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 | |
parent | 659b3613fc635fb1813fb3006680876b24d86919 (diff) | |
parent | 768d612f79822d30a1e7d132a4d4b05337ce42ec (diff) | |
download | linux-starfive-3ef96fcfd50b9980470efb1acec7c27a60b98e87.tar.gz linux-starfive-3ef96fcfd50b9980470efb1acec7c27a60b98e87.tar.bz2 linux-starfive-3ef96fcfd50b9980470efb1acec7c27a60b98e87.zip |
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()
...
-rw-r--r-- | fs/ext4/balloc.c | 15 | ||||
-rw-r--r-- | fs/ext4/block_validity.c | 8 | ||||
-rw-r--r-- | fs/ext4/crypto.c | 4 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 32 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.c | 5 | ||||
-rw-r--r-- | fs/ext4/extents_status.c | 44 | ||||
-rw-r--r-- | fs/ext4/file.c | 38 | ||||
-rw-r--r-- | fs/ext4/fsync.c | 9 | ||||
-rw-r--r-- | fs/ext4/hash.c | 2 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 8 | ||||
-rw-r--r-- | fs/ext4/inline.c | 2 | ||||
-rw-r--r-- | fs/ext4/inode.c | 124 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 2 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 200 | ||||
-rw-r--r-- | fs/ext4/mballoc.h | 14 | ||||
-rw-r--r-- | fs/ext4/mmp.c | 2 | ||||
-rw-r--r-- | fs/ext4/namei.c | 17 | ||||
-rw-r--r-- | fs/ext4/page-io.c | 2 | ||||
-rw-r--r-- | fs/ext4/super.c | 308 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 2 | ||||
-rw-r--r-- | fs/jbd2/checkpoint.c | 34 | ||||
-rw-r--r-- | fs/jbd2/journal.c | 484 | ||||
-rw-r--r-- | fs/jbd2/recovery.c | 12 | ||||
-rw-r--r-- | fs/libfs.c | 14 | ||||
-rw-r--r-- | fs/ocfs2/journal.c | 8 | ||||
-rw-r--r-- | include/linux/jbd2.h | 5 |
26 files changed, 717 insertions, 678 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 1f72f977c6db..79b20d6ae39e 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -913,11 +913,11 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) } /* - * This function returns the number of file system metadata clusters at + * This function returns the number of file system metadata blocks at * the beginning of a block group, including the reserved gdt blocks. */ -static unsigned ext4_num_base_meta_clusters(struct super_block *sb, - ext4_group_t block_group) +unsigned int ext4_num_base_meta_blocks(struct super_block *sb, + ext4_group_t block_group) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned num; @@ -935,8 +935,15 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb, } else { /* For META_BG_BLOCK_GROUPS */ num += ext4_bg_num_gdb_meta(sb, block_group); } - return EXT4_NUM_B2C(sbi, num); + return num; } + +static unsigned int ext4_num_base_meta_clusters(struct super_block *sb, + ext4_group_t block_group) +{ + return EXT4_NUM_B2C(EXT4_SB(sb), ext4_num_base_meta_blocks(sb, block_group)); +} + /** * ext4_inode_to_goal_block - return a hint for block allocation * @inode: inode for block allocation diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 5504f72bbbbe..6fe3c941b565 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -215,7 +215,6 @@ int ext4_setup_system_zone(struct super_block *sb) struct ext4_system_blocks *system_blks; struct ext4_group_desc *gdp; ext4_group_t i; - int flex_size = ext4_flex_bg_size(sbi); int ret; system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); @@ -223,12 +222,13 @@ int ext4_setup_system_zone(struct super_block *sb) return -ENOMEM; for (i=0; i < ngroups; i++) { + unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i); + cond_resched(); - if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) { + if (meta_blks != 0) { ret = add_system_zone(system_blks, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1, 0); + meta_blks, 0); if (ret) goto err; } diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index e20ac0654b3f..453d4da5de52 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -33,6 +33,8 @@ int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); + if (err) + ext4_fname_free_filename(fname); #endif return err; } @@ -51,6 +53,8 @@ int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); + if (err) + ext4_fname_free_filename(fname); #endif return err; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 481491e892df..9418359b1d9d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -176,9 +176,6 @@ enum criteria { EXT4_MB_NUM_CRS }; -/* criteria below which we use fast block scanning and avoid unnecessary IO */ -#define CR_FAST CR_GOAL_LEN_SLOW - /* * Flags used in mballoc's allocation_context flags field. * @@ -1241,6 +1238,7 @@ struct ext4_inode_info { #define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group * scanning in mballoc */ +#define EXT4_MOUNT2_ABORT 0x00000100 /* Abort filesystem */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1258,10 +1256,8 @@ struct ext4_inode_info { #define ext4_test_and_set_bit __test_and_set_bit_le #define ext4_set_bit __set_bit_le -#define ext4_set_bit_atomic ext2_set_bit_atomic #define ext4_test_and_clear_bit __test_and_clear_bit_le #define ext4_clear_bit __clear_bit_le -#define ext4_clear_bit_atomic ext2_clear_bit_atomic #define ext4_test_bit test_bit_le #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le @@ -1708,10 +1704,13 @@ struct ext4_sb_info { const char *s_last_error_func; time64_t s_last_error_time; /* - * If we are in a context where we cannot update error information in - * the on-disk superblock, we queue this work to do it. + * If we are in a context where we cannot update the on-disk + * superblock, we queue the work here. This is used to update + * the error information in the superblock, and for periodic + * updates of the superblock called from the commit callback + * function. */ - struct work_struct s_error_work; + struct work_struct s_sb_upd_work; /* Ext4 fast commit sub transaction ID */ atomic_t s_fc_subtid; @@ -1804,7 +1803,6 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) */ enum { EXT4_MF_MNTDIR_SAMPLED, - EXT4_MF_FS_ABORTED, /* Fatal error detected */ EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */ }; @@ -2228,9 +2226,9 @@ extern int ext4_feature_set_ok(struct super_block *sb, int readonly); #define EXT4_FLAGS_SHUTDOWN 1 #define EXT4_FLAGS_BDEV_IS_DAX 2 -static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) +static inline int ext4_forced_shutdown(struct super_block *sb) { - return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); + return test_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); } /* @@ -2708,7 +2706,6 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags); extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); -extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); @@ -2864,7 +2861,6 @@ extern void ext4_free_inode(handle_t *, struct inode *); extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); extern unsigned long ext4_count_dirs(struct super_block *); -extern void ext4_check_inodes_bitmap(struct super_block *); extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap); extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int barrier); @@ -2907,7 +2903,6 @@ extern int ext4_mb_init(struct super_block *); extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); -extern int ext4_mb_reserve_blocks(struct super_block *, int); extern void ext4_discard_preallocations(struct inode *, unsigned int); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); @@ -2930,6 +2925,10 @@ extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid); extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, int state); +static inline bool ext4_mb_cr_expensive(enum criteria cr) +{ + return cr >= CR_GOAL_LEN_SLOW; +} /* inode.c */ void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, @@ -2983,7 +2982,6 @@ extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); extern int ext4_file_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); -extern int ext4_sync_inode(handle_t *, struct inode *); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); @@ -3090,6 +3088,8 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno, extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); +extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb, + ext4_group_t block_group); extern __printf(7, 8) void __ext4_error(struct super_block *, const char *, unsigned int, bool, @@ -3531,8 +3531,6 @@ extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* inline.c */ extern int ext4_get_max_inline_size(struct inode *inode); extern int ext4_find_inline_data_nolock(struct inode *inode); -extern int ext4_init_inline_data(handle_t *handle, struct inode *inode, - unsigned int len); extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode); int ext4_readpage_inline(struct inode *inode, struct folio *folio); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index b38d59581411..d1a2e6624401 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -67,11 +67,12 @@ static int ext4_journal_check_start(struct super_block *sb) might_sleep(); - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_forced_shutdown(sb))) return -EIO; - if (sb_rdonly(sb)) + if (WARN_ON_ONCE(sb_rdonly(sb))) return -EROFS; + WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; /* diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 9b5b8951afb4..6f7de14c0fa8 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -878,23 +878,29 @@ retry: err1 = __es_remove_extent(inode, lblk, end, NULL, es1); if (err1 != 0) goto error; + /* Free preallocated extent if it didn't get used. */ + if (es1) { + if (!es1->es_len) + __es_free_extent(es1); + es1 = NULL; + } err2 = __es_insert_extent(inode, &newes, es2); if (err2 == -ENOMEM && !ext4_es_must_keep(&newes)) err2 = 0; if (err2 != 0) goto error; + /* Free preallocated extent if it didn't get used. */ + if (es2) { + if (!es2->es_len) + __es_free_extent(es2); + es2 = NULL; + } if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && (status & EXTENT_STATUS_WRITTEN || status & EXTENT_STATUS_UNWRITTEN)) __revise_pending(inode, lblk, len); - - /* es is pre-allocated but not used, free it. */ - if (es1 && !es1->es_len) - __es_free_extent(es1); - if (es2 && !es2->es_len) - __es_free_extent(es2); error: write_unlock(&EXT4_I(inode)->i_es_lock); if (err1 || err2) @@ -1491,8 +1497,12 @@ retry: */ write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, &reserved, es); - if (es && !es->es_len) - __es_free_extent(es); + /* Free preallocated extent if it didn't get used. */ + if (es) { + if (!es->es_len) + __es_free_extent(es); + es = NULL; + } write_unlock(&EXT4_I(inode)->i_es_lock); if (err) goto retry; @@ -2047,19 +2057,25 @@ retry: err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); if (err1 != 0) goto error; + /* Free preallocated extent if it didn't get used. */ + if (es1) { + if (!es1->es_len) + __es_free_extent(es1); + es1 = NULL; + } err2 = __es_insert_extent(inode, &newes, es2); if (err2 != 0) goto error; + /* Free preallocated extent if it didn't get used. */ + if (es2) { + if (!es2->es_len) + __es_free_extent(es2); + es2 = NULL; + } if (allocated) __insert_pending(inode, lblk); - - /* es is pre-allocated but not used, free it. */ - if (es1 && !es1->es_len) - __es_free_extent(es1); - if (es2 && !es2->es_len) - __es_free_extent(es2); error: write_unlock(&EXT4_I(inode)->i_es_lock); if (err1 || err2) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2dc3f8301225..6830ea3a6c59 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -131,7 +131,7 @@ static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (!iov_iter_count(to)) @@ -153,7 +153,7 @@ static ssize_t ext4_file_splice_read(struct file *in, loff_t *ppos, { struct inode *inode = file_inode(in); - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; return filemap_splice_read(in, ppos, pipe, len, flags); } @@ -476,6 +476,11 @@ restart: * required to change security info in file_modified(), for extending * I/O, any form of non-overwrite I/O, and unaligned I/O to unwritten * extents (as partial block zeroing may be required). + * + * Note that unaligned writes are allowed under shared lock so long as + * they are pure overwrites. Otherwise, concurrent unaligned writes risk + * data corruption due to partial block zeroing in the dio layer, and so + * the I/O must occur exclusively. */ if (*ilock_shared && ((!IS_NOSEC(inode) || *extend || !overwrite || @@ -492,21 +497,12 @@ restart: /* * Now that locking is settled, determine dio flags and exclusivity - * requirements. Unaligned writes are allowed under shared lock so long - * as they are pure overwrites. Set the iomap overwrite only flag as an - * added precaution in this case. Even though this is unnecessary, we - * can detect and warn on unexpected -EAGAIN if an unsafe unaligned - * write is ever submitted. - * - * Otherwise, concurrent unaligned writes risk data corruption due to - * partial block zeroing in the dio layer, and so the I/O must occur - * exclusively. The inode lock is already held exclusive if the write is - * non-overwrite or extending, so drain all outstanding dio and set the - * force wait dio flag. + * requirements. We don't use DIO_OVERWRITE_ONLY because we enforce + * behavior already. The inode lock is already held exclusive if the + * write is non-overwrite or extending, so drain all outstanding dio and + * set the force wait dio flag. */ - if (*ilock_shared && unaligned_io) { - *dio_flags = IOMAP_DIO_OVERWRITE_ONLY; - } else if (!*ilock_shared && (unaligned_io || *extend)) { + if (!