diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-08-31 15:18:15 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-08-31 15:18:15 -0700 |
commit | 3ef96fcfd50b9980470efb1acec7c27a60b98e87 (patch) | |
tree | 655bb734384a6ee0173a0b099b0c1785717b2021 /fs/jbd2/journal.c | |
parent | 659b3613fc635fb1813fb3006680876b24d86919 (diff) | |
parent | 768d612f79822d30a1e7d132a4d4b05337ce42ec (diff) |
Merge tag 'ext4_for_linus-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o:
"Many ext4 and jbd2 cleanups and bug fixes:
- Cleanups in the ext4 remount code when going to and from read-only
- Cleanups in ext4's multiblock allocator
- Cleanups in the jbd2 setup/mounting code paths
- Performance improvements when appending to a delayed allocation file
- Miscellaneous syzbot and other bug fixes"
* tag 'ext4_for_linus-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (60 commits)
ext4: fix slab-use-after-free in ext4_es_insert_extent()
libfs: remove redundant checks of s_encoding
ext4: remove redundant checks of s_encoding
ext4: reject casefold inode flag without casefold feature
ext4: use LIST_HEAD() to initialize the list_head in mballoc.c
ext4: do not mark inode dirty every time when appending using delalloc
ext4: rename s_error_work to s_sb_upd_work
ext4: add periodic superblock update check
ext4: drop dio overwrite only flag and associated warning
ext4: add correct group descriptors and reserved GDT blocks to system zone
ext4: remove unused function declaration
ext4: mballoc: avoid garbage value from err
ext4: use sbi instead of EXT4_SB(sb) in ext4_mb_new_blocks_simple()
ext4: change the type of blocksize in ext4_mb_init_cache()
ext4: fix unttached inode after power cut with orphan file feature enabled
jbd2: correct the end of the journal recovery scan range
ext4: ext4_get_{dev}_journal return proper error value
ext4: cleanup ext4_get_dev_journal() and ext4_get_journal()
jbd2: jbd2_journal_init_{dev,inode} return proper error return value
jbd2: drop useless error tag in jbd2_journal_wipe()
...
Diffstat (limited to 'fs/jbd2/journal.c')
-rw-r--r-- | fs/jbd2/journal.c | 484 |
1 files changed, 230 insertions, 254 deletions
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 1b5a45ab62b0..768fa05bcbed 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -115,14 +115,6 @@ void __jbd2_debug(int level, const char *file, const char *func, #endif /* Checksumming functions */ -static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) -{ - if (!jbd2_journal_has_csum_v2or3_feature(j)) - return 1; - - return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; -} - static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) { __u32 csum; @@ -1334,6 +1326,189 @@ static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, } /* + * If the journal init or create aborts, we need to mark the journal + * superblock as being NULL to prevent the journal destroy from writing + * back a bogus superblock. + */ +static void journal_fail_superblock(journal_t *journal) +{ + struct buffer_head *bh = journal->j_sb_buffer; + brelse(bh); + journal->j_sb_buffer = NULL; +} + +/* + * Check the superblock for a given journal, performing initial + * validation of the format. + */ +static int journal_check_superblock(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + int num_fc_blks; + int err = -EINVAL; + + if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || + sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { + printk(KERN_WARNING "JBD2: no valid journal superblock found\n"); + return err; + } + + if (be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V1 && + be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V2) { + printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); + return err; + } + + if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { + printk(KERN_WARNING "JBD2: journal file too short\n"); + return err; + } + + if (be32_to_cpu(sb->s_first) == 0 || + be32_to_cpu(sb->s_first) >= journal->j_total_len) { + printk(KERN_WARNING + "JBD2: Invalid start block of journal: %u\n", + be32_to_cpu(sb->s_first)); + return err; + } + + /* + * If this is a V2 superblock, then we have to check the + * features flags on it. + */ + if (!jbd2_format_support_feature(journal)) + return 0; + + if ((sb->s_feature_ro_compat & + ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || + (sb->s_feature_incompat & + ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { + printk(KERN_WARNING "JBD2: Unrecognised features on journal\n"); + return err; + } + + num_fc_blks = jbd2_has_feature_fast_commit(journal) ? + jbd2_journal_get_num_fc_blks(sb) : 0; + if (be32_to_cpu(sb->s_maxlen) < JBD2_MIN_JOURNAL_BLOCKS || + be32_to_cpu(sb->s_maxlen) - JBD2_MIN_JOURNAL_BLOCKS < num_fc_blks) { + printk(KERN_ERR "JBD2: journal file too short %u,%d\n", + be32_to_cpu(sb->s_maxlen), num_fc_blks); + return err; + } + + if (jbd2_has_feature_csum2(journal) && + jbd2_has_feature_csum3(journal)) { + /* Can't have checksum v2 and v3 at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " + "at the same time!