diff options
Diffstat (limited to 'fs/btrfs/super.c')
-rw-r--r-- | fs/btrfs/super.c | 697 |
1 files changed, 383 insertions, 314 deletions
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 35a128acfbd1..170baef49fae 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -41,6 +41,7 @@ #include <linux/slab.h> #include <linux/cleancache.h> #include <linux/ratelimit.h> +#include <linux/crc32c.h> #include <linux/btrfs.h> #include "delayed-inode.h" #include "ctree.h" @@ -48,7 +49,6 @@ #include "transaction.h" #include "btrfs_inode.h" #include "print-tree.h" -#include "hash.h" #include "props.h" #include "xattr.h" #include "volumes.h" @@ -61,12 +61,21 @@ #include "tests/btrfs-tests.h" #include "qgroup.h" -#include "backref.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> static const struct super_operations btrfs_super_ops; + +/* + * Types for mounting the default subvolume and a subvolume explicitly + * requested by subvol=/path. That way the callchain is straightforward and we + * don't have to play tricks with the mount options and recursive calls to + * btrfs_mount. + * + * The new btrfs_root_fs_type also servers as a tag for the bdev_holder. + */ static struct file_system_type btrfs_fs_type; +static struct file_system_type btrfs_root_fs_type; static int btrfs_remount(struct super_block *sb, int *flags, char *data); @@ -98,30 +107,6 @@ const char *btrfs_decode_error(int errno) return errstr; } -/* btrfs handle error by forcing the filesystem readonly */ -static void btrfs_handle_error(struct btrfs_fs_info *fs_info) -{ - struct super_block *sb = fs_info->sb; - - if (sb_rdonly(sb)) - return; - - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - sb->s_flags |= MS_RDONLY; - btrfs_info(fs_info, "forced readonly"); - /* - * Note that a running device replace operation is not - * canceled here although there is no way to update - * the progress. It would add the risk of a deadlock, - * therefore the canceling is omitted. The only penalty - * is that some I/O remains active until the procedure - * completes. The next time when the filesystem is - * mounted writeable again, the device replace - * operation continues. - */ - } -} - /* * __btrfs_handle_fs_error decodes expected errors from the caller and * invokes the approciate error response. @@ -137,7 +122,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function /* * Special case: if the error is EROFS, and we're already - * under MS_RDONLY, then it is safe here. + * under SB_RDONLY, then it is safe here. */ if (errno == -EROFS && sb_rdonly(sb)) return; @@ -168,8 +153,23 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); /* Don't go through full error handling during mount */ - if (sb->s_flags & MS_BORN) - btrfs_handle_error(fs_info); + if (!(sb->s_flags & SB_BORN)) + return; + + if (sb_rdonly(sb)) + return; + + /* btrfs handle error by forcing the filesystem readonly */ + sb->s_flags |= SB_RDONLY; + btrfs_info(fs_info, "forced readonly"); + /* + * Note that a running device replace operation is not canceled here + * although there is no way to update the progress. It would add the + * risk of a deadlock, therefore the canceling is omitted. The only + * penalty is that some I/O remains active until the procedure + * completes. The next time when the filesystem is mounted writeable + * again, the device replace operation continues. + */ } #ifdef CONFIG_PRINTK @@ -202,7 +202,6 @@ static struct ratelimit_state printk_limits[] = { void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) { - struct super_block *sb = fs_info->sb; char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0"; struct va_format vaf; va_list args; @@ -228,7 +227,8 @@ void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) vaf.va = &args; if (__ratelimit(ratelimit)) - printk("%sBTRFS %s (device %s): %pV\n", lvl, type, sb->s_id, &vaf); + printk("%sBTRFS %s (device %s): %pV\n", lvl, type, + fs_info ? fs_info->sb->s_id : "<unknown>", &vaf); va_end(args); } @@ -292,7 +292,7 @@ void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function, vaf.va = &args; errstr = btrfs_decode_error(errno); - if (fs_info && (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR)) + if (fs_info && (btrfs_test_opt(fs_info, PANIC_ON_FATAL_ERROR))) panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n", s_id, function, line, &vaf, errno, errstr); @@ -308,85 +308,125 @@ static void btrfs_put_super(struct super_block *sb) } enum { - Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum, - Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd, - Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress, - Opt_compress_type, Opt_compress_force, Opt_compress_force_type, - Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, - Opt_space_cache, Opt_space_cache_version, Opt_clear_cache, - Opt_user_subvol_rm_allowed, Opt_enospc_debug, Opt_subvolrootid, - Opt_defrag, Opt_inode_cache, Opt_no_space_cache, Opt_recovery, - Opt_skip_balance, Opt_check_integrity, + Opt_acl, Opt_noacl, + Opt_clear_cache, + Opt_commit_interval, + Opt_compress, + Opt_compress_force, + Opt_compress_force_type, + Opt_compress_type, + Opt_degraded, + Opt_device, + Opt_fatal_errors, + Opt_flushoncommit, Opt_noflushoncommit, + Opt_inode_cache, Opt_noinode_cache, + Opt_max_inline, + Opt_barrier, Opt_nobarrier, + Opt_datacow, Opt_nodatacow, + Opt_datasum, Opt_nodatasum, + Opt_defrag, Opt_nodefrag, + Opt_discard, Opt_nodiscard, + Opt_nologreplay, + Opt_norecovery, + Opt_ratio, + Opt_rescan_uuid_tree, + Opt_skip_balance, + Opt_space_cache, Opt_no_space_cache, + Opt_space_cache_version, + Opt_ssd, Opt_nossd, + Opt_ssd_spread, Opt_nossd_spread, + Opt_subvol, + Opt_subvolid, + Opt_thread_pool, + Opt_treelog, Opt_notreelog, + Opt_usebackuproot, + Opt_user_subvol_rm_allowed, + + /* Deprecated options */ + Opt_alloc_start, + Opt_recovery, + Opt_subvolrootid, + + /* Debugging options */ + Opt_check_integrity, Opt_check_integrity_including_extent_data, - 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, Opt_usebackuproot, - Opt_nologreplay, Opt_norecovery, + Opt_check_integrity_print_mask, + Opt_enospc_debug, Opt_noenospc_debug, #ifdef CONFIG_BTRFS_DEBUG Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all, #endif +#ifdef CONFIG_BTRFS_FS_REF_VERIFY + Opt_ref_verify, +#endif Opt_err, }; static const match_table_t tokens = { - {Opt_degraded, "degraded"}, - {Opt_subvol, "subvol=%s"}, - {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"}, + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, + {Opt_clear_cache, "clear_cache"}, + {Opt_commit_interval, "commit=%u"}, {Opt_compress, "compress"}, {Opt_compress_type, "compress=%s"}, {Opt_compress_force, "compress-force"}, {Opt_compress_force_type, "compress-force=%s"}, - {Opt_ssd, "ssd"}, - {Opt_ssd_spread, "ssd_spread"}, - {Opt_nossd, "nossd"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_notreelog, "notreelog"}, - {Opt_treelog, "treelog"}, - {Opt_nologreplay, "nologreplay"}, - {Opt_norecovery, "norecovery"}, + {Opt_degraded, "degraded"}, + {Opt_device, "device=%s"}, + {Opt_fatal_errors, "fatal_errors=%s"}, {Opt_flushoncommit, "flushoncommit"}, {Opt_noflushoncommit, "noflushoncommit"}, - {Opt_ratio, "metadata_ratio=%d"}, + {Opt_inode_cache, "inode_cache"}, + {Opt_noinode_cache, "noinode_cache"}, + {Opt_max_inline, "max_inline=%s"}, + {Opt_barrier, "barrier"}, + {Opt_nobarrier, "nobarrier"}, + {Opt_datacow, "datacow"}, + {Opt_nodatacow, "nodatacow"}, + {Opt_datasum, "datasum"}, + {Opt_nodatasum, "nodatasum"}, + {Opt_defrag, "autodefrag"}, + {Opt_nodefrag, "noautodefrag"}, {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, + {Opt_nologreplay, "nologreplay"}, + {Opt_norecovery, "norecovery"}, + {Opt_ratio, "metadata_ratio=%u"}, + {Opt_rescan_uuid_tree, "rescan_uuid_tree"}, + {Opt_skip_balance, "skip_balance"}, {Opt_space_cache, "space_cache"}, + {Opt_no_space_cache, "nospace_cache"}, {Opt_space_cache_version, "space_cache=%s"}, - {Opt_clear_cache, "clear_cache"}, + {Opt_ssd, "ssd"}, + {Opt_nossd, "nossd"}, + {Opt_ssd_spread, "ssd_spread"}, + {Opt_nossd_spread, "nossd_spread"}, + {Opt_subvol, "subvol=%s"}, + {Opt_subvolid, "subvolid=%s"}, + {Opt_thread_pool, "thread_pool=%u"}, + {Opt_treelog, "treelog"}, + {Opt_notreelog, "notreelog"}, + {Opt_usebackuproot, "usebackuproot"}, {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, - {Opt_enospc_debug, "enospc_debug"}, - {Opt_noenospc_debug, "noenospc_debug"}, + + /* Deprecated