct file *file, +static noinline int __btrfs_ioctl_snap_create(struct file *file, + struct user_namespace *mnt_userns, const char *name, unsigned long fd, int subvol, - u64 *transid, bool readonly, + bool readonly, struct btrfs_qgroup_inherit *inherit) { int namelen; @@ -1762,8 +2159,8 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, } if (subvol) { - ret = btrfs_mksubvol(&file->f_path, name, namelen, - NULL, transid, readonly, inherit); + ret = btrfs_mksubvol(&file->f_path, mnt_userns, name, + namelen, NULL, readonly, inherit); } else { struct fd src = fdget(fd); struct inode *src_inode; @@ -1777,16 +2174,17 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); ret = -EXDEV; - } else if (!inode_owner_or_capable(src_inode)) { + } else if (!inode_owner_or_capable(mnt_userns, src_inode)) { /* * Subvolume creation is not restricted, but snapshots * are limited to own subvolumes only */ ret = -EPERM; } else { - ret = btrfs_mksubvol(&file->f_path, name, namelen, - BTRFS_I(src_inode)->root, - transid, readonly, inherit); + ret = btrfs_mksnapshot(&file->f_path, mnt_userns, + name, namelen, + BTRFS_I(src_inode)->root, + readonly, inherit); } fdput(src); } @@ -1810,9 +2208,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, return PTR_ERR(vol_args); vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - ret = btrfs_ioctl_snap_create_transid(file, vol_args->name, - vol_args->fd, subvol, - NULL, false, NULL); + ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file), + vol_args->name, vol_args->fd, subvol, + false, NULL); kfree(vol_args); return ret; @@ -1823,8 +2221,6 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, { struct btrfs_ioctl_vol_args_v2 *vol_args; int ret; - u64 transid = 0; - u64 *ptr = NULL; bool readonly = false; struct btrfs_qgroup_inherit *inherit = NULL; @@ -1836,26 +2232,18 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, return PTR_ERR(vol_args); vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0'; - if (vol_args->flags & - ~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY | - BTRFS_SUBVOL_QGROUP_INHERIT)) { + if (vol_args->flags & ~BTRFS_SUBVOL_CREATE_ARGS_MASK) { ret = -EOPNOTSUPP; goto free_args; } - if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - - btrfs_warn(fs_info, -"SNAP_CREATE_V2 ioctl with CREATE_ASYNC is deprecated and will be removed in kernel 5.7"); - - ptr = &transid; - } if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - if (vol_args->size > PAGE_SIZE) { + u64 nums; + + if (vol_args->size < sizeof(*inherit) || + vol_args->size > PAGE_SIZE) { ret = -EINVAL; goto free_args; } @@ -1864,20 +2252,27 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, ret = PTR_ERR(inherit); 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; + goto free_inherit; + } } - ret = btrfs_ioctl_snap_create_transid(file, vol_args->name, - vol_args->fd, subvol, ptr, - readonly, inherit); + ret = __btrfs_ioctl_snap_create(file, file_mnt_user_ns(file), + vol_args->name, vol_args->fd, subvol, + readonly, inherit); if (ret) goto free_inherit; - - if (ptr && copy_to_user(arg + - offsetof(struct btrfs_ioctl_vol_args_v2, - transid), - ptr, sizeof(*ptr))) - ret = -EFAULT; - free_inherit: kfree(inherit); free_args: @@ -1885,10 +2280,9 @@ free_args: return ret; } -static noinline int btrfs_ioctl_subvol_getflags(struct file *file, +static noinline int btrfs_ioctl_subvol_getflags(struct 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; int ret = 0; @@ -1919,7 +2313,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, u64 flags; int ret = 0; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(file_mnt_user_ns(file), inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -1936,11 +2330,6 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, goto out_drop_write; } - if (flags & BTRFS_SUBVOL_CREATE_ASYNC) { - ret = -EINVAL; - goto out_drop_write; - } - if (flags & ~BTRFS_SUBVOL_RDONLY) { ret = -EOPNOTSUPP; goto out_drop_write; @@ -2057,7 +2446,7 @@ static noinline int copy_to_sk(struct btrfs_path *path, for (i = slot; i < nritems; i++) { item_off = btrfs_item_ptr_offset(leaf, i); - item_len = btrfs_item_size_nr(leaf, i); + item_len = btrfs_item_size(leaf, i); btrfs_item_key_to_cpu(leaf, key, i); if (!key_in_sk(key, sk)) @@ -2090,9 +2479,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, sh.len = item_len; sh.transid = found_transid; - /* copy search result header */ - if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { - ret = -EFAULT; + /* + * Copy search result header. If we fault then loop again so we + * can fault in the pages and -EFAULT there if there's a + * problem. Otherwise we'll fault and then copy the buffer in + * properly this next time through + */ + if (copy_to_user_nofault(ubuf + *sk_offset, &sh, sizeof(sh))) { + ret = 0; goto out; } @@ -2100,10 +2494,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, if (item_len) { char __user *up = ubuf + *sk_offset; - /* copy the item */ - if (read_extent_buffer_to_user(leaf, up, - item_off, item_len)) { - ret = -EFAULT; + /* + * Copy the item, same behavior as above, but reset the + * * sk_offset so we copy the full thing again. + */ + if (read_extent_buffer_to_user_nofault(leaf, up, + item_off, item_len)) { + ret = 0; + *sk_offset -= sizeof(sh); goto out; } @@ -2174,12 +2572,9 @@ static noinline int search_ioctl(struct inode *inode, if (sk->tree_id == 0) { /* search the root of the inode that was passed */ - root = BTRFS_I(inode)->root; + root = btrfs_grab_root(BTRFS_I(inode)->root); } else { - key.objectid = sk->tree_id; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - root = btrfs_read_fs_root_no_name(info, &key); + root = btrfs_get_fs_root(info, sk->tree_id, true); if (IS_ERR(root)) { btrfs_free_path(path); return PTR_ERR(root); @@ -2191,6 +2586,15 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { + ret = -EFAULT; + /* + * 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)) + break; + ret = btrfs_search_forward(root, &key, path, sk->min_transid); if (ret != 0) { if (ret > 0) @@ -2208,30 +2612,27 @@ static noinline int search_ioctl(struct inode *inode, 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 inode *inode, + 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; 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); /* @@ -2246,12 +2647,11 @@ 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 inode *inode, 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; @@ -2260,7 +2660,6 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file, 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; @@ -2270,7 +2669,6 @@ 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, (char __user *)(&uarg->buf[0])); if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key))) @@ -2311,12 +2709,10 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX - 1]; - key.objectid = tree_id; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - root = btrfs_read_fs_root_no_name(info, &key); + root = btrfs_get_fs_root(info, tree_id, true); if (IS_ERR(root)) { ret = PTR_ERR(root); + root = NULL; goto out; } @@ -2325,23 +2721,16 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.offset = (u64)-1; while (1) { - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + ret = btrfs_search_backwards(root, &key, path); if (ret < 0) goto out; else if (ret > 0) { - ret = btrfs_previous_item(root, path, dirid, - BTRFS_INODE_REF_KEY); - if (ret < 0) - goto out; - else if (ret > 0) { - ret = -ENOENT; - goto out; - } + ret = -ENOENT; + goto out; } l = path->nodes[0]; slot = path->slots[0]; - btrfs_item_key_to_cpu(l, &key, slot); iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref); len = btrfs_inode_ref_name_len(l, iref); @@ -2367,11 +2756,13 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, name[total_len] = '\0'; ret = 0; out: + btrfs_put_root(root); btrfs_free_path(path); return ret; } -static int btrfs_search_path_in_tree_user(struct inode *inode, +static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, + struct inode *inode, struct btrfs_ioctl_ino_lookup_user_args *args) { struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; @@ -2383,7 +2774,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, unsigned long item_len; struct btrfs_inode_ref *iref; struct btrfs_root_ref *rref; - struct btrfs_root *root; + struct btrfs_root *root = NULL; struct btrfs_path *path; struct btrfs_key key, key2; struct extent_buffer *leaf; @@ -2405,10 +2796,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, if (dirid != upper_limit.objectid) { ptr = &args->path[BTRFS_INO_LOOKUP_USER_PATH_MAX - 1]; - key.objectid = treeid; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - root = btrfs_read_fs_root_no_name(fs_info, &key); + root = btrfs_get_fs_root(fs_info, treeid, true); if (IS_ERR(root)) { ret = PTR_ERR(root); goto out; @@ -2418,23 +2806,16 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; while (1) { - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = btrfs_previous_item(root, path, dirid, - BTRFS_INODE_REF_KEY); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = -ENOENT; - goto out; - } + ret = btrfs_search_backwards(root, &key, path); + 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, &key, slot); iref = btrfs_item_ptr(leaf, slot, struct btrfs_inode_ref); len = btrfs_inode_ref_name_len(leaf, iref); @@ -2442,7 +2823,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, total_len += len + 1; if (ptr < args->path) { ret = -ENAMETOOLONG; - goto out; + goto out_put; } *(ptr + len) = '/'; @@ -2453,10 +2834,10 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, ret = btrfs_previous_item(root, path, dirid, BTRFS_INODE_ITEM_KEY); if (ret < 0) { - goto out; + goto out_put; } else if (ret > 0) { ret = -ENOENT; - goto out; + goto out_put; } leaf = path->nodes[0]; @@ -2464,26 +2845,27 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, btrfs_item_key_to_cpu(leaf, &key2, slot); if (key2.objectid != dirid) { ret = -ENOENT; - goto out; + goto out_put; } - temp_inode = btrfs_iget(sb, &key2, root); + temp_inode = btrfs_iget(sb, key2.objectid, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); - goto out; + goto out_put; } - ret = inode_permission(temp_inode, MAY_READ | MAY_EXEC); + ret = inode_permission(mnt_userns, temp_inode, + MAY_READ | MAY_EXEC); iput(temp_inode); if (ret) { ret = -EACCES; - goto out; + goto out_put; } if (key.offset == upper_limit.objectid) break; if (key.objectid == BTRFS_FIRST_FREE_OBJECTID) { ret = -EACCES; - goto out; + goto out_put; } btrfs_release_path(path); @@ -2494,15 +2876,16 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, memmove(args->path, ptr, total_len); args->path[total_len] = '\0'; + btrfs_put_root(root); + root = NULL; btrfs_release_path(path); } /* Get the bottom subvolume's name from ROOT_REF */ - root = fs_info->tree_root; key.objectid = treeid; key.type = BTRFS_ROOT_REF_KEY; key.offset = args->treeid; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); if (ret < 0) { goto out; } else if (ret > 0) { @@ -2515,7 +2898,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, btrfs_item_key_to_cpu(leaf, &key, slot); item_off = btrfs_item_ptr_offset(leaf, slot); - item_len = btrfs_item_size_nr(leaf, slot); + 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)) { @@ -2529,30 +2912,29 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, read_extent_buffer(leaf, args->name, item_off, item_len); args->name[item_len] = 0; +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 = root->root_key.objectid; if (args->objectid == BTRFS_FIRST_FREE_OBJECTID) { args->name[0] = 0; @@ -2564,7 +2946,7 @@ 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); @@ -2610,7 +2992,7 @@ static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp) return -EACCES; } - ret = btrfs_search_path_in_tree_user(inode, args); + ret = btrfs_search_path_in_tree_user(file_mnt_user_ns(file), inode, args); if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) ret = -EFAULT; @@ -2620,7 +3002,7 @@ 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; @@ -2632,7 +3014,6 @@ 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; @@ -2646,17 +3027,14 @@ 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.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - root = btrfs_read_fs_root_no_name(fs_info, &key); + root = btrfs_get_fs_root(fs_info, key.objectid, true); if (IS_ERR(root)) { ret = PTR_ERR(root); - goto out; + goto out_free; } root_item = &root->root_item; @@ -2689,16 +3067,14 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) if (key.objectid != BTRFS_FS_TREE_OBJECTID) { /* Search root tree for ROOT_BACKREF of this subvolume */ - root = fs_info->tree_root; - key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); if (ret < 0) { goto out; } else if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { - ret = btrfs_next_leaf(root, path); + ret = btrfs_next_leaf(fs_info->tree_root, path); if (ret < 0) { goto out; } else if (ret > 0) { @@ -2719,7 +3095,7 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) item_off = btrfs_item_ptr_offset(leaf, slot) + sizeof(struct btrfs_root_ref); - item_len = btrfs_item_size_nr(leaf, slot) + item_len = btrfs_item_size(leaf, slot) - sizeof(struct btrfs_root_ref); read_extent_buffer(leaf, subvol_info->name, item_off, item_len); @@ -2733,8 +3109,10 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) ret = -EFAULT; out: + btrfs_put_root(root); +out_free: btrfs_free_path(path); - kzfree(subvol_info); + kfree(subvol_info); return ret; } @@ -2742,15 +3120,14 @@ out: * 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; @@ -2766,15 +3143,13 @@ 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 = root->root_key.objectid; 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; @@ -2836,7 +3211,8 @@ out: } static noinline int btrfs_ioctl_snap_destroy(struct file *file, - void __user *arg) + void __user *arg, + bool destroy_v2) { struct dentry *parent = file->f_path.dentry; struct btrfs_fs_info *fs_info = btrfs_sb(parent->d_sb); @@ -2845,34 +3221,145 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, struct inode *inode; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *dest = NULL; - struct btrfs_ioctl_vol_args *vol_args; - int namelen; + 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); + char *subvol_name, *subvol_name_ptr = NULL; + int subvol_namelen; int err = 0; + bool destroy_parent = false; - if (!S_ISDIR(dir->i_mode)) - return -ENOTDIR; + /* 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; + } - vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (destroy_v2) { + vol_args2 = memdup_user(arg, sizeof(*vol_args2)); + if (IS_ERR(vol_args2)) + return PTR_ERR(vol_args2); - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - namelen = strlen(vol_args->name); - if (strchr(vol_args->name, '/') || - strncmp(vol_args->name, "..", namelen) == 0) { - err = -EINVAL; - goto out; + if (vol_args2->flags & ~BTRFS_SUBVOL_DELETE_ARGS_MASK) { + err = -EOPNOTSUPP; + goto out; + } + + /* + * If SPEC_BY_ID is not set, we are looking for the subvolume by + * name, same as v1 currently does. + */ + if (!