*ilock_shared && (unaligned_io || *extend)) { if (iocb->ki_flags & IOCB_NOWAIT) { ret = -EAGAIN; goto out; @@ -608,7 +604,6 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) iomap_ops = &ext4_iomap_overwrite_ops; ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, dio_flags, NULL, 0); - WARN_ON_ONCE(ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT)); if (ret == -ENOTBLK) ret = 0; @@ -709,7 +704,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; #ifdef CONFIG_FS_DAX @@ -806,10 +801,9 @@ static const struct vm_operations_struct ext4_file_vm_ops = { static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file->f_mapping->host; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct dax_device *dax_dev = sbi->s_daxdev; + struct dax_device *dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; - if (unlikely(ext4_forced_shutdown(sbi))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; /* @@ -885,7 +879,7 @@ static int ext4_file_open(struct inode *inode, struct file *filp) { int ret; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt); diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 0c56f3a011a1..b40d3b29f7e5 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -131,9 +131,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) int ret = 0, err; bool needs_barrier = false; struct inode *inode = file->f_mapping->host; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - if (unlikely(ext4_forced_shutdown(sbi))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; ASSERT(ext4_journal_current_handle() == NULL); @@ -141,14 +140,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) trace_ext4_sync_file_enter(file, datasync); if (sb_rdonly(inode->i_sb)) { - /* Make sure that we read updated s_mount_flags value */ + /* Make sure that we read updated s_ext4_flags value */ smp_rmb(); - if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED)) + if (ext4_forced_shutdown(inode->i_sb)) ret = -EROFS; goto out; } - if (!sbi->s_journal) { + if (!EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fsync_nojournal(file, start, end, datasync, &needs_barrier); if (needs_barrier) diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 46c3423ddfa1..deabe29da7fb 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -300,7 +300,7 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len, unsigned char *buff; struct qstr qstr = {.name = name, .len = len }; - if (len && IS_CASEFOLDED(dir) && um && + if (len && IS_CASEFOLDED(dir) && (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) { buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); if (!buff) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 48abef5f23e7..b65058d972f9 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -950,7 +950,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap, sb = dir->i_sb; sbi = EXT4_SB(sb); - if (unlikely(ext4_forced_shutdown(sbi))) + if (unlikely(ext4_forced_shutdown(sb))) return ERR_PTR(-EIO); ngroups = ext4_get_groups_count(sb); @@ -1523,12 +1523,6 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int num, ret = 0, used_blks = 0; unsigned long used_inos = 0; - /* This should not happen, but just to be sure check this */ - if (sb_rdonly(sb)) { - ret = 1; - goto out; - } - gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp || !grp) goto out; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 003861037374..012d9259ff53 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -228,7 +228,7 @@ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, struct ext4_inode *raw_inode; int cp_len = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; BUG_ON(!EXT4_I(inode)->i_inline_off); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 89737d5a1614..4ce35f1c8b0a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1114,7 +1114,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, pgoff_t index; unsigned from, to; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; trace_ext4_write_begin(inode, pos, len); @@ -2213,8 +2213,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, if (err < 0) { struct super_block *sb = inode->i_sb; - if (ext4_forced_shutdown(EXT4_SB(sb)) || - ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) + if (ext4_forced_shutdown(sb)) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. @@ -2534,14 +2533,13 @@ static int ext4_do_writepages(struct mpage_da_data *mpd) * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test - * EXT4_MF_FS_ABORTED instead of sb->s_flag's SB_RDONLY because + * fs shutdown state instead of sb->s_flag's SB_RDONLY because * the latter could be true if the filesystem is mounted * read-only, and in that case, ext4_writepages should * *never* be called, so if that ever happens, we would want * the stack trace. */ - if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) || - ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) { + if (unlikely(ext4_forced_shutdown(mapping->host->i_sb))) { ret = -EROFS; goto out_writepages; } @@ -2759,7 +2757,7 @@ static int ext4_writepages(struct address_space *mapping, int ret; int alloc_ctx; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_forced_shutdown(sb))) return -EIO; alloc_ctx = ext4_writepages_down_read(sb); @@ -2798,16 +2796,16 @@ static int ext4_dax_writepages(struct address_space *mapping, int ret; long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; - struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); int alloc_ctx; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); - ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); + ret = dax_writeback_mapping_range(mapping, + EXT4_SB(inode->i_sb)->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); ext4_writepages_up_read(inode->i_sb, alloc_ctx); @@ -2857,7 +2855,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, pgoff_t index; struct inode *inode = mapping->host; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; index = pos >> PAGE_SHIFT; @@ -2937,14 +2935,73 @@ static int ext4_da_should_update_i_disksize(struct folio *folio, return 1; } +static int ext4_da_do_write_end(struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page) +{ + struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; + bool disksize_changed = false; + loff_t new_i_size; + + /* + * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES + * flag, which all that's needed to trigger page writeback. + */ + copied = block_write_end(NULL, mapping, pos, len, copied, page, NULL); + new_i_size = pos + copied; + + /* + * It's important to update i_size while still holding page lock, + * because page writeout could otherwise come in and zero beyond + * i_size. + * + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range up to i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize up to i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block which ext4_da_should_update_i_disksize() + * checked, we need to update i_disksize here as certain + * ext4_writepages() paths not allocating blocks and update i_disksize. + */ + if (new_i_size > inode->i_size) { + unsigned long end; + + i_size_write(inode, new_i_size); + end = (new_i_size - 1) & (PAGE_SIZE - 1); + if (copied && ext4_da_should_update_i_disksize(page_folio(page), end)) { + ext4_update_i_disksize(inode, new_i_size); + disksize_changed = true; + } + } + + unlock_page(page); + put_page(page); + + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); + + if (disksize_changed) { + handle_t *handle; + + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + } + + return copied; +} + static int ext4_da_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - loff_t new_i_size; - unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; struct folio *folio = page_folio(page); @@ -2963,30 +3020,7 @@ static int ext4_da_write_end(struct file *file, if (unlikely(copied < len) && !PageUptodate(page)) copied = 0; - start = pos & (PAGE_SIZE - 