--- zzzz-none-000/linux-3.10.107/fs/btrfs/super.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/fs/btrfs/super.c 2021-02-04 17:41:59.000000000 +0000 @@ -42,29 +42,34 @@ #include #include #include -#include "compat.h" #include "delayed-inode.h" #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "btrfs_inode.h" #include "print-tree.h" +#include "hash.h" +#include "props.h" #include "xattr.h" #include "volumes.h" -#include "version.h" #include "export.h" #include "compression.h" #include "rcu-string.h" #include "dev-replace.h" #include "free-space-cache.h" +#include "backref.h" +#include "tests/btrfs-tests.h" +#include "qgroup.h" #define CREATE_TRACE_POINTS #include static const struct super_operations btrfs_super_ops; static struct file_system_type btrfs_fs_type; -static const char *btrfs_decode_error(int errno) +static int btrfs_remount(struct super_block *sb, int *flags, char *data); + +const char *btrfs_decode_error(int errno) { char *errstr = "unknown"; @@ -125,16 +130,18 @@ } } -#ifdef CONFIG_PRINTK /* * __btrfs_std_error decodes expected errors from the caller and * invokes the approciate error response. */ +__cold void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...) { struct super_block *sb = fs_info->sb; +#ifdef CONFIG_PRINTK const char *errstr; +#endif /* * Special case: if the error is EROFS, and we're already @@ -143,6 +150,7 @@ if (errno == -EROFS && (sb->s_flags & MS_RDONLY)) return; +#ifdef CONFIG_PRINTK errstr = btrfs_decode_error(errno); if (fmt) { struct va_format vaf; @@ -152,13 +160,15 @@ vaf.fmt = fmt; vaf.va = &args; - printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: errno=%d %s (%pV)\n", + printk(KERN_CRIT + "BTRFS: error (device %s) in %s:%d: errno=%d %s (%pV)\n", sb->s_id, function, line, errno, errstr, &vaf); va_end(args); } else { - printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: errno=%d %s\n", + printk(KERN_CRIT "BTRFS: error (device %s) in %s:%d: errno=%d %s\n", sb->s_id, function, line, errno, errstr); } +#endif /* Don't go through full error handling during mount */ save_error_info(fs_info); @@ -166,6 +176,7 @@ btrfs_handle_error(fs_info); } +#ifdef CONFIG_PRINTK static const char * const logtypes[] = { "emergency", "alert", @@ -205,27 +216,6 @@ va_end(args); } - -#else - -void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, - unsigned int line, int errno, const char *fmt, ...) -{ - struct super_block *sb = fs_info->sb; - - /* - * Special case: if the error is EROFS, and we're already - * under MS_RDONLY, then it is safe here. - */ - if (errno == -EROFS && (sb->s_flags & MS_RDONLY)) - return; - - /* Don't go through full error handling during mount */ - if (sb->s_flags & MS_BORN) { - save_error_info(fs_info); - btrfs_handle_error(fs_info); - } -} #endif /* @@ -241,22 +231,15 @@ * We'll complete the cleanup in btrfs_end_transaction and * btrfs_commit_transaction. */ +__cold void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *function, unsigned int line, int errno) { - /* - * Report first abort since mount - */ - if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, - &root->fs_info->fs_state)) { - WARN(1, KERN_DEBUG "btrfs: Transaction aborted (error %d)\n", - errno); - } trans->aborted = errno; /* Nothing used. The other threads that have joined this * transaction may be able to continue. */ - if (!trans->blocks_used) { + if (!trans->dirty && list_empty(&trans->new_bgs)) { const char *errstr; errstr = btrfs_decode_error(errno); @@ -266,12 +249,16 @@ return; } ACCESS_ONCE(trans->transaction->aborted) = errno; + /* Wake up anybody who may be waiting on this transaction */ + wake_up(&root->fs_info->transaction_wait); + wake_up(&root->fs_info->transaction_blocked_wait); __btrfs_std_error(root->fs_info, function, line, errno, NULL); } /* * __btrfs_panic decodes unexpected, fatal errors from the caller, * issues an alert, and either panics or BUGs, depending on mount options. */ +__cold void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...) { @@ -291,21 +278,15 @@ panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n", s_id, function, line, &vaf, errno, errstr); - printk(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n", - s_id, function, line, &vaf, errno, errstr); + btrfs_crit(fs_info, "panic in %s:%d: %pV (errno=%d %s)", + function, line, &vaf, errno, errstr); va_end(args); /* Caller calls BUG() */ } static void btrfs_put_super(struct super_block *sb) { - (void)close_ctree(btrfs_sb(sb)->tree_root); - /* FIXME: need to fix VFS to return error? */ - /* AV: return it _where_? ->put_super() can be triggered by any number - * of async events, up to and including delivery of SIGKILL to the - * last process that kept it busy. Or segfault in the aforementioned - * process... Whom would you report that to? - */ + close_ctree(btrfs_sb(sb)->tree_root); } enum { @@ -318,18 +299,27 @@ Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_skip_balance, Opt_check_integrity, Opt_check_integrity_including_extent_data, - Opt_check_integrity_print_mask, Opt_fatal_errors, + Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree, + Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard, + Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow, + Opt_datasum, Opt_treelog, Opt_noinode_cache, +#ifdef CONFIG_BTRFS_DEBUG + Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all, +#endif Opt_err, }; static match_table_t tokens = { {Opt_degraded, "degraded"}, {Opt_subvol, "subvol=%s"}, - {Opt_subvolid, "subvolid=%d"}, + {Opt_subvolid, "subvolid=%s"}, {Opt_device, "device=%s"}, {Opt_nodatasum, "nodatasum"}, + {Opt_datasum, "datasum"}, {Opt_nodatacow, "nodatacow"}, + {Opt_datacow, "datacow"}, {Opt_nobarrier, "nobarrier"}, + {Opt_barrier, "barrier"}, {Opt_max_inline, "max_inline=%s"}, {Opt_alloc_start, "alloc_start=%s"}, {Opt_thread_pool, "thread_pool=%d"}, @@ -340,25 +330,39 @@ {Opt_ssd, "ssd"}, {Opt_ssd_spread, "ssd_spread"}, {Opt_nossd, "nossd"}, + {Opt_acl, "acl"}, {Opt_noacl, "noacl"}, {Opt_notreelog, "notreelog"}, + {Opt_treelog, "treelog"}, {Opt_flushoncommit, "flushoncommit"}, + {Opt_noflushoncommit, "noflushoncommit"}, {Opt_ratio, "metadata_ratio=%d"}, {Opt_discard, "discard"}, + {Opt_nodiscard, "nodiscard"}, {Opt_space_cache, "space_cache"}, {Opt_clear_cache, "clear_cache"}, {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, {Opt_enospc_debug, "enospc_debug"}, + {Opt_noenospc_debug, "noenospc_debug"}, {Opt_subvolrootid, "subvolrootid=%d"}, {Opt_defrag, "autodefrag"}, + {Opt_nodefrag, "noautodefrag"}, {Opt_inode_cache, "inode_cache"}, + {Opt_noinode_cache, "noinode_cache"}, {Opt_no_space_cache, "nospace_cache"}, {Opt_recovery, "recovery"}, {Opt_skip_balance, "skip_balance"}, {Opt_check_integrity, "check_int"}, {Opt_check_integrity_including_extent_data, "check_int_data"}, {Opt_check_integrity_print_mask, "check_int_print_mask=%d"}, + {Opt_rescan_uuid_tree, "rescan_uuid_tree"}, {Opt_fatal_errors, "fatal_errors=%s"}, + {Opt_commit_interval, "commit=%d"}, +#ifdef