\n"); + return err; + } + + if (jbd2_journal_has_csum_v2or3_feature(journal) && + jbd2_has_feature_checksum(journal)) { + /* Can't have checksum v1 and v2 on at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " + "at the same time!\n"); + return err; + } + + /* Load the checksum driver */ + if (jbd2_journal_has_csum_v2or3_feature(journal)) { + if (sb->s_checksum_type != JBD2_CRC32C_CHKSUM) { + printk(KERN_ERR "JBD2: Unknown checksum type\n"); + return err; + } + + journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); + err = PTR_ERR(journal->j_chksum_driver); + journal->j_chksum_driver = NULL; + return err; + } + /* Check superblock checksum */ + if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { + printk(KERN_ERR "JBD2: journal checksum error\n"); + err = -EFSBADCRC; + return err; + } + } + + return 0; +} + +static int journal_revoke_records_per_block(journal_t *journal) +{ + int record_size; + int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); + + if (jbd2_has_feature_64bit(journal)) + record_size = 8; + else + record_size = 4; + + if (jbd2_journal_has_csum_v2or3(journal)) + space -= sizeof(struct jbd2_journal_block_tail); + return space / record_size; +} + +/* + * Load the on-disk journal superblock and read the key fields into the + * journal_t. + */ +static int journal_load_superblock(journal_t *journal) +{ + int err; + struct buffer_head *bh; + journal_superblock_t *sb; + + bh = getblk_unmovable(journal->j_dev, journal->j_blk_offset, + journal->j_blocksize); + if (bh) + err = bh_read(bh, 0); + if (!bh || err < 0) { + pr_err("%s: Cannot read journal superblock\n", __func__); + brelse(bh); + return -EIO; + } + + journal->j_sb_buffer = bh; + sb = (journal_superblock_t *)bh->b_data; + journal->j_superblock = sb; + err = journal_check_superblock(journal); + if (err) { + journal_fail_superblock(journal); + return err; + } + + journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); + journal->j_tail = be32_to_cpu(sb->s_start); + journal->j_first = be32_to_cpu(sb->s_first); + journal->j_errno = be32_to_cpu(sb->s_errno); + journal->j_last = be32_to_cpu(sb->s_maxlen); + + if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) + journal->j_total_len = be32_to_cpu(sb->s_maxlen); + /* Precompute checksum seed for all metadata */ + if (jbd2_journal_has_csum_v2or3(journal)) + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); + + if (jbd2_has_feature_fast_commit(journal)) { + journal->j_fc_last = be32_to_cpu(sb->s_maxlen); + journal->j_last = journal->j_fc_last - + jbd2_journal_get_num_fc_blks(sb); + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + } + + return 0; +} + + +/* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing * journal blocks from disk. */ @@ -1349,12 +1524,21 @@ static journal_t *journal_init_common(struct block_device *bdev, static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; int err; - struct buffer_head *bh; int n; journal = kzalloc(sizeof(*journal), GFP_KERNEL); if (!journal) - return NULL; + return ERR_PTR(-ENOMEM); + + journal->j_blocksize = blocksize; + journal->j_dev = bdev; + journal->j_fs_dev = fs_dev; + journal->j_blk_offset = start; + journal->j_total_len = len; + + err = journal_load_superblock(journal); + if (err) + goto err_cleanup; init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_done_commit); @@ -1367,12 +1551,15 @@ static journal_t *journal_init_common(struct block_device *bdev, mutex_init(&journal->j_checkpoint_mutex); spin_lock_init(&journal->j_revoke_lock); spin_lock_init(&journal->j_list_lock); + spin_lock_init(&journal->j_history_lock); rwlock_init(&journal->j_state_lock); journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); journal->j_min_batch_time = 0; journal->j_max_batch_time = 15000; /* 15ms */ atomic_set(&journal->j_reserved_credits, 0); + lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", + &jbd2_trans_commit_key, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; @@ -1382,18 +1569,11 @@ static journal_t *journal_init_common(struct block_device *bdev, if (err) goto err_cleanup; - spin_lock_init(&journal->j_history_lock); - - lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", - &jbd2_trans_commit_key, 0); - - /* journal descriptor can store up to n blocks -bzzz */ - journal->j_blocksize = blocksize; - journal->j_dev = bdev; - journal->j_fs_dev = fs_dev; - journal->j_blk_offset = start; - journal->j_total_len = len; - /* We need enough buffers to write out full descriptor block. */ + /* + * journal descriptor can store up to n blocks, we need enough + * buffers to write out full descriptor block. + */ + err = -ENOMEM; n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; journal->j_fc_wbuf = NULL; @@ -1402,37 +1582,30 @@ static journal_t *journal_init_common(struct block_device *bdev, if (!journal->j_wbuf) goto err_cleanup; - bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); - if (!bh) { - pr_err("%s: Cannot get buffer for journal superblock\n", - __func__); + err = percpu_counter_init(&journal->j_checkpoint_jh_count, 0, + GFP_KERNEL); + if (err) goto err_cleanup; - } - journal->j_sb_buffer = bh; - journal->j_superblock = (journal_superblock_t *)bh->b_data; journal->j_shrink_transaction = NULL; journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan; journal->j_shrinker.count_objects = jbd2_journal_shrink_count; journal->j_shrinker.seeks = DEFAULT_SEEKS; journal->j_shrinker.batch = journal->j_max_transaction_buffers; - - if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL)) + err = register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + if (err) goto err_cleanup; - if (register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", - MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev))) { - percpu_counter_destroy(&journal->j_checkpoint_jh_count); - goto err_cleanup; - } return journal; err_cleanup: - brelse(journal->j_sb_buffer); + percpu_counter_destroy(&journal->j_checkpoint_jh_count); kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); + journal_fail_superblock(journal); kfree(journal); - return NULL; + return ERR_PTR(err); } /* jbd2_journal_init_dev and jbd2_journal_init_inode: @@ -1465,8 +1638,8 @@ journal_t *jbd2_journal_init_dev(struct block_device *bdev, journal_t *journal; journal = journal_init_common(bdev, fs_dev, start, len, blocksize); - if (!journal) - return NULL; + if (IS_ERR(journal)) + return ERR_CAST(journal); snprintf(journal->j_devname, sizeof(journal->j_devname), "%pg", journal->j_dev); @@ -1492,11 +1665,9 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) blocknr = 0; err = bmap(inode, &blocknr); - if (err || !blocknr) { - pr_err("%s: Cannot locate journal superblock\n", - __func__); - return NULL; + pr_err("%s: Cannot locate journal superblock\n", __func__); + return err ? ERR_PTR(err) : ERR_PTR(-EINVAL); } jbd2_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", @@ -1506,8 +1677,8 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) journal = journal_init_common(inode->i_sb->s_bdev, inode->i_sb->s_bdev, blocknr, inode->i_size >> inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); - if (!journal) - return NULL; + if (IS_ERR(journal)) + return ERR_CAST(journal); journal->j_inode = inode; snprintf(journal->j_devname, sizeof(journal->j_devname), @@ -1519,18 +1690,6 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) } /* - * If the journal init or create aborts, we need to mark the journal - * superblock as being NULL to prevent the journal destroy from writing - * back a bogus superblock. - */ -static void journal_fail_superblock(journal_t *journal) -{ - struct buffer_head *bh = journal->j_sb_buffer; - brelse(bh); - journal->j_sb_buffer = NULL; -} - -/* * Given a journal_t structure, initialise the various fields for * startup of a new journaling session. We use this both when creating * a journal, and after recovering an old journal to reset it for @@ -1886,163 +2045,6 @@ void jbd2_journal_update_sb_errno(journal_t *journal) } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); -static int journal_revoke_records_per_block(journal_t *journal) -{ - int record_size; - int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); - - if (jbd2_has_feature_64bit(journal)) - record_size = 8; - else - record_size = 4; - - if (jbd2_journal_has_csum_v2or3(journal)) - space -= sizeof(struct jbd2_journal_block_tail); - return space / record_size; -} - -/* - * Read the superblock for a given journal, performing initial - * validation of the format. - */ -static int journal_get_superblock(journal_t *journal) -{ - struct buffer_head *bh; - journal_superblock_t *sb; - int err; - - bh = journal->j_sb_buffer; - - J_ASSERT(bh != NULL); - if (buffer_verified(bh)) - return 0; - - err = bh_read(bh, 0); - if (err < 0) { - printk(KERN_ERR - "JBD2: IO error reading journal superblock\n"); - goto out; - } - - sb = journal->j_superblock; - - err = -EINVAL; - - if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || - sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { - printk(KERN_WARNING "JBD2: no valid journal superblock found\n"); - goto out; - } - - if (be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V1 && - be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V2) { - printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); - goto out; - } - - if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { - printk(KERN_WARNING "JBD2: journal file too short\n"); - goto out; - } - - if (be32_to_cpu(sb->s_first) == 0 || - be32_to_cpu(sb->s_first) >= journal->j_total_len) { - printk(KERN_WARNING - "JBD2: Invalid start block of journal: %u\n", - be32_to_cpu(sb->s_first)); - goto out; - } - - if (jbd2_has_feature_csum2(journal) && - jbd2_has_feature_csum3(journal)) { - /* Can't have checksum v2 and v3 at the same time! */ - printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " - "at the same time!