1); - end = start + copied - 1; - - /* - * Since we are holding inode lock, we are sure i_disksize <= - * i_size. We also know that if i_disksize < i_size, there are - * delalloc writes pending in the range upto i_size. If the end of - * the current write is <= i_size, there's no need to touch - * i_disksize since writeback will push i_disksize upto i_size - * eventually. If the end of the current write is > i_size and - * inside an allocated block (ext4_da_should_update_i_disksize() - * check), we need to update i_disksize here as certain - * ext4_writepages() paths not allocating blocks update i_disksize. - * - * Note that we defer inode dirtying to generic_write_end() / - * ext4_da_write_inline_data_end(). - */ - new_i_size = pos + copied; - if (copied && new_i_size > inode->i_size && - ext4_da_should_update_i_disksize(folio, end)) - ext4_update_i_disksize(inode, new_i_size); - - return generic_write_end(file, mapping, pos, len, copied, &folio->page, - fsdata); + return ext4_da_do_write_end(mapping, pos, len, copied, &folio->page); } /* @@ -4940,9 +4974,12 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, "iget: bogus i_mode (%o)", inode->i_mode); goto bad_inode; } - if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) + if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) { ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); + ret = -EFSCORRUPTED; + goto bad_inode; + } if ((err_str = check_igot_inode(inode, flags)) != NULL) { ext4_error_inode(inode, function, line, 0, err_str); ret = -EFSCORRUPTED; @@ -5131,11 +5168,10 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; - if (WARN_ON_ONCE(current->flags & PF_MEMALLOC) || - sb_rdonly(inode->i_sb)) + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) return 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (EXT4_SB(inode->i_sb)->s_journal) { @@ -5255,7 +5291,7 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, const unsigned int ia_valid = attr->ia_valid; bool inc_ivers = true; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (unlikely(IS_IMMUTABLE(inode))) @@ -5674,7 +5710,7 @@ int ext4_mark_iloc_dirty(handle_t *handle, { int err = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { + if (unlikely(ext4_forced_shutdown(inode->i_sb))) { put_bh(iloc->bh); return -EIO; } @@ -5700,7 +5736,7 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode, { int err; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; err = ext4_get_inode_loc(inode, iloc); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index b0349f451863..0bfe2ce589e2 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -802,7 +802,7 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags) if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH) return -EINVAL; - if (ext4_forced_shutdown(sbi)) + if (ext4_forced_shutdown(sb)) return 0; ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 21b903fe546e..c91db9f57524 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -874,7 +874,7 @@ static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - struct ext4_group_info *iter, *grp; + struct ext4_group_info *iter; int i; if (ac->ac_status == AC_STATUS_FOUND) @@ -883,7 +883,6 @@ static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context if (unlikely(sbi->s_mb_stats && ac->ac_flags & EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED)) atomic_inc(&sbi->s_bal_p2_aligned_bad_suggestions); - grp = NULL; for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { if (list_empty(&sbi->s_mb_largest_free_orders[i])) continue; @@ -892,28 +891,22 @@ static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); continue; } - grp = NULL; list_for_each_entry(iter, &sbi->s_mb_largest_free_orders[i], bb_largest_free_order_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[CR_POWER2_ALIGNED]); if (likely(ext4_mb_good_group(ac, iter->bb_group, CR_POWER2_ALIGNED))) { - grp = iter; - break; + *group = iter->bb_group; + ac->ac_flags |= EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED; + read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); + return; } } read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); - if (grp) - break; } - if (!grp) { - /* Increment cr and search again */ - *new_cr = CR_GOAL_LEN_FAST; - } else { - *group = grp->bb_group; - ac->ac_flags |= EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED; - } + /* Increment cr and search again if no group is found */ + *new_cr = CR_GOAL_LEN_FAST; } /* @@ -966,16 +959,25 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context * for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); i < MB_NUM_ORDERS(ac->ac_sb); i++) { grp = ext4_mb_find_good_group_avg_frag_lists(ac, i); - if (grp) - break; + if (grp) { + *group = grp->bb_group; + ac->ac_flags |= EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED; + return; + } } - if (grp) { - *group = grp->bb_group; - ac->ac_flags |= EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED; - } else { + /* + * CR_BEST_AVAIL_LEN works based on the concept that we have + * a larger normalized goal len request which can be trimmed to + * a smaller goal len such that it can still satisfy original + * request len. However, allocation request for non-regular + * files never gets normalized. + * See function ext4_mb_normalize_request() (EXT4_MB_HINT_DATA). + */ + if (ac->ac_flags & EXT4_MB_HINT_DATA) *new_cr = CR_BEST_AVAIL_LEN; - } + else + *new_cr = CR_GOAL_LEN_SLOW; } /* @@ -1051,18 +1053,16 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context ac->ac_g_ex.fe_len); grp = ext4_mb_find_good_group_avg_frag_lists(ac, frag_order); - if (grp) - break; + if (grp) { + *group = grp->bb_group; + ac->ac_flags |= EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED; + return; + } } - if (grp) { - *group = grp->bb_group; - ac->ac_flags |= EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED; - } else { - /* Reset goal length to original goal length before falling into CR_GOAL_LEN_SLOW */ - ac->ac_g_ex.fe_len = ac->ac_orig_goal_len; - *new_cr = CR_GOAL_LEN_SLOW; - } + /* Reset goal length to original goal length before falling into CR_GOAL_LEN_SLOW */ + ac->ac_g_ex.fe_len = ac->ac_orig_goal_len; + *new_cr = CR_GOAL_LEN_SLOW; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) @@ -1080,8 +1080,9 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac) * Return next linear group for allocation. If linear traversal should not be * performed, this function just returns the same group */ -static int -next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) +static ext4_group_t +next_linear_group(struct ext4_allocation_context *ac, ext4_group_t group, + ext4_group_t ngroups) { if (!should_optimize_scan(ac)) goto inc_and_return; @@ -1255,7 +1256,7 @@ void ext4_mb_generate_buddy(struct super_block *sb, static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) { ext4_group_t ngroups; - int blocksize; + unsigned int blocksize; int blocks_per_page; int groups_per_page; int err = 0; @@ -2450,7 +2451,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, break; } - if (ac->ac_criteria < CR_FAST) { + if (!ext4_mb_cr_expensive(ac->ac_criteria)) { /* * In CR_GOAL_LEN_FAST and CR_BEST_AVAIL_LEN, we are * sure that this group will have a large enough @@ -2553,7 +2554,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < CR_POWER2_ALIGNED || cr >= EXT4_MB_NUM_CRS); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp)) + if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; @@ -2634,7 +2635,12 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, free = grp->bb_free; if (free == 0) goto out; - if (cr <= CR_FAST && free < ac->ac_g_ex.fe_len) + /* + * In all criterias except CR_ANY_FREE we try to avoid groups that + * can't possibly satisfy the full goal request due to insufficient + * free blocks. + */ + if (cr < CR_ANY_FREE && free < ac->ac_g_ex.fe_len) goto out; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) goto out; @@ -2658,7 +2664,7 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, * sure we locate metadata blocks in the first block group in * the flex_bg if possible. */ - if (cr < CR_FAST && + if (!ext4_mb_cr_expensive(cr) && (!sbi->s_log_groups_per_flex || ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && !(ext4_has_group_desc_csum(sb) && @@ -2787,8 +2793,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) /* * ac->ac_2order is set only if the fe_len is a power of 2 - * if ac->ac_2order is set we also set criteria to 0 so that we - * try exact allocation using buddy. + * if ac->ac_2order is set we also set criteria to CR_POWER2_ALIGNED + * so that we try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); ac->ac_2order = 0; @@ -2800,10 +2806,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) * requests upto maximum buddy size we have constructed. */ if (i >= sbi->s_mb_order2_reqs && i <= MB_NUM_ORDERS(sb)) { - /* - * This should tell if fe_len is exactly power of 2 - */ - if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0) + if (is_power_of_2(ac->ac_g_ex.fe_len)) ac->ac_2order = array_index_nospec(i - 1, MB_NUM_ORDERS(sb)); } @@ -2848,11 +2851,11 @@ repeat: /* * Batch reads of the block allocation bitmaps * to get multiple READs in flight; limit - * prefetching at cr=0/1, otherwise mballoc can - * spend a lot of time loading imperfect groups + * prefetching at inexpensive CR, otherwise mballoc + * can spend a lot of time loading imperfect groups */ if ((prefetch_grp == group) && - (cr >= CR_FAST || + (ext4_mb_cr_expensive(cr) || prefetch_ios < sbi->s_mb_prefetch_limit)) { nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { @@ -3501,11 +3504,10 @@ static void ext4_discard_work(struct work_struct *work) struct super_block *sb = sbi->s_sb; struct ext4_free_data *fd, *nfd; struct ext4_buddy e4b; - struct list_head discard_list; + LIST_HEAD(discard_list); ext4_group_t grp, load_grp; int err = 0; - INIT_LIST_HEAD(&discard_list); spin_lock(&sbi->s_md_lock); list_splice_init(&sbi->s_discard_list, &discard_list); spin_unlock(&sbi->s_md_lock); @@ -3879,12 +3881,10 @@ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; - struct list_head freed_data_list; + LIST_HEAD(freed_data_list); struct list_head *cut_pos = NULL; bool wake; - INIT_LIST_HEAD(&freed_data_list); - spin_lock(&sbi->s_md_lock); list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { if (entry->efd_tid != commit_tid) @@ -4084,7 +4084,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; - int i, err; + int i, err = 0; int already; unsigned int clen, clen_changed, thisgrp_len; @@ -4222,12 +4222,13 @@ ext4_mb_pa_rb_next_iter(ext4_lblk_t new_start, ext4_lblk_t cur_start, struct rb_ static inline void ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac, - ext4_lblk_t start, ext4_lblk_t end) + ext4_lblk_t start, loff_t end) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_prealloc_space *tmp_pa; - ext4_lblk_t tmp_pa_start, tmp_pa_end; + ext4_lblk_t tmp_pa_start; + loff_t tmp_pa_end; struct rb_node *iter; read_lock(&ei->i_prealloc_lock); @@ -4236,7 +4237,7 @@ ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac, tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; - tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len); + tmp_pa_end = pa_logical_end(sbi, tmp_pa); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) @@ -4258,14 +4259,14 @@ ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac, */ static inline void ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac, - ext4_lblk_t *start, ext4_lblk_t *end) + ext4_lblk_t *start, loff_t *end) { struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *tmp_pa = NULL, *left_pa = NULL, *right_pa = NULL; struct rb_node *iter; - ext4_lblk_t new_start, new_end; - ext4_lblk_t tmp_pa_start, tmp_pa_end, left_pa_end = -1, right_pa_start = -1; + ext4_lblk_t new_start, tmp_pa_start, right_pa_start = -1; + loff_t new_end, tmp_pa_end, left_pa_end = -1; new_start = *start; new_end = *end; @@ -4284,7 +4285,7 @@ ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac, tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; - tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len); + tmp_pa_end = pa_logical_end(sbi, tmp_pa); /* PA must not overlap original request */ spin_lock(&tmp_pa->pa_lock); @@ -4364,8 +4365,7 @@ ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac, } if (left_pa) { - left_pa_end = - left_pa->pa_lstart + EXT4_C2B(sbi, left_pa->pa_len); + left_pa_end = pa_logical_end(sbi, left_pa); BUG_ON(left_pa_end > ac->ac_o_ex.fe_logical); } @@ -4404,8 +4404,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_super_block *es = sbi->s_es; int bsbits, max; - ext4_lblk_t end; - loff_t size, start_off; + loff_t size, start_off, end; loff_t orig_size __maybe_unused; ext4_lblk_t start; @@ -4432,7 +4431,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, /* first, let's learn actual file size * given current request is allocated */ - size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); + size = extent_logical_end(sbi, &ac->ac_o_ex); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); @@ -4766,7 +4765,6 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_locality_group *lg; struct ext4_prealloc_space *tmp_pa = NULL, *cpa = NULL; - loff_t tmp_pa_end; struct rb_node *iter; ext4_fsblk_t goal_block; @@ -4862,9 +4860,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) * pa can possibly satisfy the request hence check if it overlaps * original logical start and stop searching if it doesn't. */ - tmp_pa_end = (loff_t)tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len); - - if (ac->ac_o_ex.fe_logical >= tmp_pa_end) { + if (ac->ac_o_ex.fe_logical >= pa_logical_end(sbi, tmp_pa)) { spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } @@ -4984,7 +4980,6 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); n = rb_next(n); } - return; } /* @@ -5180,8 +5175,11 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_orig_goal_len) { - int new_bex_start; - int new_bex_end; + struct ext4_free_extent ex = { + .fe_logical = ac->ac_g_ex.fe_logical, + .fe_len = ac->ac_orig_goal_len, + }; + loff_t orig_goal_end = extent_logical_end(sbi, &ex); /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart @@ -5200,29 +5198,23 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * still cover original start * 3. Else, keep the best ex at start of original request. */ - new_bex_end = ac->ac_g_ex.fe_logical + - EXT4_C2B(sbi, ac->ac_orig_goal_len); - new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (ac->ac_o_ex.fe_logical >= new_bex_start) - goto adjust_bex; + ex.fe_len = ac->ac_b_ex.fe_len; - new_bex_start = ac->ac_g_ex.fe_logical; - new_bex_end = - new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (ac->ac_o_ex.fe_logical < new_bex_end) + ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len); + if (ac->ac_o_ex.fe_logical >= ex.fe_logical) goto adjust_bex; - new_bex_start = ac->ac_o_ex.fe_logical; - new_bex_end = - new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + ex.fe_logical = ac->ac_g_ex.fe_logical; + if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + goto adjust_bex; + ex.fe_logical = ac->ac_o_ex.fe_logical; adjust_bex: - ac->ac_b_ex.fe_logical = new_bex_start; + ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); - BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical + - EXT4_C2B(sbi, ac->ac_orig_goal_len))); + BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } pa->pa_lstart = ac->ac_b_ex.fe_logical; @@ -5419,7 +5411,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; - struct list_head list; + LIST_HEAD(list); struct ext4_buddy e4b; struct ext4_inode_info *ei; int err; @@ -5448,7 +5440,6 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, goto out_dbg; } - INIT_LIST_HEAD(&list); ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { @@ -5529,7 +5520,7 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed) struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; ext4_group_t group = 0; - struct list_head list; + LIST_HEAD(list); struct ext4_buddy e4b; struct rb_node *iter; int err; @@ -5546,8 +5537,6 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed) trace_ext4_discard_preallocations(inode, atomic_read(&ei->i_prealloc_active), needed); - INIT_LIST_HEAD(&list); - if (needed == 0) needed = UINT_MAX; @@ -5671,7 +5660,7 @@ static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; - if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) + if (ext4_forced_shutdown(sb)) return; ngroups = ext4_get_groups_count(sb); @@ -5705,7 +5694,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) + if (ext4_forced_shutdown(sb)) return; mb_debug(sb, "Can't allocate:" @@ -5738,12 +5727,10 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) #else static inline void ext4_mb_show_pa(struct super_block *sb) { - return; } static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { ext4_mb_show_pa(ac->ac_sb); - return; } #endif @@ -5769,7 +5756,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) group_pa_eligible = sbi->s_mb_group_prealloc > 0; inode_pa_eligible = true; - size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); + size = extent_logical_end(sbi, &ac->ac_o_ex); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; @@ -5865,13 +5852,11 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, { ext4_group_t group = 0; struct ext4_buddy e4b; - struct list_head discard_list; + LIST_HEAD(discard_list); struct ext4_prealloc_space *pa, *tmp; mb_debug(sb, "discard locality group preallocation\n"); - INIT_LIST_HEAD(&discard_list); - spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], pa_node.lg_list, @@ -5984,12 +5969,9 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) spin_unlock(&lg->lg_prealloc_lock); /* Now trim the list to be not more than 8 elements */ - if (lg_prealloc_count > 8) { + if (lg_prealloc_count > 8) ext4_mb_discard_lg_preallocations(sb, lg, order, lg_prealloc_count); - return; - } - return ; } /* @@ -6102,7 +6084,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; - struct ext4_super_block *es = EXT4_SB(sb)->s_es; + struct ext4_super_block *es = sbi->s_es; goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || @@ -6643,7 +6625,6 @@ do_more: error_return: brelse(bitmap_bh); ext4_std_error(sb, err); - return; } /** @@ -6746,7 +6727,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, } ext4_mb_clear_bb(handle, inode, block, count, flags); - return; } /** @@ -6936,8 +6916,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) void *bitmap; bitmap = e4b->bd_bitmap; - start = (e4b->bd_info->bb_first_free > start) ? - e4b->bd_info->bb_first_free : start; + start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -7154,8 +7133,7 @@ ext4_mballoc_query_range( ext4_lock_group(sb, group); - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; + start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index df6b5e7c2274..d7aeb5da7d86 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -233,6 +233,20 @@ static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb, (fex->fe_start << EXT4_SB(sb)->s_cluster_bits); } +static inline loff_t extent_logical_end(struct ext4_sb_info *sbi, + struct ext4_free_extent *fex) +{ + /* Use loff_t to avoid end exceeding ext4_lblk_t max. */ + return (loff_t)fex->fe_logical + EXT4_C2B(sbi, fex->fe_len); +} + +static inline loff_t pa_logical_end(struct ext4_sb_info *sbi, + struct ext4_prealloc_space *pa) +{ + /* Use loff_t to avoid end exceeding ext4_lblk_t max. */ + return (loff_t)pa->pa_lstart + EXT4_C2B(sbi, pa->pa_len); +} + typedef int (*ext4_mballoc_query_range_fn)( struct super_block *sb, ext4_group_t agno, diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 0aaf38ffcb6e..bd946d0c71b7 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -162,7 +162,7 @@ static int kmmpd(void *data) memcpy(mmp->mmp_nodename, init_utsname()->nodename, sizeof(mmp->mmp_nodename)); - while (!kthread_should_stop() && !sb_rdonly(sb)) { + while (!kthread_should_stop() && !ext4_forced_shutdown(sb)) { if (!ext4_has_feature_mmp(sb)) { ext4_warning(sb, "kmmpd being stopped since MMP feature" " has been disabled."); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 933ad03f4f58..41a6411c600b 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1445,7 +1445,7 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct dx_hash_info *hinfo = &name->hinfo; int len; - if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding || + if (!IS_CASEFOLDED(dir) || (IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) { cf_name->name = NULL; return 0; @@ -1496,7 +1496,7 @@ static bool ext4_match(struct inode *parent, #endif #if IS_ENABLED(CONFIG_UNICODE) - if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) && + if (IS_CASEFOLDED(parent) && (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) { if (fname->cf_name.name) { struct qstr cf = {.name = fname->cf_name.name, @@ -2393,7 +2393,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, #if IS_ENABLED(CONFIG_UNICODE) if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) && - sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name)) + utf8_validate(sb->s_encoding, &dentry->d_name)) return -EINVAL; #endif @@ -2799,6 +2799,7 @@ static int ext4_add_nondir(handle_t *handle, return