(vol_args2->flags & BTRFS_SUBVOL_SPEC_BY_ID)) { + vol_args2->name[BTRFS_SUBVOL_NAME_MAX] = 0; + subvol_name = vol_args2->name; + + err = mnt_want_write_file(file); + if (err) + goto out; + } else { + struct inode *old_dir; + + if (vol_args2->subvolid < BTRFS_FIRST_FREE_OBJECTID) { + err = -EINVAL; + goto out; + } + + err = mnt_want_write_file(file); + if (err) + goto out; + + dentry = btrfs_get_dentry(fs_info->sb, + BTRFS_FIRST_FREE_OBJECTID, + vol_args2->subvolid, 0, 0); + if (IS_ERR(dentry)) { + err = PTR_ERR(dentry); + goto out_drop_write; + } + + /* + * Change the default parent since the subvolume being + * deleted can be outside of the current mount point. + */ + parent = btrfs_get_parent(dentry); + + /* + * At this point dentry->d_name can point to '/' if the + * subvolume we want to destroy is outsite of the + * current mount point, so we need to release the + * current dentry and execute the lookup to return a new + * one with ->d_name pointing to the + * <mount point>/subvol_name. + */ + dput(dentry); + if (IS_ERR(parent)) { + err = PTR_ERR(parent); + goto out_drop_write; + } + old_dir = dir; + dir = d_inode(parent); + + /* + * If v2 was used with SPEC_BY_ID, a new parent was + * allocated since the subvolume can be outside of the + * current mount point. Later on we need to release this + * new parent dentry. + */ + destroy_parent = true; + + /* + * On idmapped mounts, deletion via subvolid is + * restricted to subvolumes that are immediate + * ancestors of the inode referenced by the file + * descriptor in the ioctl. Otherwise the idmapping + * could potentially be abused to delete subvolumes + * 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; + 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); + goto free_parent; + } + /* subvol_name_ptr is already nul terminated */ + subvol_name = (char *)kbasename(subvol_name_ptr); + } + } else { + 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; + subvol_name = vol_args->name; + + err = mnt_want_write_file(file); + if (err) + goto out; } - err = mnt_want_write_file(file); - if (err) - goto out; + subvol_namelen = strlen(subvol_name); + if (strchr(subvol_name, '/') || + strncmp(subvol_name, "..", subvol_namelen) == 0) { + err = -EINVAL; + goto free_subvol_name; + } + + if (!S_ISDIR(dir->i_mode)) { + err = -ENOTDIR; + goto free_subvol_name; + } err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); if (err == -EINTR) - goto out_drop_write; - dentry = lookup_one_len(vol_args->name, parent, namelen); + goto free_subvol_name; + dentry = lookup_one(mnt_userns, subvol_name, parent, subvol_namelen); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_unlock_dir; @@ -2914,13 +3401,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, if (root == dest) goto out_dput; - err = inode_permission(inode, MAY_WRITE | MAY_EXEC); + err = inode_permission(mnt_userns, inode, MAY_WRITE | MAY_EXEC); if (err) goto out_dput; } /* check if subvolume may be deleted by a user */ - err = btrfs_may_delete(dir, dentry, 1); + err = btrfs_may_delete(mnt_userns, dir, dentry, 1); if (err) goto out_dput; @@ -2929,21 +3416,25 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto out_dput; } - inode_lock(inode); + btrfs_inode_lock(inode, 0); err = btrfs_delete_subvolume(dir, dentry); - inode_unlock(inode); - if (!err) { - fsnotify_rmdir(dir, dentry); - d_delete(dentry); - } + btrfs_inode_unlock(inode, 0); + if (!err) + d_delete_notify(dir, dentry); out_dput: dput(dentry); out_unlock_dir: - inode_unlock(dir); + btrfs_inode_unlock(dir, 0); +free_subvol_name: + kfree(subvol_name_ptr); +free_parent: + if (destroy_parent) + dput(parent); out_drop_write: mnt_drop_write_file(file); out: + kfree(vol_args2); kfree(vol_args); return err; } @@ -2952,7 +3443,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) { struct inode *inode = file_inode(file); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_ioctl_defrag_range_args *range; + struct btrfs_ioctl_defrag_range_args range = {0}; int ret; ret = mnt_want_write_file(file); @@ -2979,38 +3470,29 @@ 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(inode, MAY_WRITE)) { + inode_permission(&init_user_ns, inode, MAY_WRITE)) { ret = -EPERM; goto out; } - range = kzalloc(sizeof(*range), GFP_KERNEL); - if (!range) { - ret = -ENOMEM; - goto out; - } - if (argp) { - if (copy_from_user(range, argp, - sizeof(*range))) { + if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; - kfree(range); goto out; } /* compression requires us to start the IO */ - if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { - range->flags |= BTRFS_DEFRAG_RANGE_START_IO; - range->extent_thresh = (u32)-1; + if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + range.flags |= BTRFS_DEFRAG_RANGE_START_IO; + range.extent_thresh = (u32)-1; } } else { /* the rest are all set to zero by kzalloc */ - range->len = (u64)-1; + range.len = (u64)-1; } - ret = btrfs_defrag_file(file_inode(file), file, - range, BTRFS_OLDEST_GENERATION, 0); + ret = btrfs_defrag_file(file_inode(file), &file->f_ra, + &range, BTRFS_OLDEST_GENERATION, 0); if (ret > 0) ret = 0; - kfree(range); break; default: ret = -EINVAL; @@ -3023,13 +3505,30 @@ out: static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg) { struct btrfs_ioctl_vol_args *vol_args; + bool restore_op = false; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) - return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; + 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 (!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; + + /* + * We can do the device add because we have a paused balanced, + * change the exclusive op type and remember we should bring + * back the paused balance + */ + fs_info->exclusive_operation = BTRFS_EXCLOP_DEV_ADD; + btrfs_exclop_start_unlock(fs_info); + restore_op = true; + } vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) { @@ -3045,48 +3544,60 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg) kfree(vol_args); out: - clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); + if (restore_op) + btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE_PAUSED); + else + btrfs_exclop_finish(fs_info); return ret; } 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_ioctl_vol_args_v2 *vol_args; + struct block_device *bdev = NULL; + fmode_t mode; int ret; + bool cancel = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - ret = mnt_want_write_file(file); - if (ret) - return ret; - vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) { - ret = PTR_ERR(vol_args); - goto err_drop; - } + if (IS_ERR(vol_args)) + return PTR_ERR(vol_args); - /* Check for compatibility reject unknown flags */ - if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED) { + if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) { ret = -EOPNOTSUPP; goto out; } - if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) { - ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; - goto out; - } - + vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0'; if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) { - ret = btrfs_rm_device(fs_info, NULL, vol_args->devid); + args.devid = vol_args->devid; + } else if (!strcmp("cancel", vol_args->name)) { + cancel = true; } else { - vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0'; - ret = btrfs_rm_device(fs_info, vol_args->name, 0); + ret = btrfs_get_dev_args_from_path(fs_info, &args, vol_args->name); + if (ret) + goto out; } - clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); + + ret = mnt_want_write_file(file); + if (ret) + goto out; + + ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE, + cancel); + if (ret) + goto err_drop; + + /* Exclusive operation is now claimed */ + ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + + btrfs_exclop_finish(fs_info); if (!ret) { if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) @@ -3096,49 +3607,62 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) btrfs_info(fs_info, "device deleted: %s", vol_args->name); } -out: - kfree(vol_args); err_drop: mnt_drop_write_file(file); + if (bdev) + blkdev_put(bdev, mode); +out: + btrfs_put_dev_args_from_path(&args); + kfree(vol_args); return ret; } 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_ioctl_vol_args *vol_args; + struct block_device *bdev = NULL; + fmode_t mode; int ret; + bool cancel = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - ret = mnt_want_write_file(file); - if (ret) - return ret; + vol_args = memdup_user(arg, sizeof(*vol_args)); + if (IS_ERR(vol_args)) + return PTR_ERR(vol_args); - if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) { - ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; - goto out_drop_write; + vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + if (!strcmp("cancel", vol_args->name)) { + cancel = true; + } else { + ret = btrfs_get_dev_args_from_path(fs_info, &args, vol_args->name); + if (ret) + goto out; } - vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) { - ret = PTR_ERR(vol_args); + ret = mnt_want_write_file(file); + if (ret) goto out; - } - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - ret = btrfs_rm_device(fs_info, vol_args->name, 0); + 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); + if (!ret) + btrfs_info(fs_info, "disk deleted %s", vol_args->name); + btrfs_exclop_finish(fs_info); + } - if (!ret) - btrfs_info(fs_info, "disk deleted %s", vol_args->name); - kfree(vol_args); -out: - clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); -out_drop_write: mnt_drop_write_file(file); - + if (bdev) + blkdev_put(bdev, mode); +out: + btrfs_put_dev_args_from_path(&args); + kfree(vol_args); return ret; } @@ -3148,11 +3672,15 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_fs_info_args *fi_args; struct btrfs_device *device; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + u64 flags_in; int ret = 0; - fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL); - if (!fi_args) - return -ENOMEM; + fi_args = memdup_user(arg, sizeof(*fi_args)); + if (IS_ERR(fi_args)) + return PTR_ERR(fi_args); + + flags_in = fi_args->flags; + memset(fi_args, 0, sizeof(*fi_args)); rcu_read_lock(); fi_args->num_devices = fs_devices->num_devices; @@ -3168,6 +3696,23 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, fi_args->sectorsize = fs_info->sectorsize; fi_args->clone_alignment = fs_info->sectorsize; + if (flags_in & BTRFS_FS_INFO_FLAG_CSUM_INFO) { + fi_args->csum_type = btrfs_super_csum_type(fs_info->super_copy); + fi_args->csum_size = btrfs_super_csum_size(fs_info->super_copy); + fi_args->flags |= BTRFS_FS_INFO_FLAG_CSUM_INFO; + } + + if (flags_in & BTRFS_FS_INFO_FLAG_GENERATION) { + fi_args->generation = fs_info->generation; + fi_args->flags |= BTRFS_FS_INFO_FLAG_GENERATION; + } + + if (flags_in & BTRFS_FS_INFO_FLAG_METADATA_UUID) { + memcpy(&fi_args->metadata_uuid, fs_devices->metadata_uuid, + sizeof(fi_args->metadata_uuid)); + fi_args->flags |= BTRFS_FS_INFO_FLAG_METADATA_UUID; + } + if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; @@ -3178,22 +3723,21 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, void __user *arg) { + BTRFS_DEV_LOOKUP_ARGS(args); struct btrfs_ioctl_dev_info_args *di_args; struct btrfs_device *dev; int ret = 0; - char *s_uuid = NULL; di_args = memdup_user(arg, sizeof(*di_args)); if (IS_ERR(di_args)) return PTR_ERR(di_args); + args.devid = di_args->devid; if (!btrfs_is_empty_uuid(di_args->uuid)) - s_uuid = di_args->uuid; + args.uuid = di_args->uuid; rcu_read_lock(); - dev = btrfs_find_device(fs_info->fs_devices, di_args->devid, s_uuid, - NULL, true); - + dev = btrfs_find_device(fs_info->fs_devices, &args); if (!dev) { ret = -ENODEV; goto out; @@ -3220,733 +3764,6 @@ out: return ret; } -static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, - struct inode *inode2, u64 loff2, u64 len) -{ - unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); - unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); -} - -static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, - struct inode *inode2, u64 loff2, u64 len) -{ - if (inode1 < inode2) { - swap(inode1, inode2); - swap(loff1, loff2); - } else if (inode1 == inode2 && loff2 < loff1) { - swap(loff1, loff2); - } - lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); - lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); -} - -static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len, - struct inode *dst, u64 dst_loff) -{ - const u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; - int ret; - - /* - * Lock destination range to serialize with concurrent readpages() and - * source range to serialize with relocation. - */ - btrfs_double_extent_lock(src, loff, dst, dst_loff, len); - ret = btrfs_clone(src, dst, loff, len, ALIGN(len, bs), dst_loff, 1); - btrfs_double_extent_unlock(src, loff, dst, dst_loff, len); - - return ret; -} - -#define BTRFS_MAX_DEDUPE_LEN SZ_16M - -static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, - struct inode *dst, u64 dst_loff) -{ - int ret; - u64 i, tail_len, chunk_count; - struct btrfs_root *root_dst = BTRFS_I(dst)->root; - - spin_lock(&root_dst->root_item_lock); - if (root_dst->send_in_progress) { - btrfs_warn_rl(root_dst->fs_info, -"cannot deduplicate to root %llu while send operations are using it (%d in progress)", - root_dst->root_key.objectid, - root_dst->send_in_progress); - spin_unlock(&root_dst->root_item_lock); - return -EAGAIN; - } - root_dst->dedupe_in_progress++; - spin_unlock(&root_dst->root_item_lock); - - tail_len = olen % BTRFS_MAX_DEDUPE_LEN; - chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN); - - for (i = 0; i < chunk_count; i++) { - ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN, - dst, dst_loff); - if (ret) - goto out; - - loff += BTRFS_MAX_DEDUPE_LEN; - dst_loff += BTRFS_MAX_DEDUPE_LEN; - } - - if (tail_len > 0) - ret = btrfs_extent_same_range(src, loff, tail_len, dst, - dst_loff); -out: - spin_lock(&root_dst->root_item_lock); - root_dst->dedupe_in_progress--; - spin_unlock(&root_dst->root_item_lock); - - return ret; -} - -static int clone_finish_inode_update(struct btrfs_trans_handle *trans, - struct inode *inode, - u64 endoff, - const u64 destoff, - const u64 olen, - int no_time_update) -{ - struct btrfs_root *root = BTRFS_I(inode)->root; - int ret; - - inode_inc_iversion(inode); - if (!no_time_update) - inode->i_mtime = inode->i_ctime = current_time(inode); - /* - * We round up to the block size at eof when determining which - * extents to clone above, but shouldn't round up the file size. - */ - if (endoff > destoff + olen) - endoff = destoff + olen; - if (endoff > inode->i_size) - btrfs_i_size_write(BTRFS_I(inode), endoff); - - ret = btrfs_update_inode(trans, root, inode); - if (ret) { - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - goto out; - } - ret = btrfs_end_transaction(trans); -out: - return ret; -} - -/* - * Make sure we do not end up inserting an inline extent into a file that has - * already other (non-inline) extents. If a file has an inline extent it can - * not have any other extents and the (single) inline extent must start at the - * file offset 0. Failing to respect these rules will lead to file corruption, - * resulting in EIO errors on read/write operations, hitting BUG_ON's in mm, etc - * - * We can have extents that have been already written to disk or we can have - * dirty ranges still in delalloc, in which case the extent maps and items are - * created only when we run delalloc, and the delalloc ranges might fall outside - * the range we are currently locking in the inode's io tree. So we check the - * inode's i_size because of that (i_size updates are done while holding the - * i_mutex, which we are holding here). - * We also check to see if the inode has a size not greater than "datal" but has - * extents beyond it, due to an fallocate with FALLOC_FL_KEEP_SIZE (and we are - * protected against such concurrent fallocate calls by the i_mutex). - * - * If the file has no extents but a size greater than datal, do not allow the - * copy because we would need turn the inline extent into a non-inline one (even - * with NO_HOLES enabled). If we find our destination inode only has one inline - * extent, just overwrite it with the source inline extent if its size is less - * than the source extent's size, or we could copy the source inline extent's - * data into the destination inode's inline extent if the later is greater then - * the former. - */ -static int clone_copy_inline_extent(struct inode *dst, - struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct btrfs_key *new_key, - const u64 drop_start, - const u64 datal, - const u64 skip, - const u64 size, - char *inline_data) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(dst->i_sb); - struct btrfs_root *root = BTRFS_I(dst)->root; - const u64 aligned_end = ALIGN(new_key->offset + datal, - fs_info->sectorsize); - int ret; - struct btrfs_key key; - - if (new_key->offset > 0) - return -EOPNOTSUPP; - - key.objectid = btrfs_ino(BTRFS_I(dst)); - key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = 0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) { - return ret; - } else if (ret > 0) { - if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - return ret; - else if (ret > 0) - goto copy_inline_extent; - } - btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - if (key.objectid == btrfs_ino(BTRFS_I(dst)) && - key.type == BTRFS_EXTENT_DATA_KEY) { - ASSERT(key.offset > 0); - return -EOPNOTSUPP; - } - } else if (i_size_read(dst) <= datal) { - struct btrfs_file_extent_item *ei; - u64 ext_len; - - /* - * If the file size is <= datal, make sure there are no other - * extents following (can happen do to an fallocate call with - * the flag FALLOC_FL_KEEP_SIZE). - */ - ei = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_file_extent_item); - /* - * If it's an inline extent, it can not have other extents - * following it. - */ - if (btrfs_file_extent_type(path->nodes[0], ei) == - BTRFS_FILE_EXTENT_INLINE) - goto copy_inline_extent; - - ext_len = btrfs_file_extent_num_bytes(path->nodes[0], ei); - if (ext_len > aligned_end) - return -EOPNOTSUPP; - - ret = btrfs_next_item(root, path); - if (ret < 0) { - return ret; - } else if (ret == 0) { - btrfs_item_key_to_cpu(path->nodes[0], &key, - path->slots[0]); - if (key.objectid == btrfs_ino(BTRFS_I(dst)) && - key.type == BTRFS_EXTENT_DATA_KEY) - return -EOPNOTSUPP; - } - } - -copy_inline_extent: - /* - * We have no extent items, or we have an extent at offset 0 which may - * or may not be inlined. All these cases are dealt the same way. - */ - if (i_size_read(dst) > datal) { - /* - * If the destination inode has an inline extent... - * This would require copying the data from the source inline - * extent into the beginning of the destination's inline extent. - * But this is really complex, both extents can be compressed - * or just one of them, which would require decompressing and - * re-compressing data (which could increase the new compressed - * size, not allowing the compressed data to fit anymore in an - * inline extent). - * So just don't support this case for now (it should be rare, - * we are not really saving space when cloning inline extents). - */ - return -EOPNOTSUPP; - } - - btrfs_release_path(path); - ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1); - if (ret) - return ret; - ret = btrfs_insert_empty_item(trans, root, path, new_key, size); - if (ret) - return ret; - - if (skip) { - const u32 start = btrfs_file_extent_calc_inline_size(0); - - memmove(inline_data + start, inline_data + start + skip, datal); - } - - write_extent_buffer(path->nodes[0], inline_data, - btrfs_item_ptr_offset(path->nodes[0], - path->slots[0]), - size); - inode_add_bytes(dst, datal); - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags); - - return 0; -} - -/** - * btrfs_clone() - clone a range from inode file to another - * - * @src: Inode to clone from - * @inode: Inode to clone to - * @off: Offset within source to start clone from - * @olen: Original length, passed by user, of range to clone - * @olen_aligned: Block-aligned value of olen - * @destoff: Offset within @inode to start clone - * @no_time_update: Whether to update mtime/ctime on the target inode - */ -static int btrfs_clone(struct inode *src, struct inode *inode, - const u64 off, const u64 olen, const u64 olen_aligned, - const u64 destoff, int no_time_update) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_path *path = NULL; - struct extent_buffer *leaf; - struct btrfs_trans_handle *trans; - char *buf = NULL; - struct btrfs_key key; - u32 nritems; - int slot; - int ret; - const u64 len = olen_aligned; - u64 last_dest_end = destoff; - - ret = -ENOMEM; - buf = kvmalloc(fs_info->nodesize, GFP_KERNEL); - if (!buf) - return ret; - - path = btrfs_alloc_path(); - if (!path) { - kvfree(buf); - return ret; - } - - path->reada = READA_FORWARD; - /* clone data */ - key.objectid = btrfs_ino(BTRFS_I(src)); - key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = off; - - while (1) { - u64 next_key_min_offset = key.offset + 1; - struct btrfs_file_extent_item *extent; - int type; - u32 size; - struct btrfs_key new_key; - u64 disko = 0, diskl = 0; - u64 datao = 0, datal = 0; - u8 comp; - u64 drop_start; - - /* - * note the key will change type as we walk through the - * tree. - */ - path->leave_spinning = 1; - ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path, - 0, 0); - if (ret < 0) - goto out; - /* - * First search, if no extent item that starts at offset off was - * found but the previous item is an extent