CONFIG_BTRFS_DEBUG + {Opt_fragment_data, "fragment=data"}, + {Opt_fragment_metadata, "fragment=metadata"}, + {Opt_fragment_all, "fragment=all"}, +#endif {Opt_err, NULL}, }; @@ -403,7 +407,7 @@ token = match_token(p, tokens, args); switch (token) { case Opt_degraded: - printk(KERN_INFO "btrfs: allowing degraded mounts\n"); + btrfs_info(root->fs_info, "allowing degraded mounts"); btrfs_set_opt(info->mount_opt, DEGRADED); break; case Opt_subvol: @@ -416,22 +420,38 @@ */ break; case Opt_nodatasum: - printk(KERN_INFO "btrfs: setting nodatasum\n"); - btrfs_set_opt(info->mount_opt, NODATASUM); + btrfs_set_and_info(root, NODATASUM, + "setting nodatasum"); + break; + case Opt_datasum: + if (btrfs_test_opt(root, NODATASUM)) { + if (btrfs_test_opt(root, NODATACOW)) + btrfs_info(root->fs_info, "setting datasum, datacow enabled"); + else + btrfs_info(root->fs_info, "setting datasum"); + } + btrfs_clear_opt(info->mount_opt, NODATACOW); + btrfs_clear_opt(info->mount_opt, NODATASUM); break; case Opt_nodatacow: - if (!btrfs_test_opt(root, COMPRESS) || - !btrfs_test_opt(root, FORCE_COMPRESS)) { - printk(KERN_INFO "btrfs: setting nodatacow, compression disabled\n"); - } else { - printk(KERN_INFO "btrfs: setting nodatacow\n"); + if (!btrfs_test_opt(root, NODATACOW)) { + if (!btrfs_test_opt(root, COMPRESS) || + !btrfs_test_opt(root, FORCE_COMPRESS)) { + btrfs_info(root->fs_info, + "setting nodatacow, compression disabled"); + } else { + btrfs_info(root->fs_info, "setting nodatacow"); + } } - info->compress_type = BTRFS_COMPRESS_NONE; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); btrfs_set_opt(info->mount_opt, NODATACOW); btrfs_set_opt(info->mount_opt, NODATASUM); break; + case Opt_datacow: + btrfs_clear_and_info(root, NODATACOW, + "setting datacow"); + break; case Opt_compress_force: case Opt_compress_force_type: compress_force = true; @@ -455,7 +475,6 @@ btrfs_set_fs_incompat(info, COMPRESS_LZO); } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; - info->compress_type = BTRFS_COMPRESS_NONE; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); compress_force = false; @@ -465,39 +484,55 @@ } if (compress_force) { - btrfs_set_opt(info->mount_opt, FORCE_COMPRESS); - pr_info("btrfs: force %s compression\n", - compress_type); - } else - pr_info("btrfs: use %s compression\n", - compress_type); + btrfs_set_and_info(root, FORCE_COMPRESS, + "force %s compression", + compress_type); + } else { + if (!btrfs_test_opt(root, COMPRESS)) + btrfs_info(root->fs_info, + "btrfs: use %s compression", + compress_type); + /* + * If we remount from compress-force=xxx to + * compress=xxx, we need clear FORCE_COMPRESS + * flag, otherwise, there is no way for users + * to disable forcible compression separately. + */ + btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); + } break; case Opt_ssd: - printk(KERN_INFO "btrfs: use ssd allocation scheme\n"); - btrfs_set_opt(info->mount_opt, SSD); + btrfs_set_and_info(root, SSD, + "use ssd allocation scheme"); break; case Opt_ssd_spread: - printk(KERN_INFO "btrfs: use spread ssd " - "allocation scheme\n"); + btrfs_set_and_info(root, SSD_SPREAD, + "use spread ssd allocation scheme"); btrfs_set_opt(info->mount_opt, SSD); - btrfs_set_opt(info->mount_opt, SSD_SPREAD); break; case Opt_nossd: - printk(KERN_INFO "btrfs: not using ssd allocation " - "scheme\n"); - btrfs_set_opt(info->mount_opt, NOSSD); + btrfs_set_and_info(root, NOSSD, + "not using ssd allocation scheme"); btrfs_clear_opt(info->mount_opt, SSD); - btrfs_clear_opt(info->mount_opt, SSD_SPREAD); + break; + case Opt_barrier: + btrfs_clear_and_info(root, NOBARRIER, + "turning on barriers"); break; case Opt_nobarrier: - printk(KERN_INFO "btrfs: turning off barriers\n"); - btrfs_set_opt(info->mount_opt, NOBARRIER); + btrfs_set_and_info(root, NOBARRIER, + "turning off barriers"); break; case Opt_thread_pool: - intarg = 0; - match_int(&args[0], &intarg); - if (intarg) + ret = match_int(&args[0], &intarg); + if (ret) { + goto out; + } else if (intarg > 0) { info->thread_pool_size = intarg; + } else { + ret = -EINVAL; + goto out; + } break; case Opt_max_inline: num = match_strdup(&args[0]); @@ -506,12 +541,15 @@ kfree(num); if (info->max_inline) { - info->max_inline = max_t(u64, + info->max_inline = min_t(u64, info->max_inline, root->sectorsize); } - printk(KERN_INFO "btrfs: max_inline at %llu\n", - (unsigned long long)info->max_inline); + btrfs_info(root->fs_info, "max_inline at %llu", + info->max_inline); + } else { + ret = -ENOMEM; + goto out; } break; case Opt_alloc_start: @@ -521,48 +559,85 @@ info->alloc_start = memparse(num, NULL); mutex_unlock(&info->chunk_mutex); kfree(num); - printk(KERN_INFO - "btrfs: allocations start at %llu\n", - (unsigned long long)info->alloc_start); + btrfs_info(root->fs_info, "allocations start at %llu", + info->alloc_start); + } else { + ret = -ENOMEM; + goto out; } break; + case Opt_acl: +#ifdef CONFIG_BTRFS_FS_POSIX_ACL + root->fs_info->sb->s_flags |= MS_POSIXACL; + break; +#else + btrfs_err(root->fs_info, + "support for ACL not compiled in!"); + ret = -EINVAL; + goto out; +#endif case Opt_noacl: root->fs_info->sb->s_flags &= ~MS_POSIXACL; break; case Opt_notreelog: - printk(KERN_INFO "btrfs: disabling tree log\n"); - btrfs_set_opt(info->mount_opt, NOTREELOG); + btrfs_set_and_info(root, NOTREELOG, + "disabling tree log"); + break; + case Opt_treelog: + btrfs_clear_and_info(root, NOTREELOG, + "enabling tree log"); break; case Opt_flushoncommit: - printk(KERN_INFO "btrfs: turning on flush-on-commit\n"); - btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT); + btrfs_set_and_info(root, FLUSHONCOMMIT, + "turning on flush-on-commit"); + break; + case Opt_noflushoncommit: + btrfs_clear_and_info(root, FLUSHONCOMMIT, + "turning off flush-on-commit"); break; case Opt_ratio: - intarg = 0; - match_int(&args[0], &intarg); - if (intarg) { + ret = match_int(&args[0], &intarg); + if (ret) { + goto