options */ + {Opt_alloc_start, "alloc_start=%s"}, + {Opt_recovery, "recovery"}, {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"}, /* deprecated */ - {Opt_usebackuproot, "usebackuproot"}, - {Opt_skip_balance, "skip_balance"}, + + /* Debugging options */ {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"}, + {Opt_check_integrity_print_mask, "check_int_print_mask=%u"}, + {Opt_enospc_debug, "enospc_debug"}, + {Opt_noenospc_debug, "noenospc_debug"}, #ifdef CONFIG_BTRFS_DEBUG {Opt_fragment_data, "fragment=data"}, {Opt_fragment_metadata, "fragment=metadata"}, {Opt_fragment_all, "fragment=all"}, #endif +#ifdef CONFIG_BTRFS_FS_REF_VERIFY + {Opt_ref_verify, "ref_verify"}, +#endif {Opt_err, NULL}, }; @@ -399,7 +439,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, unsigned long new_flags) { substring_t args[MAX_OPT_ARGS]; - char *p, *num, *orig = NULL; + char *p, *num; u64 cache_gen; int intarg; int ret = 0; @@ -422,16 +462,6 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, if (!options) goto check; - /* - * strsep changes the string, duplicate it because parse_options - * gets called twice - */ - options = kstrdup(options, GFP_KERNEL); - if (!options) - return -ENOMEM; - - orig = options; - while ((p = strsep(&options, ",")) != NULL) { int token; if (!*p) @@ -448,7 +478,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_subvolrootid: case Opt_device: /* - * These are parsed by btrfs_parse_early_options + * These are parsed by btrfs_parse_subvol_options + * and btrfs_parse_early_options * and can be happily ignored here. */ break; @@ -501,7 +532,18 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, token == Opt_compress_force || strncmp(args[0].from, "zlib", 4) == 0) { compress_type = "zlib"; + info->compress_type = BTRFS_COMPRESS_ZLIB; + info->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL; + /* + * args[0] contains uninitialized data since + * for these tokens we don't expect any + * parameter. + */ + if (token != Opt_compress && + token != Opt_compress_force) + info->compress_level = + btrfs_compress_str2level(args[0].from); btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); @@ -549,9 +591,9 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, compress_force != saved_compress_force)) || (!btrfs_test_opt(info, COMPRESS) && no_compress == 1)) { - btrfs_info(info, "%s %s compression", + btrfs_info(info, "%s %s compression, level %d", (compress_force) ? "force" : "use", - compress_type); + compress_type, info->compress_level); } compress_force = false; break; @@ -571,6 +613,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, btrfs_set_opt(info->mount_opt, NOSSD); btrfs_clear_and_info(info, SSD, "not using ssd optimizations"); + /* Fallthrough */ + case Opt_nossd_spread: btrfs_clear_and_info(info, SSD_SPREAD, "not using spread ssd allocation scheme"); break; @@ -586,12 +630,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, ret = match_int(&args[0], &intarg); if (ret) { goto out; - } else if (intarg > 0) { - info->thread_pool_size = intarg; - } else { + } else if (intarg == 0) { ret = -EINVAL; goto out; } + info->thread_pool_size = intarg; break; case Opt_max_inline: num = match_strdup(&args[0]); @@ -617,7 +660,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, break; case Opt_acl: #ifdef CONFIG_BTRFS_FS_POSIX_ACL - info->sb->s_flags |= MS_POSIXACL; + info->sb->s_flags |= SB_POSIXACL; break; #else btrfs_err(info, "support for ACL not compiled in!"); @@ -625,7 +668,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, goto out; #endif case Opt_noacl: - info->sb->s_flags &= ~MS_POSIXACL; + info->sb->s_flags &= ~SB_POSIXACL; break; case Opt_notreelog: btrfs_set_and_info(info, NOTREELOG, @@ -650,16 +693,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, break; case Opt_ratio: ret = match_int(&args[0], &intarg); - if (ret) { + if (ret) goto out; - } else if (intarg >= 0) { - info->metadata_ratio = intarg; - btrfs_info(info, "metadata ratio %d", - info->metadata_ratio); - } else { - ret = -EINVAL; - goto out; - } + info->metadata_ratio = intarg; + btrfs_info(info, "metadata ratio %u", + info->metadata_ratio); break; case Opt_discard: btrfs_set_and_info(info, DISCARD, @@ -754,17 +792,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, break; case Opt_check_integrity_print_mask: ret = match_int(&args[0], &intarg); - if (ret) { + if (ret) goto out; - } else if (intarg >= 0) { - info->check_integrity_print_mask = intarg; - btrfs_info(info, - "check_integrity_print_mask 0x%x", - info->check_integrity_print_mask); - } else { - ret = -EINVAL; - goto out; - } + info->check_integrity_print_mask = intarg; + btrfs_info(info, "check_integrity_print_mask 0x%x", + info->check_integrity_print_mask); break; #else case Opt_check_integrity_including_extent_data: @@ -790,24 +822,18 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_commit_interval: intarg = 0; ret = match_int(&args[0], &intarg); - if (ret < 0) { - btrfs_err(info, "invalid commit interval"); - ret = -EINVAL; + if (ret) goto out; - } - if (intarg > 0) { - if (intarg > 300) { - btrfs_warn(info, - "excessive commit interval %d", - intarg); - } - info->commit_interval = intarg; - } else { + if (intarg == 0) { btrfs_info(info, - "using default commit interval %ds", + "using default commit interval %us", BTRFS_DEFAULT_COMMIT_INTERVAL); - info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; + intarg = BTRFS_DEFAULT_COMMIT_INTERVAL; + } else if (intarg > 300) { + btrfs_warn(info, "excessive commit interval %d", + intarg); } + info->commit_interval = intarg; break; #ifdef CONFIG_BTRFS_DEBUG case Opt_fragment_all: @@ -825,6 +851,12 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, btrfs_set_opt(info->mount_opt, FRAGMENT_DATA); break; #endif +#ifdef CONFIG_BTRFS_FS_REF_VERIFY + case Opt_ref_verify: + btrfs_info(info, "doing ref verification"); + btrfs_set_opt(info->mount_opt, REF_VERIFY); + break; +#endif case Opt_err: btrfs_info(info, "unrecognized mount option '%s'", p); ret = -EINVAL; @@ -837,7 +869,7 @@ check: /* * Extra check for current option against current flag */ - if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) { + if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & SB_RDONLY)) { btrfs_err(info, "nologreplay must be used with ro mount option"); ret = -EINVAL; @@ -854,7 +886,6 @@ out: btrfs_info(info, "disk space caching is enabled"); if (!ret && btrfs_test_opt(info, FREE_SPACE_TREE)) btrfs_info(info, "using free space tree"); - kfree(orig); return ret; } @@ -865,20 +896,69 @@ out: * only when we need to allocate a new super block. */ static int btrfs_parse_early_options(const char *options, fmode_t flags, - void *holder, char **subvol_name, u64 *subvol_objectid, - struct btrfs_fs_devices **fs_devices) + void *holder, struct btrfs_fs_devices **fs_devices) { substring_t args[MAX_OPT_ARGS]; char *device_name, *opts, *orig, *p; - char *num = NULL; int error = 0; if (!options) return 0; /* - * strsep changes the string, duplicate it because parse_options - * gets called twice + * strsep changes the string, duplicate it because btrfs_parse_options + * gets called later + */ + opts = kstrdup(options, GFP_KERNEL); + if (!opts) + return -ENOMEM; + orig = opts; + + while ((p = strsep(&opts, ",")) != NULL) { + int token; + + if (!*p) + continue; + + token = match_token(p, tokens, args); + if (token == Opt_device) { + device_name = match_strdup(&args[0]); + if (!device_name) { + error = -ENOMEM; + goto out; + } + error = btrfs_scan_one_device(device_name, + flags, holder, fs_devices); + kfree(device_name); + if (error) + goto out; + } + } + +out: + kfree(orig); + return error; +} + +/* + * Parse mount options that are related to subvolume id + * + * The value is later passed to mount_subvol() + */ +static int btrfs_parse_subvol_options(const char *options, fmode_t flags, + char **subvol_name, u64 *subvol_objectid) +{ + substring_t args[MAX_OPT_ARGS]; + char *opts, *orig, *p; + int error = 0; + u64 subvolid; + + if (!options) + return 0; + + /* + * strsep changes the string, duplicate it because + * btrfs_parse_early_options gets called later */ opts = kstrdup(options, GFP_KERNEL); if (!opts) @@ -901,34 +981,19 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, } break; case Opt_subvolid: - num = match_strdup(&args[0]); - if (num) { - *subvol_objectid = memparse(num, NULL); - kfree(num); - /* we want the original fs_tree */ - if (!