\n"); - goto out; - } - - if (jbd2_journal_has_csum_v2or3_feature(journal) && - jbd2_has_feature_checksum(journal)) { - /* Can't have checksum v1 and v2 on at the same time! */ - printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " - "at the same time!\n"); - goto out; - } - - if (!jbd2_verify_csum_type(journal, sb)) { - printk(KERN_ERR "JBD2: Unknown checksum type\n"); - goto out; - } - - /* Load the checksum driver */ - if (jbd2_journal_has_csum_v2or3_feature(journal)) { - journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); - err = PTR_ERR(journal->j_chksum_driver); - journal->j_chksum_driver = NULL; - goto out; - } - /* Check superblock checksum */ - if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { - printk(KERN_ERR "JBD2: journal checksum error\n"); - err = -EFSBADCRC; - goto out; - } - } - set_buffer_verified(bh); - return 0; - -out: - journal_fail_superblock(journal); - return err; -} - -/* - * Load the on-disk journal superblock and read the key fields into the - * journal_t. - */ - -static int load_superblock(journal_t *journal) -{ - int err; - journal_superblock_t *sb; - int num_fc_blocks; - - err = journal_get_superblock(journal); - if (err) - return err; - - sb = journal->j_superblock; - - journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); - journal->j_tail = be32_to_cpu(sb->s_start); - journal->j_first = be32_to_cpu(sb->s_first); - journal->j_errno = be32_to_cpu(sb->s_errno); - journal->j_last = be32_to_cpu(sb->s_maxlen); - - if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) - journal->j_total_len = be32_to_cpu(sb->s_maxlen); - /* Precompute checksum seed for all metadata */ - if (jbd2_journal_has_csum_v2or3(journal)) - journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, - sizeof(sb->s_uuid)); - journal->j_revoke_records_per_block = - journal_revoke_records_per_block(journal); - - if (jbd2_has_feature_fast_commit(journal)) { - journal->j_fc_last = be32_to_cpu(sb->s_maxlen); - num_fc_blocks = jbd2_journal_get_num_fc_blks(sb); - if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) - journal->j_last = journal->j_fc_last - num_fc_blocks; - journal->j_fc_first = journal->j_last + 1; - journal->j_fc_off = 0; - } - - return 0; -} - - /** * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. @@ -2054,28 +2056,7 @@ static int load_superblock(journal_t *journal) int jbd2_journal_load(journal_t *journal) { int err; - journal_superblock_t *sb; - - err = load_superblock(journal); - if (err) - return err; - - sb = journal->j_superblock; - - /* - * If this is a V2 superblock, then we have to check the - * features flags on it. - */ - if (jbd2_format_support_feature(journal)) { - if ((sb->s_feature_ro_compat & - ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || - (sb->s_feature_incompat & - ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { - printk(KERN_WARNING - "JBD2: Unrecognised features on journal\n"); - return -EINVAL; - } - } + journal_superblock_t *sb = journal->j_superblock; /* * Create a slab for this blocksize @@ -2086,8 +2067,11 @@ int jbd2_journal_load(journal_t *journal) /* Let the recovery code check whether it needs to recover any * data from the journal. */ - if (jbd2_journal_recover(journal)) - goto recovery_error; + err = jbd2_journal_recover(journal); + if (err) { + pr_warn("JBD2: journal recovery failed\n"); + return err; + } if (journal->j_failed_commit) { printk(KERN_ERR "JBD2: journal transaction %u on %s " @@ -2104,15 +2088,14 @@ int jbd2_journal_load(journal_t *journal) /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ - if (journal_reset(journal)) - goto recovery_error; + err = journal_reset(journal); + if (err) { + pr_warn("JBD2: journal reset failed\n"); + return err; + } journal->j_flags |= JBD2_LOADED; return 0; - -recovery_error: - printk(KERN_WARNING "JBD2: recovery failed\n"); - return -EIO; } /** @@ -2224,8 +2207,6 @@ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, if (!compat && !ro && !incompat) return 1; - if (journal_get_superblock(journal)) - return 0; if (!jbd2_format_support_feature(journal)) return 0; @@ -2515,16 +2496,12 @@ out: int jbd2_journal_wipe(journal_t *journal, int write) { - int err = 0; + int err; J_ASSERT (!(journal->j_flags & JBD2_LOADED)); - err = load_superblock(journal); - if (err) - return err; - if (!journal->j_tail) - goto no_recovery; + return 0; printk(KERN_WARNING "JBD2: %s recovery information on journal\n", write ? "Clearing" : "Ignoring"); @@ -2537,7 +2514,6 @@ int jbd2_journal_wipe(journal_t *journal, int write) mutex_unlock(&journal->j_checkpoint_mutex); } - no_recovery: return err; } |