out; + } else if (intarg >= 0) { info->metadata_ratio = intarg; - printk(KERN_INFO "btrfs: metadata ratio %d\n", + btrfs_info(root->fs_info, "metadata ratio %d", info->metadata_ratio); + } else { + ret = -EINVAL; + goto out; } break; case Opt_discard: - btrfs_set_opt(info->mount_opt, DISCARD); + btrfs_set_and_info(root, DISCARD, + "turning on discard"); + break; + case Opt_nodiscard: + btrfs_clear_and_info(root, DISCARD, + "turning off discard"); break; case Opt_space_cache: - btrfs_set_opt(info->mount_opt, SPACE_CACHE); + btrfs_set_and_info(root, SPACE_CACHE, + "enabling disk space caching"); + break; + case Opt_rescan_uuid_tree: + btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE); break; case Opt_no_space_cache: - printk(KERN_INFO "btrfs: disabling disk space caching\n"); - btrfs_clear_opt(info->mount_opt, SPACE_CACHE); + btrfs_clear_and_info(root, SPACE_CACHE, + "disabling disk space caching"); break; case Opt_inode_cache: - printk(KERN_INFO "btrfs: enabling inode map caching\n"); - btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE); + btrfs_set_pending_and_info(info, INODE_MAP_CACHE, + "enabling inode map caching"); + break; + case Opt_noinode_cache: + btrfs_clear_pending_and_info(info, INODE_MAP_CACHE, + "disabling inode map caching"); break; case Opt_clear_cache: - printk(KERN_INFO "btrfs: force clearing of disk cache\n"); - btrfs_set_opt(info->mount_opt, CLEAR_CACHE); + btrfs_set_and_info(root, CLEAR_CACHE, + "force clearing of disk cache"); break; case Opt_user_subvol_rm_allowed: btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED); @@ -570,12 +645,19 @@ case Opt_enospc_debug: btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG); break; + case Opt_noenospc_debug: + btrfs_clear_opt(info->mount_opt, ENOSPC_DEBUG); + break; case Opt_defrag: - printk(KERN_INFO "btrfs: enabling auto defrag\n"); - btrfs_set_opt(info->mount_opt, AUTO_DEFRAG); + btrfs_set_and_info(root, AUTO_DEFRAG, + "enabling auto defrag"); + break; + case Opt_nodefrag: + btrfs_clear_and_info(root, AUTO_DEFRAG, + "disabling auto defrag"); break; case Opt_recovery: - printk(KERN_INFO "btrfs: enabling auto recovery\n"); + btrfs_info(root->fs_info, "enabling auto recovery"); btrfs_set_opt(info->mount_opt, RECOVERY); break; case Opt_skip_balance: @@ -583,32 +665,35 @@ break; #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY case Opt_check_integrity_including_extent_data: - printk(KERN_INFO "btrfs: enabling check integrity" - " including extent data\n"); + btrfs_info(root->fs_info, + "enabling check integrity including extent data"); btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA); btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); break; case Opt_check_integrity: - printk(KERN_INFO "btrfs: enabling check integrity\n"); + btrfs_info(root->fs_info, "enabling check integrity"); btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); break; case Opt_check_integrity_print_mask: - intarg = 0; - match_int(&args[0], &intarg); - if (intarg) { + ret = match_int(&args[0], &intarg); + if (ret) { + goto out; + } else if (intarg >= 0) { info->check_integrity_print_mask = intarg; - printk(KERN_INFO "btrfs:" - " check_integrity_print_mask 0x%x\n", + btrfs_info(root->fs_info, "check_integrity_print_mask 0x%x", info->check_integrity_print_mask); + } else { + ret = -EINVAL; + goto out; } break; #else case Opt_check_integrity_including_extent_data: case Opt_check_integrity: case Opt_check_integrity_print_mask: - printk(KERN_ERR "btrfs: support for check_integrity*" - " not compiled in!\n"); + btrfs_err(root->fs_info, + "support for check_integrity* not compiled in!"); ret = -EINVAL; goto out; #endif @@ -624,9 +709,44 @@ goto out; } break; + case Opt_commit_interval: + intarg = 0; + ret = match_int(&args[0], &intarg); + if (ret < 0) { + btrfs_err(root->fs_info, "invalid commit interval"); + ret = -EINVAL; + goto out; + } + if (intarg > 0) { + if (intarg > 300) { + btrfs_warn(root->fs_info, "excessive commit interval %d", + intarg); + } + info->commit_interval = intarg; + } else { + btrfs_info(root->fs_info, "using default commit interval %ds", + BTRFS_DEFAULT_COMMIT_INTERVAL); + info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; + } + break; +#ifdef CONFIG_BTRFS_DEBUG + case Opt_fragment_all: + btrfs_info(root->fs_info, "fragmenting all space"); + btrfs_set_opt(info->mount_opt, FRAGMENT_DATA); + btrfs_set_opt(info->mount_opt, FRAGMENT_METADATA); + break; + case Opt_fragment_metadata: + btrfs_info(root->fs_info, "fragmenting metadata"); + btrfs_set_opt(info->mount_opt, + FRAGMENT_METADATA); + break; + case Opt_fragment_data: + btrfs_info(root->fs_info, "fragmenting data"); + btrfs_set_opt(info->mount_opt, FRAGMENT_DATA); + break; +#endif case Opt_err: - printk(KERN_INFO "btrfs: unrecognized mount option " - "'%s'\n", p); + btrfs_info(root->fs_info, "unrecognized mount option '%s'", p); ret = -EINVAL; goto out; default: @@ -635,7 +755,7 @@ } out: if (!ret && btrfs_test_opt(root, SPACE_CACHE)) - printk(KERN_INFO "btrfs: disk space caching is enabled\n"); + btrfs_info(root->fs_info, "disk space caching is enabled"); kfree(orig); return ret; } @@ -652,8 +772,8 @@ { substring_t args[MAX_OPT_ARGS]; char *device_name, *opts, *orig, *p; + char *num = NULL; int error = 0; - int intarg; if (!options) return 0; @@ -677,22 +797,29 @@ case Opt_subvol: kfree(*subvol_name); *subvol_name = match_strdup(&args[0]); + if (!*subvol_name) { + error = -ENOMEM; + goto out; + } break; case Opt_subvolid: - intarg = 0; - error = match_int(&args[0], &intarg); - if (!error) { + num = match_strdup(&args[0]); + if (num) { + *subvol_objectid = memparse(num, NULL); + kfree(num); /* we want the original fs_tree */ - if (!intarg) + if (!