item, it's possible - * it might overlap our target range, therefore process it. - */ - if (key.offset == off && ret > 0 && path->slots[0] > 0) { - btrfs_item_key_to_cpu(path->nodes[0], &key, - path->slots[0] - 1); - if (key.type == BTRFS_EXTENT_DATA_KEY) - path->slots[0]--; - } - - nritems = btrfs_header_nritems(path->nodes[0]); -process_slot: - if (path->slots[0] >= nritems) { - ret = btrfs_next_leaf(BTRFS_I(src)->root, path); - if (ret < 0) - goto out; - if (ret > 0) - break; - nritems = btrfs_header_nritems(path->nodes[0]); - } - leaf = path->nodes[0]; - slot = path->slots[0]; - - btrfs_item_key_to_cpu(leaf, &key, slot); - if (key.type > BTRFS_EXTENT_DATA_KEY || - key.objectid != btrfs_ino(BTRFS_I(src))) - break; - - ASSERT(key.type == BTRFS_EXTENT_DATA_KEY); - - extent = btrfs_item_ptr(leaf, slot, - struct btrfs_file_extent_item); - comp = btrfs_file_extent_compression(leaf, extent); - type = btrfs_file_extent_type(leaf, extent); - if (type == BTRFS_FILE_EXTENT_REG || - type == BTRFS_FILE_EXTENT_PREALLOC) { - disko = btrfs_file_extent_disk_bytenr(leaf, extent); - diskl = btrfs_file_extent_disk_num_bytes(leaf, extent); - datao = btrfs_file_extent_offset(leaf, extent); - datal = btrfs_file_extent_num_bytes(leaf, extent); - } else if (type == BTRFS_FILE_EXTENT_INLINE) { - /* Take upper bound, may be compressed */ - datal = btrfs_file_extent_ram_bytes(leaf, extent); - } - - /* - * The first search might have left us at an extent item that - * ends before our target range's start, can happen if we have - * holes and NO_HOLES feature enabled. - */ - if (key.offset + datal <= off) { - path->slots[0]++; - goto process_slot; - } else if (key.offset >= off + len) { - break; - } - next_key_min_offset = key.offset + datal; - size = btrfs_item_size_nr(leaf, slot); - read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot), - size); - - btrfs_release_path(path); - path->leave_spinning = 0; - - memcpy(&new_key, &key, sizeof(new_key)); - new_key.objectid = btrfs_ino(BTRFS_I(inode)); - if (off <= key.offset) - new_key.offset = key.offset + destoff - off; - else - new_key.offset = destoff; - - /* - * Deal with a hole that doesn't have an extent item that - * represents it (NO_HOLES feature enabled). - * This hole is either in the middle of the cloning range or at - * the beginning (fully overlaps it or partially overlaps it). - */ - if (new_key.offset != last_dest_end) - drop_start = last_dest_end; - else - drop_start = new_key.offset; - - if (type == BTRFS_FILE_EXTENT_REG || - type == BTRFS_FILE_EXTENT_PREALLOC) { - struct btrfs_clone_extent_info clone_info; - - /* - * a | --- range to clone ---| b - * | ------------- extent ------------- | - */ - - /* Subtract range b */ - if (key.offset + datal > off + len) - datal = off + len - key.offset; - - /* Subtract range a */ - if (off > key.offset) { - datao += off - key.offset; - datal -= off - key.offset; - } - - clone_info.disk_offset = disko; - clone_info.disk_len = diskl; - clone_info.data_offset = datao; - clone_info.data_len = datal; - clone_info.file_offset = new_key.offset; - clone_info.extent_buf = buf; - clone_info.item_size = size; - ret = btrfs_punch_hole_range(inode, path, - drop_start, - new_key.offset + datal - 1, - &clone_info, &trans); - if (ret) - goto out; - } else if (type == BTRFS_FILE_EXTENT_INLINE) { - u64 skip = 0; - u64 trim = 0; - - if (off > key.offset) { - skip = off - key.offset; - new_key.offset += skip; - } - - if (key.offset + datal > off + len) - trim = key.offset + datal - (off + len); - - if (comp && (skip || trim)) { - ret = -EINVAL; - goto out; - } - size -= skip + trim; - datal -= skip + trim; - - /* - * If our extent is inline, we know we will drop or - * adjust at most 1 extent item in the destination root. - * - * 1 - adjusting old extent (we may have to split it) - * 1 - add new extent - * 1 - inode update - */ - trans = btrfs_start_transaction(root, 3); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - goto out; - } - - ret = clone_copy_inline_extent(inode, trans, path, - &new_key, drop_start, - datal, skip, size, buf); - if (ret) { - if (ret != -EOPNOTSUPP) - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - goto out; - } - } - - btrfs_release_path(path); - - last_dest_end = ALIGN(new_key.offset + datal, - fs_info->sectorsize); - ret = clone_finish_inode_update(trans, inode, last_dest_end, - destoff, olen, no_time_update); - if (ret) - goto out; - if (new_key.offset + datal >= destoff + len) - break; - - btrfs_release_path(path); - key.offset = next_key_min_offset; - - if (fatal_signal_pending(current)) { - ret = -EINTR; - goto out; - } - } - ret = 0; - - if (last_dest_end < destoff + len) { - /* - * We have an implicit hole that fully or partially overlaps our - * cloning range at its end. This means that we either have the - * NO_HOLES feature enabled or the implicit hole happened due to - * mixing buffered and direct IO writes against this file. - */ - btrfs_release_path(path); - path->leave_spinning = 0; - - ret = btrfs_punch_hole_range(inode, path, - last_dest_end, destoff + len - 1, - NULL, &trans); - if (ret) - goto out; - - ret = clone_finish_inode_update(trans, inode, destoff + len, - destoff, olen, no_time_update); - } - -out: - btrfs_free_path(path); - kvfree(buf); - return ret; -} - -static noinline int btrfs_clone_files(struct file *file, struct file *file_src, - u64 off, u64 olen, u64 destoff) -{ - struct inode *inode = file_inode(file); - struct inode *src = file_inode(file_src); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int ret; - u64 len = olen; - u64 bs = fs_info->sb->s_blocksize; - - /* - * TODO: - * - split compressed inline extents. annoying: we need to - * decompress into destination's address_space (the file offset - * may change, so source mapping won't do), then recompress (or - * otherwise reinsert) a subrange. - * - * - split destination inode's inline extents. The inline extents can - * be either compressed or non-compressed. - */ - - /* - * VFS's generic_remap_file_range_prep() protects us from cloning the - * eof block into the middle of a file, which would result in corruption - * if the file size is not blocksize aligned. So we don't need to check - * for that case here. - */ - if (off + len == src->i_size) - len = ALIGN(src->i_size, bs) - off; - - if (destoff > inode->i_size) { - const u64 wb_start = ALIGN_DOWN(inode->i_size, bs); - - ret = btrfs_cont_expand(inode, inode->i_size, destoff); - if (ret) - return ret; - /* - * We may have truncated the last block if the inode's size is - * not sector size aligned, so we need to wait for writeback to - * complete before proceeding further, otherwise we can race - * with cloning and attempt to increment a reference to an - * extent that no longer exists (writeback completed right after - * we found the previous extent covering eof and before we - * attempted to increment its reference count). - */ - ret = btrfs_wait_ordered_range(inode, wb_start, - destoff - wb_start); - if (ret) - return ret; - } - - /* - * Lock destination range to serialize with concurrent readpages() and - * source range to serialize with relocation. - */ - btrfs_double_extent_lock(src, off, inode, destoff, len); - ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); - btrfs_double_extent_unlock(src, off, inode, destoff, len); - /* - * Truncate page cache pages so that future reads will see the cloned - * data immediately and not the previous data. - */ - truncate_inode_pages_range(&inode->i_data, - round_down(destoff, PAGE_SIZE), - round_up(destoff + len, PAGE_SIZE) - 1); - - return ret; -} - -static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *len, unsigned int remap_flags) -{ - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); - u64 bs = BTRFS_I(inode_out)->root->fs_info->sb->s_blocksize; - bool same_inode = inode_out == inode_in; - u64 wb_len; - int ret; - - if (!