*subvol_objectid) - *subvol_objectid = - BTRFS_FS_TREE_OBJECTID; - } else { - error = -EINVAL; + error = match_u64(&args[0], &subvolid); + if (error) goto out; - } + + /* we want the original fs_tree */ + if (subvolid == 0) + subvolid = BTRFS_FS_TREE_OBJECTID; + + *subvol_objectid = subvolid; break; case Opt_subvolrootid: pr_warn("BTRFS: 'subvolrootid' mount option is deprecated and has no effect\n"); break; - case Opt_device: - device_name = match_strdup(&args[0]); - if (!device_name) { - error = -ENOMEM; - goto out; - } - error = btrfs_scan_one_device(device_name, - flags, holder, fs_devices); - kfree(device_name); - if (error) - goto out; - break; default: break; } @@ -1133,9 +1198,9 @@ static int btrfs_fill_super(struct super_block *sb, sb->s_xattr = btrfs_xattr_handlers; sb->s_time_gran = 1; #ifdef CONFIG_BTRFS_FS_POSIX_ACL - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; #endif - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; sb->s_iflags |= SB_I_CGROUPWB; err = super_setup_bdi(sb); @@ -1166,7 +1231,7 @@ static int btrfs_fill_super(struct super_block *sb, } cleancache_init_fs(sb); - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; return 0; fail_close: @@ -1205,8 +1270,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait) * 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); + if (sb_start_write_trylock(sb)) + sb_end_write(sb); else return 0; trans = btrfs_start_transaction(root, 0); @@ -1220,7 +1285,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) { struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb); - char *compress_type; + const char *compress_type; if (btrfs_test_opt(info, DEGRADED)) seq_puts(seq, ",degraded"); @@ -1234,18 +1299,15 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_printf(seq, ",max_inline=%llu", info->max_inline); if (info->thread_pool_size != min_t(unsigned long, num_online_cpus() + 2, 8)) - seq_printf(seq, ",thread_pool=%d", info->thread_pool_size); + seq_printf(seq, ",thread_pool=%u", info->thread_pool_size); if (btrfs_test_opt(info, COMPRESS)) { - if (info->compress_type == BTRFS_COMPRESS_ZLIB) - compress_type = "zlib"; - else if (info->compress_type == BTRFS_COMPRESS_LZO) - compress_type = "lzo"; - else - compress_type = "zstd"; + compress_type = btrfs_compress_type2str(info->compress_type); if (btrfs_test_opt(info, FORCE_COMPRESS)) seq_printf(seq, ",compress-force=%s", compress_type); else seq_printf(seq, ",compress=%s", compress_type); + if (info->compress_level) + seq_printf(seq, ":%d", info->compress_level); } if (btrfs_test_opt(info, NOSSD)) seq_puts(seq, ",nossd"); @@ -1261,7 +1323,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",flushoncommit"); if (btrfs_test_opt(info, DISCARD)) seq_puts(seq, ",discard"); - if (!(info->sb->s_flags & MS_POSIXACL)) + if (!(info->sb->s_flags & SB_POSIXACL)) seq_puts(seq, ",noacl"); if (btrfs_test_opt(info, SPACE_CACHE)) seq_puts(seq, ",space_cache"); @@ -1293,18 +1355,19 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) info->check_integrity_print_mask); #endif if (info->metadata_ratio) - seq_printf(seq, ",metadata_ratio=%d", - info->metadata_ratio); + seq_printf(seq, ",metadata_ratio=%u", info->metadata_ratio); if (btrfs_test_opt(info, 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); + seq_printf(seq, ",commit=%u", info->commit_interval); #ifdef CONFIG_BTRFS_DEBUG if (btrfs_test_opt(info, FRAGMENT_DATA)) seq_puts(seq, ",fragment=data"); if (btrfs_test_opt(info, FRAGMENT_METADATA)) seq_puts(seq, ",fragment=metadata"); #endif + if (btrfs_test_opt(info, REF_VERIFY)) + seq_puts(seq, ",ref_verify"); seq_printf(seq, ",subvolid=%llu", BTRFS_I(d_inode(dentry))->root->root_key.objectid); seq_puts(seq, ",subvol="); @@ -1338,86 +1401,12 @@ static inline int is_subvolume_inode(struct inode *inode) return 0; } -/* - * 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) -{ - char *buf, *dst, *sep; - - if (!args) - return kstrdup("subvolid=0", GFP_KERNEL); - - /* The worst case is that we add ",subvolid=0" to the end. */ - buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1, - GFP_KERNEL); - if (!buf) - return NULL; - - 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"); - - return buf; -} - static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid, - int flags, const char *device_name, - char *data) + const char *device_name, struct vfsmount *mnt) { struct dentry *root; - struct vfsmount *mnt = NULL; - char *newargs; int ret; - newargs = setup_root_args(data); - 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), @@ -1473,7 +1462,6 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid, out: mntput(mnt); - kfree(newargs); kfree(subvol_name); return root; } @@ -1531,11 +1519,11 @@ static int setup_security_options(struct btrfs_fs_info *fs_info, /* * Find a superblock for the given device / mount point. * - * Note: This is based on get_sb_bdev from fs/super.c with a few additions - * for multiple device setup. Make sure to keep it in sync. + * Note: This is based on mount_bdev from fs/super.c with a few additions + * for multiple device setup. Make sure to keep it in sync. */ -static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, - const char *device_name, void *data) +static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, + int flags, const char *device_name, void *data) { struct block_device *bdev = NULL; struct super_block *s; @@ -1543,27 +1531,17 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, 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; int error = 0; - if (!(flags & MS_RDONLY)) + if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; error = btrfs_parse_early_options(data, mode, fs_type, - &subvol_name, &subvol_objectid, &fs_devices); if (error) { - kfree(subvol_name); return ERR_PTR(error); } - 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); @@ -1581,7 +1559,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, * it for searching for existing supers, so this lets us do that and * then open_ctree will properly initialize everything later. */ - fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); + fs_info = kvzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); if (!fs_info) { error = -ENOMEM; goto error_sec_opts; @@ -1601,13 +1579,13 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error) goto error_fs_info; - if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) { + if (!(flags & SB_RDONLY) && fs_devices->rw_devices == 0) { error = -EACCES; goto error_close_devices; } bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC, + s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | SB_NOSEC, fs_info); if (IS_ERR(s)) { error = PTR_ERR(s); @@ -1617,7 +1595,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (s->s_root) { btrfs_close_devices(fs_devices); free_fs_info(fs_info); - if ((flags ^ s->s_flags) & MS_RDONLY) + if ((flags ^ s->s_flags) & SB_RDONLY) error = -EBUSY; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); @@ -1647,8 +1625,86 @@ error_sec_opts: return ERR_PTR(error); } +/* + * Mount function which is called by VFS layer. + * + * In order to allow mounting a subvolume directly, btrfs uses mount_subtree() + * which needs vfsmount* of device's root (/). This means device's root has to + * be mounted internally in any case. + * + * Operation flow: + * 1. Parse subvol id related options for later use in mount_subvol(). + * + * 2. Mount device's root (/) by calling vfs_kern_mount(). + * + * NOTE: vfs_kern_mount() is used by VFS to call btrfs_mount() in the + * first place. In order to avoid calling btrfs_mount() again, we use + * different file_system_type which is not registered to VFS by + * register_filesystem() (btrfs_root_fs_type). As a result, + * btrfs_mount_root() is called. The return value will be used by + * mount_subtree() in mount_subvol(). + * + * 3. Call mount_subvol() to get the dentry of subvolume. Since there is + * "btrfs subvolume set-default", mount_subvol() is called always. + */ +static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, + const char *device_name, void *data) +{ + struct vfsmount *mnt_root; + struct dentry *root; + fmode_t mode = FMODE_READ; + char *subvol_name = NULL; + u64 subvol_objectid = 0; + int error = 0; + + if (!