*subvol_objectid) *subvol_objectid = BTRFS_FS_TREE_OBJECTID; - else - *subvol_objectid = intarg; + } else { + error = -EINVAL; + goto out; } break; case Opt_subvolrootid: printk(KERN_WARNING - "btrfs: 'subvolrootid' mount option is deprecated and has no effect\n"); + "BTRFS: 'subvolrootid' mount option is deprecated and has " + "no effect\n"); break; case Opt_device: device_name = match_strdup(&args[0]); @@ -716,33 +843,153 @@ return error; } -static struct dentry *get_default_root(struct super_block *sb, - u64 subvol_objectid) +static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, + u64 subvol_objectid) { - struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root = fs_info->tree_root; - struct btrfs_root *new_root; - struct btrfs_dir_item *di; - struct btrfs_path *path; - struct btrfs_key location; - struct inode *inode; - u64 dir_id; - int new = 0; + struct btrfs_root *fs_root; + struct btrfs_root_ref *root_ref; + struct btrfs_inode_ref *inode_ref; + struct btrfs_key key; + struct btrfs_path *path = NULL; + char *name = NULL, *ptr; + u64 dirid; + int len; + int ret; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto err; + } + path->leave_spinning = 1; + + name = kmalloc(PATH_MAX, GFP_NOFS); + if (!name) { + ret = -ENOMEM; + goto err; + } + ptr = name + PATH_MAX - 1; + ptr[0] = '\0'; /* - * We have a specific subvol we want to mount, just setup location and - * go look up the root. + * Walk up the subvolume trees in the tree of tree roots by root + * backrefs until we hit the top-level subvolume. */ - if (subvol_objectid) { - location.objectid = subvol_objectid; - location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = (u64)-1; - goto find_root; + while (subvol_objectid != BTRFS_FS_TREE_OBJECTID) { + key.objectid = subvol_objectid; + key.type = BTRFS_ROOT_BACKREF_KEY; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + goto err; + } else if (ret > 0) { + ret = btrfs_previous_item(root, path, subvol_objectid, + BTRFS_ROOT_BACKREF_KEY); + if (ret < 0) { + goto err; + } else if (ret > 0) { + ret = -ENOENT; + goto err; + } + } + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + subvol_objectid = key.offset; + + root_ref = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_root_ref); + len = btrfs_root_ref_name_len(path->nodes[0], root_ref); + ptr -= len + 1; + if (ptr < name) { + ret = -ENAMETOOLONG; + goto err; + } + read_extent_buffer(path->nodes[0], ptr + 1, + (unsigned long)(root_ref + 1), len); + ptr[0] = '/'; + dirid = btrfs_root_ref_dirid(path->nodes[0], root_ref); + btrfs_release_path(path); + + key.objectid = subvol_objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + fs_root = btrfs_read_fs_root_no_name(fs_info, &key); + if (IS_ERR(fs_root)) { + ret = PTR_ERR(fs_root); + goto err; + } + + /* + * Walk up the filesystem tree by inode refs until we hit the + * root directory. + */ + while (dirid != BTRFS_FIRST_FREE_OBJECTID) { + key.objectid = dirid; + key.type = BTRFS_INODE_REF_KEY; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); + if (ret < 0) { + goto err; + } else if (ret > 0) { + ret = btrfs_previous_item(fs_root, path, dirid, + BTRFS_INODE_REF_KEY); + if (ret < 0) { + goto err; + } else if (ret > 0) { + ret = -ENOENT; + goto err; + } + } + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + dirid = key.offset; + + inode_ref = btrfs_item_ptr(path->nodes[0], + path->slots[0], + struct btrfs_inode_ref); + len = btrfs_inode_ref_name_len(path->nodes[0], + inode_ref); + ptr -= len + 1; + if (ptr < name) { + ret = -ENAMETOOLONG; + goto err; + } + read_extent_buffer(path->nodes[0], ptr + 1, + (unsigned long)(inode_ref + 1), len); + ptr[0] = '/'; + btrfs_release_path(path); + } } + btrfs_free_path(path); + if (ptr == name + PATH_MAX - 1) { + name[0] = '/'; + name[1] = '\0'; + } else { + memmove(name, ptr, name + PATH_MAX - ptr); + } + return name; + +err: + btrfs_free_path(path); + kfree(name); + return ERR_PTR(ret); +} + +static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objectid) +{ + struct btrfs_root *root = fs_info->tree_root; + struct btrfs_dir_item *di; + struct btrfs_path *path; + struct btrfs_key location; + u64 dir_id; + path = btrfs_alloc_path(); if (!path) - return ERR_PTR(-ENOMEM); + return -ENOMEM; path->leave_spinning = 1; /* @@ -754,61 +1001,23 @@ di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0); if (IS_ERR(di)) { btrfs_free_path(path); - return ERR_CAST(di); + return PTR_ERR(di); } if (!di) { /* * Ok the default dir item isn't there. This is weird since * it's always been there, but don't freak out, just try and - * mount to root most subvolume. + * mount the top-level subvolume. */ btrfs_free_path(path); - dir_id = BTRFS_FIRST_FREE_OBJECTID; - new_root = fs_info->fs_root; - goto setup_root; + *objectid = BTRFS_FS_TREE_OBJECTID; + return 0; } btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); btrfs_free_path(path); - -find_root: - new_root = btrfs_read_fs_root_no_name(fs_info, &location); - if (IS_ERR(new_root)) - return ERR_CAST(new_root); - - if (btrfs_root_refs(&new_root->root_item) == 0) - return ERR_PTR(-ENOENT); - - if (!(sb->s_flags & MS_RDONLY)) { - int ret; - down_read(&fs_info->cleanup_work_sem); - ret = btrfs_orphan_cleanup(new_root); - up_read(&fs_info->cleanup_work_sem); - if (ret) - return ERR_PTR(ret); - } - - dir_id = btrfs_root_dirid(&new_root->root_item); -setup_root: - location.objectid = dir_id; - location.type = BTRFS_INODE_ITEM_KEY; - location.offset = 0; - - inode = btrfs_iget(sb, &location, new_root, &new); - if (IS_ERR(inode)) - return ERR_CAST(inode); - - /* - * If we're just mounting the root most subvol put the inode and return - * a reference to the dentry. We will have already gotten a reference - * to the inode in btrfs_fill_super so we're good to go. - */ - if (!new && sb->s_root->d_inode == inode) { - iput(inode); - return dget(sb->s_root); - } - - return d_obtain_alias(inode); + *objectid = location.objectid; + return 0; } static int btrfs_fill_super(struct super_block *sb, @@ -831,9 +1040,10 @@ sb->s_flags |= MS_POSIXACL; #endif sb->s_flags |= MS_I_VERSION; + sb->s_iflags |= SB_I_CGROUPWB; err = open_ctree(sb, fs_devices, (char *)data); if (err) { - printk("btrfs: open_ctree failed\n"); + printk(KERN_ERR "BTRFS: open_ctree failed\n"); return err; } @@ -875,14 +1085,32 @@ return 0; } - btrfs_wait_ordered_extents(root, 1); + btrfs_wait_ordered_roots(fs_info, -1); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { /* no transaction, don't bother */ - if (PTR_ERR(trans) == -ENOENT) - return 0; - return PTR_ERR(trans); + if (PTR_ERR(trans) == -ENOENT) { + /* + * Exit unless we have some pending changes + * that need to go through commit + */ + if (fs_info->pending_changes == 0) + return 0; + /* + * A non-blocking test if the fs is frozen. We must not + * start a new transaction here otherwise a deadlock + * happens. The pending operations are delayed to the + * next commit after thawing. + */ + if (__sb_start_write(sb, SB_FREEZE_WRITE, false)) + __sb_end_write(sb, SB_FREEZE_WRITE); + else + return 0; + trans = btrfs_start_transaction(root, 0); + } + if (IS_ERR(trans)) + return PTR_ERR(trans); } return