(remap_flags & REMAP_FILE_DEDUP)) { - struct btrfs_root *root_out = BTRFS_I(inode_out)->root; - - if (btrfs_root_readonly(root_out)) - return -EROFS; - - if (file_in->f_path.mnt != file_out->f_path.mnt || - inode_in->i_sb != inode_out->i_sb) - return -EXDEV; - } - - /* don't make the dst file partly checksummed */ - if ((BTRFS_I(inode_in)->flags & BTRFS_INODE_NODATASUM) != - (BTRFS_I(inode_out)->flags & BTRFS_INODE_NODATASUM)) { - return -EINVAL; - } - - /* - * Now that the inodes are locked, we need to start writeback ourselves - * and can not rely on the writeback from the VFS's generic helper - * generic_remap_file_range_prep() because: - * - * 1) For compression we must call filemap_fdatawrite_range() range - * twice (btrfs_fdatawrite_range() does it for us), and the generic - * helper only calls it once; - * - * 2) filemap_fdatawrite_range(), called by the generic helper only - * waits for the writeback to complete, i.e. for IO to be done, and - * not for the ordered extents to complete. We need to wait for them - * to complete so that new file extent items are in the fs tree. - */ - if (*len == 0 && !(remap_flags & REMAP_FILE_DEDUP)) - wb_len = ALIGN(inode_in->i_size, bs) - ALIGN_DOWN(pos_in, bs); - else - wb_len = ALIGN(*len, bs); - - /* - * Since we don't lock ranges, wait for ongoing lockless dio writes (as - * any in progress could create its ordered extents after we wait for - * existing ordered extents below). - */ - inode_dio_wait(inode_in); - if (!same_inode) - inode_dio_wait(inode_out); - - /* - * Workaround to make sure NOCOW buffered write reach disk as NOCOW. - * - * Btrfs' back references do not have a block level granularity, they - * work at the whole extent level. - * NOCOW buffered write without data space reserved may not be able - * to fall back to CoW due to lack of data space, thus could cause - * data loss. - * - * Here we take a shortcut by flushing the whole inode, so that all - * nocow write should reach disk as nocow before we increase the - * reference of the extent. We could do better by only flushing NOCOW - * data, but that needs extra accounting. - * - * Also we don't need to check ASYNC_EXTENT, as async extent will be - * CoWed anyway, not affecting nocow part. - */ - ret = filemap_flush(inode_in->i_mapping); - if (ret < 0) - return ret; - - ret = btrfs_wait_ordered_range(inode_in, ALIGN_DOWN(pos_in, bs), - wb_len); - if (ret < 0) - return ret; - ret = btrfs_wait_ordered_range(inode_out, ALIGN_DOWN(pos_out, bs), - wb_len); - if (ret < 0) - return ret; - - return generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - len, remap_flags); -} - -loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, loff_t len, - unsigned int remap_flags) -{ - struct inode *src_inode = file_inode(src_file); - struct inode *dst_inode = file_inode(dst_file); - bool same_inode = dst_inode == src_inode; - int ret; - - if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) - return -EINVAL; - - if (same_inode) - inode_lock(src_inode); - else - lock_two_nondirectories(src_inode, dst_inode); - - ret = btrfs_remap_file_range_prep(src_file, off, dst_file, destoff, - &len, remap_flags); - if (ret < 0 || len == 0) - goto out_unlock; - - if (remap_flags & REMAP_FILE_DEDUP) - ret = btrfs_extent_same(src_inode, off, len, dst_inode, destoff); - else - ret = btrfs_clone_files(dst_file, src_file, off, len, destoff); - -out_unlock: - if (same_inode) - inode_unlock(src_inode); - else - unlock_two_nondirectories(src_inode, dst_inode); - - return ret < 0 ? ret : len; -} - static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) { struct inode *inode = file_inode(file); @@ -3955,8 +3772,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) struct btrfs_root *new_root; struct btrfs_dir_item *di; struct btrfs_trans_handle *trans; - struct btrfs_path *path; - struct btrfs_key location; + struct btrfs_path *path = NULL; struct btrfs_disk_key disk_key; u64 objectid = 0; u64 dir_id; @@ -3977,53 +3793,50 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) if (!objectid) objectid = BTRFS_FS_TREE_OBJECTID; - location.objectid = objectid; - location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = (u64)-1; - - new_root = btrfs_read_fs_root_no_name(fs_info, &location); + new_root = btrfs_get_fs_root(fs_info, objectid, true); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); goto out; } if (!is_fstree(new_root->root_key.objectid)) { ret = -ENOENT; - goto out; + goto out_free; } path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto out; + goto out_free; } - path->leave_spinning = 1; trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { - btrfs_free_path(path); ret = PTR_ERR(trans); - goto out; + goto out_free; } 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); if (IS_ERR_OR_NULL(di)) { - btrfs_free_path(path); + btrfs_release_path(path); btrfs_end_transaction(trans); btrfs_err(fs_info, "Umm, you don't have the default diritem, this isn't going to work"); ret = -ENOENT; - goto out; + goto out_free; } btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key); btrfs_set_dir_item_key(path->nodes[0], di, &disk_key); btrfs_mark_buffer_dirty(path->nodes[0]); - btrfs_free_path(path); + btrfs_release_path(path); btrfs_set_fs_incompat(fs_info, DEFAULT_SUBVOL); btrfs_end_transaction(trans); +out_free: + btrfs_put_root(new_root); + btrfs_free_path(path); out: mnt_drop_write_file(file); return ret; @@ -4074,15 +3887,12 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, struct btrfs_space_info *tmp; info = NULL; - rcu_read_lock(); - list_for_each_entry_rcu(tmp, &fs_info->space_info, - list) { + list_for_each_entry(tmp, &fs_info->space_info, list) { if (tmp->flags == types[i]) { info = tmp; break; } } - rcu_read_unlock(); if (!info) continue; @@ -4130,15 +3940,12 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, break; info = NULL; - rcu_read_lock(); - list_for_each_entry_rcu(tmp, &fs_info->space_info, - list) { + list_for_each_entry(tmp, &fs_info->space_info, list) { if (tmp->flags == types[i]) { info = tmp; break; } } - rcu_read_unlock(); if (!info) continue; @@ -4192,7 +3999,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root, { struct btrfs_trans_handle *trans; u64 transid; - int ret; trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { @@ -4204,11 +4010,7 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root, goto out; } transid = trans->transid; - ret = btrfs_commit_transaction_async(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } + btrfs_commit_transaction_async(trans); out: if (argp) if (copy_to_user(argp, &transid, sizeof(transid))) @@ -4239,6 +4041,11 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { + btrfs_err(fs_info, "scrub is not supported on extent tree v2 yet"); + return -EINVAL; + } + sa = memdup_user(arg, sizeof(*sa)); if (IS_ERR(sa)) return PTR_ERR(sa); @@ -4338,6 +4145,11 @@ 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); @@ -4348,11 +4160,11 @@ static long btrfs_ioctl_dev_replace(struct btrfs_fs_info *fs_info, ret = -EROFS; goto out; } - if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) { + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REPLACE)) { ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; } else { ret = btrfs_dev_replace_by_ioctl(fs_info, p); - clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); + btrfs_exclop_finish(fs_info); } break; case BTRFS_IOCTL_DEV_REPLACE_CMD_STATUS: @@ -4434,26 +4246,6 @@ out: 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) { @@ -4503,7 +4295,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, } ret = iterate_inodes_from_logical(loi->logical, fs_info, path, - build_ino_list, inodes, ignore_offset); + inodes, ignore_offset); if (ret == -EINVAL) ret = -ENOENT; if (ret < 0) @@ -4546,13 +4338,79 @@ 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 (!capable(CAP_SYS_ADMIN)) @@ -4562,133 +4420,80 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) if (ret) return ret; -again: - if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) { - 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: - BUG_ON(!test_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)); + 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); + 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 filesystem flag BTRFS_FS_EXCL_OP goes to - * btrfs_balance. bctl is freed in reset_balance_state, or, if - * restriper was paused all the way until unmount, in free_fs_info. - * The flag should be cleared after reset_balance_state. + * Ownership of bctl and exclusive operation goes to btrfs_balance. + * bctl is freed in reset_balance_state, or, if restriper was paused + * all the way until unmount, in free_fs_info. The flag should be + * cleared after reset_balance_state. */ need_unlock = false; ret = btrfs_balance(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) - clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); + btrfs_exclop_finish(fs_info); out: mnt_drop_write_file(file); + kfree(bargs); return ret; } @@ -4966,26 +4771,20 @@ drop_write: static long btrfs_ioctl_quota_rescan_status(struct btrfs_fs_info *fs_info, void __user *arg) { - struct btrfs_ioctl_quota_rescan_args *qsa; - int ret = 0; + struct btrfs_ioctl_quota_rescan_args qsa = {0}; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - qsa = kzalloc(sizeof(*qsa), GFP_KERNEL); - if (!qsa) - return -ENOMEM; - if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { - qsa->flags = 1; - qsa->progress = fs_info->qgroup_rescan_progress.objectid; + qsa.flags = 1; + qsa.progress = fs_info->qgroup_rescan_progress.objectid; } - if (copy_to_user(arg, qsa, sizeof(*qsa))) - ret = -EFAULT; + if (copy_to_user(arg, &qsa, sizeof(qsa))) + return -EFAULT; - kfree(qsa); - return ret; + return 0; } static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info, @@ -4998,6 +4797,7 @@ 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 btrfs_ioctl_received_subvol_args *sa) { struct inode *inode = file_inode(file); @@ -5009,7 +4809,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, int ret = 0; int received_uuid_changed; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -5114,7 +4914,7 @@ 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, args64); + ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_user_ns(file), args64); if (ret) goto out; @@ -5148,7 +4948,7 @@ 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, sa); + ret = _btrfs_ioctl_set_received_subvol(file, file_mnt_user_ns(file), sa); if (ret) goto out; @@ -5400,7 +5200,7 @@ out_drop_write: return ret; } -static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat) +static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat) { struct btrfs_ioctl_send_args *arg; int ret; @@ -5430,11 +5230,194 @@ 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(inode, 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 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 (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(READ, 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); + 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(WRITE, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), + &iov, &iter); + if (ret < 0) + goto out_acct; + + file_start_write(file); + + if (iov_iter_count(&iter) == 0) { + ret = 0; + goto out_end_write; + } + pos = args.offset; + ret = rw_verify_area(WRITE, file, &pos, args.len); + if (ret < 0) + goto out_end_write; + + init_sync_kiocb(&kiocb, file); + ret = kiocb_set_rw_flags(&kiocb, 0); + if (ret) + goto out_end_write; + kiocb.ki_pos = pos; + + ret = btrfs_do_write_iter(&kiocb, &iter, &args); + if (ret > 0) + fsnotify_modify(file); + +out_end_write: + file_end_write(file); + kfree(iov); +out_acct: + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -5444,12 +5427,8 @@ long btrfs_ioctl(struct file *file, unsigned int void __user *argp = (void __user *)arg; switch (cmd) { - case FS_IOC_GETFLAGS: - return btrfs_ioctl_getflags(file, argp); - case FS_IOC_SETFLAGS: - return btrfs_ioctl_setflags(file, argp); case FS_IOC_GETVERSION: - return btrfs_ioctl_getversion(file, argp); + return btrfs_ioctl_getversion(inode, argp); case FS_IOC_GETFSLABEL: return btrfs_ioctl_get_fslabel(fs_info, argp); case FS_IOC_SETFSLABEL: @@ -5465,9 +5444,11 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SUBVOL_CREATE_V2: return btrfs_ioctl_snap_create_v2(file, argp, 1); case BTRFS_IOC_SNAP_DESTROY: - return btrfs_ioctl_snap_destroy(file, argp); + 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(inode, argp); case BTRFS_IOC_SUBVOL_SETFLAGS: return btrfs_ioctl_subvol_setflags(file, argp); case BTRFS_IOC_DEFAULT_SUBVOL: @@ -5488,14 +5469,12 @@ 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(inode, argp); case BTRFS_IOC_TREE_SEARCH_V2: - return btrfs_ioctl_tree_search_v2(file, argp); + return btrfs_ioctl_tree_search_v2(inode, 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: @@ -5507,7 +5486,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: { int ret; - ret = btrfs_start_delalloc_roots(fs_info, -1); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) return ret; ret = btrfs_sync_fs(inode->i_sb, 1); @@ -5542,10 +5521,10 @@ 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(inode, 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(inode, argp, true); #endif case BTRFS_IOC_GET_DEV_STATS: return btrfs_ioctl_get_dev_stats(fs_info, argp); @@ -5571,16 +5550,26 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_get_features(fs_info, argp); case BTRFS_IOC_SET_FEATURES: return btrfs_ioctl_set_features(file, argp); - case FS_IOC_FSGETXATTR: - return btrfs_ioctl_fsgetxattr(file, argp); - case FS_IOC_FSSETXATTR: - return btrfs_ioctl_fssetxattr(file, argp); 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 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 } return -ENOTTY; @@ -5594,12 +5583,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) * handling is necessary. */ switch (cmd) { - case FS_IOC32_GETFLAGS: - cmd = FS_IOC_GETFLAGS; - break; - case FS_IOC32_SETFLAGS: - cmd = FS_IOC_SETFLAGS; - break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; |