(flags & SB_RDONLY)) + mode |= FMODE_WRITE; + + error = btrfs_parse_subvol_options(data, mode, + &subvol_name, &subvol_objectid); + if (error) { + kfree(subvol_name); + return ERR_PTR(error); + } + + /* mount device's root (/) */ + mnt_root = vfs_kern_mount(&btrfs_root_fs_type, flags, device_name, data); + if (PTR_ERR_OR_ZERO(mnt_root) == -EBUSY) { + if (flags & SB_RDONLY) { + mnt_root = vfs_kern_mount(&btrfs_root_fs_type, + flags & ~SB_RDONLY, device_name, data); + } else { + mnt_root = vfs_kern_mount(&btrfs_root_fs_type, + flags | SB_RDONLY, device_name, data); + if (IS_ERR(mnt_root)) { + root = ERR_CAST(mnt_root); + goto out; + } + + down_write(&mnt_root->mnt_sb->s_umount); + error = btrfs_remount(mnt_root->mnt_sb, &flags, NULL); + up_write(&mnt_root->mnt_sb->s_umount); + if (error < 0) { + root = ERR_PTR(error); + mntput(mnt_root); + goto out; + } + } + } + if (IS_ERR(mnt_root)) { + root = ERR_CAST(mnt_root); + goto out; + } + + /* mount_subvol() will free subvol_name and mnt_root */ + root = mount_subvol(subvol_name, subvol_objectid, device_name, mnt_root); + +out: + return root; +} + static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, - int new_pool_size, int old_pool_size) + u32 new_pool_size, u32 old_pool_size) { if (new_pool_size == old_pool_size) return; @@ -1684,11 +1740,11 @@ static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info, { if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) && (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) || - (flags & MS_RDONLY))) { + (flags & SB_RDONLY))) { /* wait for any defraggers to finish */ wait_event(fs_info->transaction_wait, (atomic_read(&fs_info->defrag_running) == 0)); - if (flags & MS_RDONLY) + if (flags & SB_RDONLY) sync_filesystem(fs_info->sb); } } @@ -1716,8 +1772,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) unsigned long old_opts = fs_info->mount_opt; unsigned long old_compress_type = fs_info->compress_type; u64 old_max_inline = fs_info->max_inline; - int old_thread_pool_size = fs_info->thread_pool_size; - unsigned int old_metadata_ratio = fs_info->metadata_ratio; + u32 old_thread_pool_size = fs_info->thread_pool_size; + u32 old_metadata_ratio = fs_info->metadata_ratio; int ret; sync_filesystem(sb); @@ -1748,10 +1804,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_resize_thread_pool(fs_info, fs_info->thread_pool_size, old_thread_pool_size); - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { /* * this also happens on 'umount -rf' or on shutdown, when * the filesystem is busy. @@ -1763,10 +1819,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) /* avoid complains from lockdep et al. */ up(&fs_info->uuid_tree_rescan_sem); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; /* - * Setting MS_RDONLY will put the cleaner thread to + * Setting SB_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 @@ -1793,7 +1849,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } - if (!btrfs_check_rw_degradable(fs_info)) { + if (!btrfs_check_rw_degradable(fs_info, NULL)) { btrfs_warn(fs_info, "too many missing devices, writeable remount is not allowed"); ret = -EACCES; @@ -1838,7 +1894,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } } - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; set_bit(BTRFS_FS_OPEN, &fs_info->flags); } @@ -1848,9 +1904,9 @@ out: return 0; restore: - /* We've hit an error - don't reset MS_RDONLY */ + /* We've hit an error - don't reset SB_RDONLY */ if (sb_rdonly(sb)) - old_flags |= MS_RDONLY; + old_flags |= SB_RDONLY; sb->s_flags = old_flags; fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; @@ -1945,8 +2001,10 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, 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) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, + &device->dev_state) || + !device->bdev || + test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) continue; if (i >= nr_devices) @@ -2112,7 +2170,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * succeed even if the Avail is zero. But this is better than the other * way around. */ - thresh = 4 * 1024 * 1024; + thresh = SZ_4M; if (!mixed && total_free_meta - thresh < block_rsv->size) buf->f_bavail = 0; @@ -2147,6 +2205,15 @@ static struct file_system_type btrfs_fs_type = { .kill_sb = btrfs_kill_super, .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA, }; + +static struct file_system_type btrfs_root_fs_type = { + .owner = THIS_MODULE, + .name = "btrfs", + .mount = btrfs_mount_root, + .kill_sb = btrfs_kill_super, + .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA, +}; + MODULE_ALIAS_FS("btrfs"); static int btrfs_control_open(struct inode *inode, struct file *file) @@ -2180,11 +2247,11 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case BTRFS_IOC_SCAN_DEV: ret = btrfs_scan_one_device(vol->name, FMODE_READ, - &btrfs_fs_type, &fs_devices); + &btrfs_root_fs_type, &fs_devices); break; case BTRFS_IOC_DEVICES_READY: ret = btrfs_scan_one_device(vol->name, FMODE_READ, - &btrfs_fs_type, &fs_devices); + &btrfs_root_fs_type, &fs_devices); if (ret) break; ret = !(fs_devices->num_devices == fs_devices->total_devices); @@ -2237,12 +2304,19 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) struct list_head *head; struct rcu_string *name; - mutex_lock(&fs_info->fs_devices->device_list_mutex); + /* + * Lightweight locking of the devices. We should not need + * device_list_mutex here as we only read the device data and the list + * is protected by RCU. Even if a device is deleted during the list + * traversals, we'll get valid data, the freeing callback will wait at + * least until until the rcu_read_unlock. + */ + rcu_read_lock(); cur_devices = fs_info->fs_devices; while (cur_devices) { head = &cur_devices->devices; - list_for_each_entry(dev, head, dev_list) { - if (dev->missing) + list_for_each_entry_rcu(dev, head, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->name) continue; @@ -2253,14 +2327,12 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) } if (first_dev) { - rcu_read_lock(); name = rcu_dereference(first_dev->name); seq_escape(m, name->str, " \t\n\\"); - rcu_read_unlock(); } else { WARN_ON(1); } - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + rcu_read_unlock(); return 0; } @@ -2297,17 +2369,17 @@ static struct miscdevice btrfs_misc = { MODULE_ALIAS_MISCDEV(BTRFS_MINOR); MODULE_ALIAS("devname:btrfs-control"); -static int btrfs_interface_init(void) +static int __init btrfs_interface_init(void) { return misc_register(&btrfs_misc); } -static void btrfs_interface_exit(void) +static __cold void btrfs_interface_exit(void) { misc_deregister(&btrfs_misc); } -static void btrfs_print_mod_info(void) +static void __init btrfs_print_mod_info(void) { pr_info("Btrfs loaded, crc32c=%s" #ifdef CONFIG_BTRFS_DEBUG @@ -2319,23 +2391,22 @@ static void btrfs_print_mod_info(void) #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY ", integrity-checker=on" #endif +#ifdef CONFIG_BTRFS_FS_REF_VERIFY + ", ref-verify=on" +#endif "\n", - btrfs_crc32c_impl()); + crc32c_impl()); } static int __init init_btrfs_fs(void) { int err; - err = btrfs_hash_init(); - if (err) - return err; - btrfs_props_init(); err = btrfs_init_sysfs(); if (err) - goto free_hash; + return err; btrfs_init_compress(); @@ -2416,8 +2487,7 @@ free_cachep: free_compress: btrfs_exit_compress(); btrfs_exit_sysfs(); -free_hash: - btrfs_hash_exit(); + return err; } @@ -2437,7 +2507,6 @@ static void __exit exit_btrfs_fs(void) btrfs_exit_sysfs(); btrfs_cleanup_fs_uuids(); btrfs_exit_compress(); - btrfs_hash_exit(); } late_initcall(init_btrfs_fs); |