btrfs_commit_transaction(trans, root); } @@ -901,12 +1129,10 @@ seq_puts(seq, ",nodatacow"); if (btrfs_test_opt(root, NOBARRIER)) seq_puts(seq, ",nobarrier"); - if (info->max_inline != 8192 * 1024) - seq_printf(seq, ",max_inline=%llu", - (unsigned long long)info->max_inline); + if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE) + seq_printf(seq, ",max_inline=%llu", info->max_inline); if (info->alloc_start != 0) - seq_printf(seq, ",alloc_start=%llu", - (unsigned long long)info->alloc_start); + seq_printf(seq, ",alloc_start=%llu", info->alloc_start); if (info->thread_pool_size != min_t(unsigned long, num_online_cpus() + 2, 8)) seq_printf(seq, ",thread_pool=%d", info->thread_pool_size); @@ -938,6 +1164,8 @@ seq_puts(seq, ",space_cache"); else seq_puts(seq, ",nospace_cache"); + if (btrfs_test_opt(root, RESCAN_UUID_TREE)) + seq_puts(seq, ",rescan_uuid_tree"); if (btrfs_test_opt(root, CLEAR_CACHE)) seq_puts(seq, ",clear_cache"); if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED)) @@ -950,8 +1178,34 @@ seq_puts(seq, ",inode_cache"); if (btrfs_test_opt(root, SKIP_BALANCE)) seq_puts(seq, ",skip_balance"); + if (btrfs_test_opt(root, RECOVERY)) + seq_puts(seq, ",recovery"); +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA)) + seq_puts(seq, ",check_int_data"); + else if (btrfs_test_opt(root, CHECK_INTEGRITY)) + seq_puts(seq, ",check_int"); + if (info->check_integrity_print_mask) + seq_printf(seq, ",check_int_print_mask=%d", + info->check_integrity_print_mask); +#endif + if (info->metadata_ratio) + seq_printf(seq, ",metadata_ratio=%d", + info->metadata_ratio); if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR)) seq_puts(seq, ",fatal_errors=panic"); + if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL) + seq_printf(seq, ",commit=%d", info->commit_interval); +#ifdef CONFIG_BTRFS_DEBUG + if (btrfs_test_opt(root, FRAGMENT_DATA)) + seq_puts(seq, ",fragment=data"); + if (btrfs_test_opt(root, FRAGMENT_METADATA)) + seq_puts(seq, ",fragment=metadata"); +#endif + seq_printf(seq, ",subvolid=%llu", + BTRFS_I(d_inode(dentry))->root->root_key.objectid); + seq_puts(seq, ",subvol="); + seq_dentry(seq, dentry, " \t\n\\"); return 0; } @@ -982,86 +1236,192 @@ } /* - * This will strip out the subvol=%s argument for an argument string and add - * subvolid=0 to make sure we get the actual tree root for path walking to the - * subvol we want. + * This will add subvolid=0 to the argument string while removing any subvol= + * and subvolid= arguments to make sure we get the top-level root for path + * walking to the subvol we want. */ static char *setup_root_args(char *args) { - unsigned len = strlen(args) + 2 + 1; - char *src, *dst, *buf; - - /* - * We need the same args as before, but with this substitution: - * s!subvol=[^,]+!subvolid=0! - * - * Since the replacement string is up to 2 bytes longer than the - * original, allocate strlen(args) + 2 + 1 bytes. - */ + char *buf, *dst, *sep; - src = strstr(args, "subvol="); - /* This shouldn't happen, but just in case.. */ - if (!src) - return NULL; + if (!args) + return kstrdup("subvolid=0", GFP_NOFS); - buf = dst = kmalloc(len, GFP_NOFS); + /* The worst case is that we add ",subvolid=0" to the end. */ + buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1, GFP_NOFS); if (!buf) return NULL; - /* - * If the subvol= arg is not at the start of the string, - * copy whatever precedes it into buf. - */ - if (src != args) { - *src++ = '\0'; - strcpy(buf, args); - dst += strlen(args); + while (1) { + sep = strchrnul(args, ','); + if (!strstarts(args, "subvol=") && + !strstarts(args, "subvolid=")) { + memcpy(dst, args, sep - args); + dst += sep - args; + *dst++ = ','; + } + if (*sep) + args = sep + 1; + else + break; } - strcpy(dst, "subvolid=0"); - dst += strlen("subvolid=0"); - - /* - * If there is a "," after the original subvol=... string, - * copy that suffix into our buffer. Otherwise, we're done. - */ - src = strchr(src, ','); - if (src) - strcpy(dst, src); return buf; } -static struct dentry *mount_subvol(const char *subvol_name, int flags, - const char *device_name, char *data) +static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid, + int flags, const char *device_name, + char *data) { struct dentry *root; - struct vfsmount *mnt; + struct vfsmount *mnt = NULL; char *newargs; + int ret; newargs = setup_root_args(data); - if (!newargs) - return ERR_PTR(-ENOMEM); - mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, - newargs); - kfree(newargs); - if (IS_ERR(mnt)) - return ERR_CAST(mnt); + if (!newargs) { + root = ERR_PTR(-ENOMEM); + goto out; + } + + mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs); + if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) { + if (flags & MS_RDONLY) { + mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY, + device_name, newargs); + } else { + mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY, + device_name, newargs); + if (IS_ERR(mnt)) { + root = ERR_CAST(mnt); + mnt = NULL; + goto out; + } + + down_write(&mnt->mnt_sb->s_umount); + ret = btrfs_remount(mnt->mnt_sb, &flags, NULL); + up_write(&mnt->mnt_sb->s_umount); + if (ret < 0) { + root = ERR_PTR(ret); + goto out; + } + } + } + if (IS_ERR(mnt)) { + root = ERR_CAST(mnt); + mnt = NULL; + goto out; + } + + if (!subvol_name) { + if (!subvol_objectid) { + ret = get_default_subvol_objectid(btrfs_sb(mnt->mnt_sb), + &subvol_objectid); + if (ret) { + root = ERR_PTR(ret); + goto out; + } + } + subvol_name = get_subvol_name_from_objectid(btrfs_sb(mnt->mnt_sb), + subvol_objectid); + if (IS_ERR(subvol_name)) { + root = ERR_CAST(subvol_name); + subvol_name = NULL; + goto out; + } + + } root = mount_subtree(mnt, subvol_name); + /* mount_subtree() drops our reference on the vfsmount. */ + mnt = NULL; - if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) { + if (!IS_ERR(root)) { struct super_block *s = root->d_sb; - dput(root); - root = ERR_PTR(-EINVAL); - deactivate_locked_super(s); - printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n", - subvol_name); + struct inode *root_inode = d_inode(root); + u64 root_objectid = BTRFS_I(root_inode)->root->root_key.objectid; + + ret = 0; + if (!is_subvolume_inode(root_inode)) { + pr_err("BTRFS: '%s' is not a valid subvolume\n", + subvol_name); + ret = -EINVAL; + } + if (subvol_objectid && root_objectid != subvol_objectid) { + /* + * This will also catch a race condition where a + * subvolume which was passed by ID is renamed and + * another subvolume is renamed over the old location. + */ + pr_err("BTRFS: subvol '%s' does not match subvolid %llu\n", + subvol_name, subvol_objectid); + ret = -EINVAL; + } + if (ret) { + dput(root); + root = ERR_PTR(ret); + deactivate_locked_super(s); + } } +out: + mntput(mnt); + kfree(newargs); + kfree(subvol_name); return root; } +static int parse_security_options(char *orig_opts, + struct security_mnt_opts *sec_opts) +{ + char *secdata = NULL; + int ret = 0; + + secdata = alloc_secdata(); + if (!secdata) + return -ENOMEM; + ret = security_sb_copy_data(orig_opts, secdata); + if (ret) { + free_secdata(secdata); + return ret; + } + ret = security_sb_parse_opts_str(secdata, sec_opts); + free_secdata(secdata); + return ret; +} + +static int setup_security_options(struct btrfs_fs_info *fs_info, + struct super_block *sb, + struct security_mnt_opts *sec_opts) +{ + int ret = 0; + + /* + * Call security_sb_set_mnt_opts() to check whether new sec_opts + * is valid. + */ + ret = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL); + if (ret) + return ret; + +#ifdef CONFIG_SECURITY + if (!fs_info->security_opts.num_mnt_opts) { + /* first time security setup, copy sec_opts to fs_info */ + memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts)); + } else { + /* + * Since SELinux(the only one supports security_mnt_opts) does + * NOT support changing context during remount/mount same sb, + * This must be the same or part of the same security options, + * just free it. + */ + security_free_mnt_opts(sec_opts); + } +#endif + return ret; +} + /* * Find a superblock for the given device / mount point. * @@ -1073,9 +1433,9 @@ { struct block_device *bdev = NULL; struct super_block *s; - struct dentry *root; struct btrfs_fs_devices *fs_devices = NULL; struct btrfs_fs_info *fs_info = NULL; + struct security_mnt_opts new_sec_opts; fmode_t mode = FMODE_READ; char *subvol_name = NULL; u64 subvol_objectid = 0; @@ -1092,15 +1452,22 @@ return ERR_PTR(error); } - if (subvol_name) { - root = mount_subvol(subvol_name, flags, device_name, data); - kfree(subvol_name); - return root; + if (subvol_name || subvol_objectid != BTRFS_FS_TREE_OBJECTID) { + /* mount_subvol() will free subvol_name. */ + return mount_subvol(subvol_name, subvol_objectid, flags, + device_name, data); + } + + security_init_mnt_opts(&new_sec_opts); + if (data) { + error = parse_security_options(data, &new_sec_opts); + if (error) + return ERR_PTR(error); } error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices); if (error) - return ERR_PTR(error); + goto error_sec_opts; /* * Setup a dummy root and fs_info for test/set super. This is because @@ -1109,13 +1476,16 @@ * then open_ctree will properly initialize everything later. */ fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS); - if (!fs_info) - return ERR_PTR(-ENOMEM); + if (!fs_info) { + error = -ENOMEM; + goto error_sec_opts; + } fs_info->fs_devices = fs_devices; fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS); fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS); + security_init_mnt_opts(&fs_info->security_opts); if (!fs_info->super_copy || !fs_info->super_for_commit) { error = -ENOMEM; goto error_fs_info; @@ -1151,27 +1521,29 @@ error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); } + if (error) { + deactivate_locked_super(s); + goto error_sec_opts; + } - root = !error ? get_default_root(s, subvol_objectid) : ERR_PTR(error); - if (IS_ERR(root)) + fs_info = btrfs_sb(s); + error = setup_security_options(fs_info, s, &new_sec_opts); + if (error) { deactivate_locked_super(s); + goto error_sec_opts; + } - return root; + return dget(s->s_root); error_close_devices: btrfs_close_devices(fs_devices); error_fs_info: free_fs_info(fs_info); +error_sec_opts: + security_free_mnt_opts(&new_sec_opts); return ERR_PTR(error); } -static void btrfs_set_max_workers(struct btrfs_workers *workers, int new_limit) -{ - spin_lock_irq(&workers->lock); - workers->max_workers = new_limit; - spin_unlock_irq(&workers->lock); -} - static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, int new_pool_size, int old_pool_size) { @@ -1180,24 +1552,23 @@ fs_info->thread_pool_size = new_pool_size; - printk(KERN_INFO "btrfs: resize thread pool %d -> %d\n", + btrfs_info(fs_info, "resize thread pool %d -> %d", old_pool_size, new_pool_size); - btrfs_set_max_workers(&fs_info->generic_worker, new_pool_size); - btrfs_set_max_workers(&fs_info->workers, new_pool_size); - btrfs_set_max_workers(&fs_info->delalloc_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->submit_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->caching_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->fixup_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->endio_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->endio_meta_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->endio_meta_write_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->endio_write_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->endio_freespace_worker, new_pool_size); - btrfs_set_max_workers(&fs_info->delayed_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->readahead_workers, new_pool_size); - btrfs_set_max_workers(&fs_info->scrub_wr_completion_workers, - new_pool_size); + btrfs_workqueue_set_max(fs_info->workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->endio_meta_write_workers, + new_pool_size); + btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size); + btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->readahead_workers, new_pool_size); + btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers, + new_pool_size); } static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info) @@ -1248,8 +1619,24 @@ unsigned int old_metadata_ratio = fs_info->metadata_ratio; int ret; + sync_filesystem(sb); btrfs_remount_prepare(fs_info); + if (data) { + struct security_mnt_opts new_sec_opts; + + security_init_mnt_opts(&new_sec_opts); + ret = parse_security_options(data, &new_sec_opts); + if (ret) + goto restore; + ret = setup_security_options(fs_info, sb, + &new_sec_opts); + if (ret) { + security_free_mnt_opts(&new_sec_opts); + goto restore; + } + } + ret = btrfs_parse_options(root, data); if (ret) { ret = -EINVAL; @@ -1268,8 +1655,24 @@ * this also happens on 'umount -rf' or on shutdown, when * the filesystem is busy. */ + cancel_work_sync(&fs_info->async_reclaim_work); + + /* wait for the uuid_scan task to finish */ + down(&fs_info->uuid_tree_rescan_sem); + /* avoid complains from lockdep et al. */ + up(&fs_info->uuid_tree_rescan_sem); + sb->s_flags |= MS_RDONLY; + /* + * Setting MS_RDONLY will put the cleaner thread to + * sleep at the next loop if it's already active. + * If it's already asleep, we'll leave unused block + * groups on disk until we're mounted read-write again + * unless we clean them up here. + */ + btrfs_delete_unused_bgs(fs_info); + btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); btrfs_pause_balance(fs_info); @@ -1278,6 +1681,12 @@ if (ret) goto restore; } else { + if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) { + btrfs_err(fs_info, + "Remounting read-write after error is not allowed"); + ret = -EINVAL; + goto restore; + } if (fs_info->fs_devices->rw_devices == 0) { ret = -EACCES; goto restore; @@ -1286,8 +1695,8 @@ if (fs_info->fs_devices->missing_devices > fs_info->num_tolerated_disk_barrier_failures && !(*flags & MS_RDONLY)) { - printk(KERN_WARNING - "Btrfs: too many missing devices, writeable remount is not allowed\n"); + btrfs_warn(fs_info, + "too many missing devices, writeable remount is not allowed"); ret = -EACCES; goto restore; } @@ -1302,7 +1711,9 @@ goto restore; /* recover relocation */ + mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(root); + mutex_unlock(&fs_info->cleaner_mutex); if (ret) goto restore; @@ -1312,12 +1723,22 @@ ret = btrfs_resume_dev_replace_async(fs_info); if (ret) { - pr_warn("btrfs: failed to resume dev_replace\n"); + btrfs_warn(fs_info, "failed to resume dev_replace"); goto restore; } + + if (!fs_info->uuid_root) { + btrfs_info(fs_info, "creating UUID tree"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, "failed to create the UUID tree %d", ret); + goto restore; + } + } sb->s_flags &= ~MS_RDONLY; } out: + wake_up_process(fs_info->transaction_kthread); btrfs_remount_cleanup(fs_info, old_opts); return 0; @@ -1384,10 +1805,22 @@ int i = 0, nr_devices; int ret; + /* + * We aren't under the device list lock, so this is racey-ish, but good + * enough for our purposes. + */ nr_devices = fs_info->fs_devices->open_devices; - BUG_ON(!nr_devices); + if (!nr_devices) { + smp_mb(); + nr_devices = fs_info->fs_devices->open_devices; + ASSERT(nr_devices); + if (!nr_devices) { + *free_bytes = 0; + return 0; + } + } - devices_info = kmalloc(sizeof(*devices_info) * nr_devices, + devices_info = kmalloc_array(nr_devices, sizeof(*devices_info), GFP_NOFS); if (!devices_info) return -ENOMEM; @@ -1410,15 +1843,21 @@ else min_stripe_size = BTRFS_STRIPE_LEN; - list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (fs_info->alloc_start) + mutex_lock(&fs_devices->device_list_mutex); + rcu_read_lock(); + list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) { if (!device->in_fs_metadata || !device->bdev || device->is_tgtdev_for_dev_replace) continue; + if (i >= nr_devices) + break; + avail_space = device->total_bytes - device->bytes_used; /* align with stripe_len */ - do_div(avail_space, BTRFS_STRIPE_LEN); + avail_space = div_u64(avail_space, BTRFS_STRIPE_LEN); avail_space *= BTRFS_STRIPE_LEN; /* @@ -1429,24 +1868,32 @@ skip_space = 1024 * 1024; /* user can set the offset in fs_info->alloc_start. */ - if (fs_info->alloc_start + BTRFS_STRIPE_LEN <= - device->total_bytes) + if (fs_info->alloc_start && + fs_info->alloc_start + BTRFS_STRIPE_LEN <= + device->total_bytes) { + rcu_read_unlock(); skip_space = max(fs_info->alloc_start, skip_space); - /* - * btrfs can not use the free space in [0, skip_space - 1], - * we must subtract it from the total. In order to implement - * it, we account the used space in this range first. - */ - ret = btrfs_account_dev_extents_size(device, 0, skip_space - 1, - &used_space); - if (ret) { - kfree(devices_info); - return ret; - } + /* + * btrfs can not use the free space in + * [0, skip_space - 1], we must subtract it from the + * total. In order to implement it, we account the used + * space in this range first. + */ + ret = btrfs_account_dev_extents_size(device, 0, + skip_space - 1, + &used_space); + if (ret) { + kfree(devices_info); + mutex_unlock(&fs_devices->device_list_mutex); + return ret; + } + + rcu_read_lock(); - /* calc the free space in [0, skip_space - 1] */ - skip_space -= used_space; + /* calc the free space in [0, skip_space - 1] */ + skip_space -= used_space; + } /* * we can use the free space in [0, skip_space - 1], subtract @@ -1465,6 +1912,9 @@ i++; } + rcu_read_unlock(); + if (fs_info->alloc_start) + mutex_unlock(&fs_devices->device_list_mutex); nr_devices = i; @@ -1494,6 +1944,23 @@ return 0; } +/* + * Calculate numbers for 'df', pessimistic in case of mixed raid profiles. + * + * If there's a redundant raid level at DATA block groups, use the respective + * multiplier to scale the sizes. + * + * Unused device space usage is based on simulating the chunk allocator + * algorithm that respects the device sizes, order of allocations and the + * 'alloc_start' value, this is a close approximation of the actual use but + * there are other factors that may change the result (like a new metadata + * chunk). + * + * If metadata is exhausted, f_bavail will be 0. + * + * FIXME: not accurate for mixed block groups, total and free/used are ok, + * available appears slightly larger. + */ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); @@ -1502,38 +1969,83 @@ struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; + u64 total_free_meta = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)fs_info->fsid; + unsigned factor = 1; + struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; + u64 thresh = 0; - /* holding chunk_muext to avoid allocating new chunks */ - mutex_lock(&fs_info->chunk_mutex); + /* + * holding chunk_muext to avoid allocating new chunks, holding + * device_list_mutex to avoid the device being removed + */ rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_DATA) { + int i; + total_free_data += found->disk_total - found->disk_used; total_free_data -= btrfs_account_ro_block_groups_free_space(found); + + for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { + if (!list_empty(&found->block_groups[i])) { + switch (i) { + case BTRFS_RAID_DUP: + case BTRFS_RAID_RAID1: + case BTRFS_RAID_RAID10: + factor = 2; + } + } + } } + if (found->flags & BTRFS_BLOCK_GROUP_METADATA) + total_free_meta += found->disk_total - found->disk_used; total_used += found->disk_used; } + rcu_read_unlock(); - buf->f_namelen = BTRFS_NAME_LEN; - buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits; - buf->f_bfree = buf->f_blocks - (total_used >> bits); - buf->f_bsize = dentry->d_sb->s_blocksize; - buf->f_type = BTRFS_SUPER_MAGIC; - buf->f_bavail = total_free_data; + buf->f_blocks = div_u64(btrfs_super_total_bytes(disk_super), factor); + buf->f_blocks >>= bits; + buf->f_bfree = buf->f_blocks - (div_u64(total_used, factor) >> bits); + + /* Account global block reserve as used, it's in logical size already */ + spin_lock(&block_rsv->lock); + buf->f_bfree -= block_rsv->size >> bits; + spin_unlock(&block_rsv->lock); + + buf->f_bavail = div_u64(total_free_data, factor); ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data); - if (ret) { - mutex_unlock(&fs_info->chunk_mutex); + if (ret) return ret; - } - buf->f_bavail += total_free_data; + buf->f_bavail += div_u64(total_free_data, factor); buf->f_bavail = buf->f_bavail >> bits; - mutex_unlock(&fs_info->chunk_mutex); + + /* + * We calculate the remaining metadata space minus global reserve. If + * this is (supposedly) smaller than zero, there's no space. But this + * does not hold in practice, the exhausted state happens where's still + * some positive delta. So we apply some guesswork and compare the + * delta to a 4M threshold. (Practically observed delta was ~2M.) + * + * We probably cannot calculate the exact threshold value because this + * depends on the internal reservations requested by various + * operations, so some operations that consume a few metadata will + * succeed even if the Avail is zero. But this is better than the other + * way around. + */ + thresh = 4 * 1024 * 1024; + + if (total_free_meta - thresh < block_rsv->size) + buf->f_bavail = 0; + + buf->f_type = BTRFS_SUPER_MAGIC; + buf->f_bsize = dentry->d_sb->s_blocksize; + buf->f_namelen = BTRFS_NAME_LEN; /* We treat it as constant endianness (it doesn't matter _which_) because we want the fsid to come out the same whether mounted @@ -1541,8 +2053,8 @@ buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]); buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]); /* Mask in the root object ID too, to disambiguate subvols */ - buf->f_fsid.val[0] ^= BTRFS_I(dentry->d_inode)->root->objectid >> 32; - buf->f_fsid.val[1] ^= BTRFS_I(dentry->d_inode)->root->objectid; + buf->f_fsid.val[0] ^= BTRFS_I(d_inode(dentry))->root->objectid >> 32; + buf->f_fsid.val[1] ^= BTRFS_I(d_inode(dentry))->root->objectid; return 0; } @@ -1559,10 +2071,21 @@ .name = "btrfs", .mount = btrfs_mount, .kill_sb = btrfs_kill_super, - .fs_flags = FS_REQUIRES_DEV, + .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA, }; MODULE_ALIAS_FS("btrfs"); +static int btrfs_control_open(struct inode *inode, struct file *file) +{ + /* + * The control file's private_data is used to hold the + * transaction when it is started and is used to keep + * track of whether a transaction is already in progress. + */ + file->private_data = NULL; + return 0; +} + /* * used by btrfsctl to scan devices when no FS is mounted */ @@ -1613,11 +2136,6 @@ return btrfs_commit_transaction(trans, root); } -static int btrfs_unfreeze(struct super_block *sb) -{ - return 0; -} - static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); @@ -1633,6 +2151,8 @@ list_for_each_entry(dev, head, dev_list) { if (dev->missing) continue; + if (!dev->name) + continue; if (!first_dev || dev->devid < first_dev->devid) first_dev = dev; } @@ -1664,10 +2184,10 @@ .statfs = btrfs_statfs, .remount_fs = btrfs_remount, .freeze_fs = btrfs_freeze, - .unfreeze_fs = btrfs_unfreeze, }; static const struct file_operations btrfs_ctl_fops = { + .open = btrfs_control_open, .unlocked_ioctl = btrfs_control_ioctl, .compat_ioctl = btrfs_control_ioctl, .owner = THIS_MODULE, @@ -1690,18 +2210,64 @@ static void btrfs_interface_exit(void) { - if (misc_deregister(&btrfs_misc) < 0) - printk(KERN_INFO "btrfs: misc_deregister failed for control device\n"); + misc_deregister(&btrfs_misc); +} + +static void btrfs_print_info(void) +{ + printk(KERN_INFO "Btrfs loaded" +#ifdef CONFIG_BTRFS_DEBUG + ", debug=on" +#endif +#ifdef CONFIG_BTRFS_ASSERT + ", assert=on" +#endif +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + ", integrity-checker=on" +#endif + "\n"); +} + +static int btrfs_run_sanity_tests(void) +{ + int ret; + + ret = btrfs_init_test_fs(); + if (ret) + return ret; + + ret = btrfs_test_free_space_cache(); + if (ret) + goto out; + ret = btrfs_test_extent_buffer_operations(); + if (ret) + goto out; + ret = btrfs_test_extent_io(); + if (ret) + goto out; + ret = btrfs_test_inodes(); + if (ret) + goto out; + ret = btrfs_test_qgroups(); +out: + btrfs_destroy_test_fs(); + return ret; } static int __init init_btrfs_fs(void) { int err; - err = btrfs_init_sysfs(); + err = btrfs_hash_init(); if (err) return err; + btrfs_props_init(); + + err = btrfs_init_sysfs(); + if (err) + goto free_hash; + btrfs_init_compress(); err = btrfs_init_cachep(); @@ -1732,25 +2298,38 @@ if (err) goto free_auto_defrag; - err = btrfs_interface_init(); + err = btrfs_prelim_ref_init(); if (err) goto free_delayed_ref; - err = register_filesystem(&btrfs_fs_type); + err = btrfs_end_io_wq_init(); if (err) - goto unregister_ioctl; + goto free_prelim_ref; + + err = btrfs_interface_init(); + if (err) + goto free_end_io_wq; btrfs_init_lockdep(); -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS - btrfs_test_free_space_cache(); -#endif + btrfs_print_info(); + + err = btrfs_run_sanity_tests(); + if (err) + goto unregister_ioctl; + + err = register_filesystem(&btrfs_fs_type); + if (err) + goto unregister_ioctl; - printk(KERN_INFO "%s loaded\n", BTRFS_BUILD_VERSION); return 0; unregister_ioctl: btrfs_interface_exit(); +free_end_io_wq: + btrfs_end_io_wq_exit(); +free_prelim_ref: + btrfs_prelim_ref_exit(); free_delayed_ref: btrfs_delayed_ref_exit(); free_auto_defrag: @@ -1768,6 +2347,8 @@ free_compress: btrfs_exit_compress(); btrfs_exit_sysfs(); +free_hash: + btrfs_hash_exit(); return err; } @@ -1777,17 +2358,20 @@ btrfs_delayed_ref_exit(); btrfs_auto_defrag_exit(); btrfs_delayed_inode_exit(); + btrfs_prelim_ref_exit(); ordered_data_exit(); extent_map_exit(); extent_io_exit(); btrfs_interface_exit(); + btrfs_end_io_wq_exit(); unregister_filesystem(&btrfs_fs_type); btrfs_exit_sysfs(); btrfs_cleanup_fs_uuids(); btrfs_exit_compress(); + btrfs_hash_exit(); } -module_init(init_btrfs_fs) +late_initcall(init_btrfs_fs); module_exit(exit_btrfs_fs) MODULE_LICENSE("GPL");