err; } drop_nlink(inode); + ext4_mark_inode_dirty(handle, inode); ext4_orphan_add(handle, inode); unlock_new_inode(inode); return err; @@ -3142,7 +3143,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) struct ext4_dir_entry_2 *de; handle_t *handle = NULL; - if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) + if (unlikely(ext4_forced_shutdown(dir->i_sb))) return -EIO; /* Initialize quotas before so that eventual writes go in @@ -3302,7 +3303,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) { int retval; - if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) + if (unlikely(ext4_forced_shutdown(dir->i_sb))) return -EIO; trace_ext4_unlink_enter(dir, dentry); @@ -3370,7 +3371,7 @@ static int ext4_symlink(struct mnt_idmap *idmap, struct inode *dir, struct fscrypt_str disk_link; int retries = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) + if (unlikely(ext4_forced_shutdown(dir->i_sb))) return -EIO; err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, @@ -3437,6 +3438,7 @@ retry: err_drop_inode: clear_nlink(inode); + ext4_mark_inode_dirty(handle, inode); ext4_orphan_add(handle, inode); unlock_new_inode(inode); if (handle) @@ -4021,6 +4023,7 @@ end_rename: ext4_resetent(handle, &old, old.inode->i_ino, old_file_type); drop_nlink(whiteout); + ext4_mark_inode_dirty(handle, whiteout); ext4_orphan_add(handle, whiteout); } unlock_new_inode(whiteout); @@ -4187,7 +4190,7 @@ static int ext4_rename2(struct mnt_idmap *idmap, { int err; - if (unlikely(ext4_forced_shutdown(EXT4_SB(old_dir->i_sb)))) + if (unlikely(ext4_forced_shutdown(old_dir->i_sb))) return -EIO; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 3621f29ec671..dfdd7e5cf038 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -184,7 +184,7 @@ static int ext4_end_io_end(ext4_io_end_t *io_end) io_end->handle = NULL; /* Following call will use up the handle */ ret = ext4_convert_unwritten_io_end_vec(handle, io_end); - if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) { + if (ret < 0 && !ext4_forced_shutdown(inode->i_sb)) { ext4_msg(inode->i_sb, KERN_EMERG, "failed to convert unwritten extents to written " "extents -- potential data loss! " diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 73547d2334fd..38217422f938 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -434,6 +434,57 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) +#define EXT4_SB_REFRESH_INTERVAL_SEC (3600) /* seconds (1 hour) */ +#define EXT4_SB_REFRESH_INTERVAL_KB (16384) /* kilobytes (16MB) */ + +/* + * The ext4_maybe_update_superblock() function checks and updates the + * superblock if needed. + * + * This function is designed to update the on-disk superblock only under + * certain conditions to prevent excessive disk writes and unnecessary + * waking of the disk from sleep. The superblock will be updated if: + * 1. More than an hour has passed since the last superblock update, and + * 2. More than 16MB have been written since the last superblock update. + * + * @sb: The superblock + */ +static void ext4_maybe_update_superblock(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + journal_t *journal = sbi->s_journal; + time64_t now; + __u64 last_update; + __u64 lifetime_write_kbytes; + __u64 diff_size; + + if (sb_rdonly(sb) || !(sb->s_flags & SB_ACTIVE) || + !journal || (journal->j_flags & JBD2_UNMOUNT)) + return; + + now = ktime_get_real_seconds(); + last_update = ext4_get_tstamp(es, s_wtime); + + if (likely(now - last_update < EXT4_SB_REFRESH_INTERVAL_SEC)) + return; + + lifetime_write_kbytes = sbi->s_kbytes_written + + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + sbi->s_sectors_written_start) >> 1); + + /* Get the number of kilobytes not written to disk to account + * for statistics and compare with a multiple of 16 MB. This + * is used to determine when the next superblock commit should + * occur (i.e. not more often than once per 16MB if there was + * less written in an hour). + */ + diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); + + if (diff_size > EXT4_SB_REFRESH_INTERVAL_KB) + schedule_work(&EXT4_SB(sb)->s_sb_upd_work); +} + /* * The del_gendisk() function uninitializes the disk-specific data * structures, including the bdi structure, without telling anyone @@ -460,6 +511,7 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) BUG_ON(txn->t_state == T_FINISHED); ext4_process_freed_data(sb, txn->t_tid); + ext4_maybe_update_superblock(sb); spin_lock(&sbi->s_md_lock); while (!list_empty(&txn->t_private_list)) { @@ -658,7 +710,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, WARN_ON_ONCE(1); if (!continue_fs && !sb_rdonly(sb)) { - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); + set_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); if (journal) jbd2_journal_abort(journal, -EIO); } @@ -672,7 +724,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, * defer superblock flushing to a workqueue. */ if (continue_fs && journal) - schedule_work(&EXT4_SB(sb)->s_error_work); + schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); } @@ -699,10 +751,10 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, sb->s_flags |= SB_RDONLY; } -static void flush_stashed_error_work(struct work_struct *work) +static void update_super_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, - s_error_work); + s_sb_upd_work); journal_t *journal = sbi->s_journal; handle_t *handle; @@ -716,6 +768,7 @@ static void flush_stashed_error_work(struct work_struct *work) */ if (!sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; + bool call_notify_err; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; @@ -723,6 +776,10 @@ static void flush_stashed_error_work(struct work_struct *work) jbd2_journal_stop(handle); goto write_directly; } + + if (sbi->s_add_error_count > 0) + call_notify_err = true; + ext4_update_super(sbi->s_sb); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " @@ -736,7 +793,10 @@ static void flush_stashed_error_work(struct work_struct *work) goto write_directly; } jbd2_journal_stop(handle); - ext4_notify_error_sysfs(sbi); + + if (call_notify_err) + ext4_notify_error_sysfs(sbi); + return; } write_directly: @@ -759,7 +819,7 @@ void __ext4_error(struct super_block *sb, const char *function, struct va_format vaf; va_list args; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_forced_shutdown(sb))) return; trace_ext4_error(sb, function, line); @@ -784,7 +844,7 @@ void __ext4_error_inode(struct inode *inode, const char *function, va_list args; struct va_format vaf; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); @@ -819,7 +879,7 @@ void __ext4_error_file(struct file *file, const char *function, struct inode *inode = file_inode(file); char pathname[80], *path; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); @@ -899,7 +959,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, char nbuf[16]; const char *errstr; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_forced_shutdown(sb))) return; /* Special case: if the error is EROFS, and we're not already @@ -993,7 +1053,7 @@ __acquires(bitlock) struct va_format vaf; va_list args; - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) + if (unlikely(ext4_forced_shutdown(sb))) return; trace_ext4_error(sb, function, line); @@ -1019,7 +1079,7 @@ __acquires(bitlock) if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - schedule_work(&EXT4_SB(sb)->s_error_work); + schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } return; } @@ -1097,26 +1157,6 @@ void ext4_update_dynamic_rev(struct super_block *sb) */ } -/* - * Open the external journal device - */ -static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) -{ - struct block_device *bdev; - - bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, - &fs_holder_ops); - if (IS_ERR(bdev)) - goto fail; - return bdev; - -fail: - ext4_msg(sb, KERN_ERR, - "failed to open journal device unknown-block(%u,%u) %ld", - MAJOR(dev), MINOR(dev), PTR_ERR(bdev)); - return NULL; -} - static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; @@ -1251,10 +1291,10 @@ static void ext4_put_super(struct super_block *sb) * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL - * Unregister sysfs before flush sbi->s_error_work. + * Unregister sysfs before flush sbi->s_sb_upd_work. * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If * read metadata verify failed then will queue error work. - * flush_stashed_error_work will call start_this_handle may trigger + * update_super_work will call start_this_handle may trigger * BUG_ON. */ ext4_unregister_sysfs(sb); @@ -1266,7 +1306,7 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); - flush_work(&sbi->s_error_work); + flush_work(&sbi->s_sb_upd_work); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); @@ -1875,6 +1915,7 @@ static const struct mount_opts { {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, #endif + {Opt_abort, EXT4_MOUNT2_ABORT, MOPT_SET | MOPT_2}, {Opt_err, 0, 0} }; @@ -1943,8 +1984,6 @@ struct ext4_fs_context { unsigned int mask_s_mount_opt; unsigned int vals_s_mount_opt2; unsigned int mask_s_mount_opt2; - unsigned long vals_s_mount_flags; - unsigned long mask_s_mount_flags; unsigned int opt_flags; /* MOPT flags */ unsigned int spec; u32 s_max_batch_time; @@ -2095,12 +2134,6 @@ EXT4_SET_CTX(mount_opt2); EXT4_CLEAR_CTX(mount_opt2); EXT4_TEST_CTX(mount_opt2); -static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit) -{ - set_bit(bit, &ctx->mask_s_mount_flags); - set_bit(bit, &ctx->vals_s_mount_flags); -} - static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; @@ -2164,9 +2197,6 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", param->key); return 0; - case Opt_abort: - ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED); - return 0; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_flags(ctx, SB_INLINECRYPT); @@ -2820,8 +2850,6 @@ static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) sbi->s_mount_opt |= ctx->vals_s_mount_opt; sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; - sbi->s_mount_flags &= ~ctx->mask_s_mount_flags; - sbi->s_mount_flags |= ctx->vals_s_mount_flags; sb->s_flags &= ~ctx->mask_s_flags; sb->s_flags |= ctx->vals_s_flags; @@ -4210,7 +4238,7 @@ int ext4_calculate_overhead(struct super_block *sb) else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); - if (j_inode) { + if (!IS_ERR(j_inode)) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; overhead += EXT4_NUM_B2C(sbi, j_blocks); iput(j_inode); @@ -4948,8 +4976,8 @@ static int ext4_load_and_init_journal(struct super_block *sb, return 0; out: - /* flush s_error_work before journal destroy. */ - flush_work(&sbi->s_error_work); + /* flush s_sb_upd_work before destroying the journal. */ + flush_work(&sbi->s_sb_upd_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; return -EINVAL; @@ -5272,7 +5300,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); - INIT_WORK(&sbi->s_error_work, flush_stashed_error_work); + INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); if (err) @@ -5615,16 +5643,16 @@ failed_mount_wq: sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { - /* flush s_error_work before journal destroy. */ - flush_work(&sbi->s_error_work); + /* flush s_sb_upd_work before journal destroy. */ + flush_work(&sbi->s_sb_upd_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: - /* flush s_error_work before sbi destroy */ - flush_work(&sbi->s_error_work); + /* flush s_sb_upd_work before sbi destroy */ + flush_work(&sbi->s_sb_upd_work); del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); ext4_group_desc_free(sbi); @@ -5751,22 +5779,22 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); - return NULL; + return ERR_CAST(journal_inode); } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); ext4_msg(sb, KERN_ERR, "journal inode is deleted"); - return NULL; + return ERR_PTR(-EFSCORRUPTED); } - - ext4_debug("Journal inode found at %p: %lld bytes\n", - journal_inode, journal_inode->i_size); if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); - return NULL; + return ERR_PTR(-EFSCORRUPTED); } + + ext4_debug("Journal inode found at %p: %lld bytes\n", + journal_inode, journal_inode->i_size); return journal_inode; } @@ -5792,24 +5820,21 @@ static int ext4_journal_bmap(journal_t *journal, sector_t *block) return 0; } -static journal_t *ext4_get_journal(struct super_block *sb, - unsigned int journal_inum) +static journal_t *ext4_open_inode_journal(struct super_block *sb, + unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; - if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) - return NULL; - journal_inode = ext4_get_journal_inode(sb, journal_inum); - if (!journal_inode) - return NULL; + if (IS_ERR(journal_inode)) + return ERR_CAST(journal_inode); journal = jbd2_journal_init_inode(journal_inode); - if (!journal) { + if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); - return NULL; + return ERR_CAST(journal); } journal->j_private = sb; journal->j_bmap = ext4_journal_bmap; @@ -5817,43 +5842,47 @@ static journal_t *ext4_get_journal(struct super_block *sb, return journal; } -static journal_t *ext4_get_dev_journal(struct super_block *sb, - dev_t j_dev) +static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, + dev_t j_dev, ext4_fsblk_t *j_start, + ext4_fsblk_t *j_len) { struct buffer_head *bh; - journal_t *journal; - ext4_fsblk_t start; - ext4_fsblk_t len; + struct block_device *bdev; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; struct ext4_super_block *es; - struct block_device *bdev; - - if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) - return NULL; + int errno; /* see get_tree_bdev why this is needed and safe */ up_write(&sb->s_umount); - bdev = ext4_blkdev_get(j_dev, sb); + bdev = blkdev_get_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, + &fs_holder_ops); down_write(&sb->s_umount); - if (bdev == NULL) - return NULL; + if (IS_ERR(bdev)) { + ext4_msg(sb, KERN_ERR, + "failed to open journal device unknown-block(%u,%u) %ld", + MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev)); + return ERR_CAST(bdev); + } blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { ext4_msg(sb, KERN_ERR, "blocksize too small for journal device"); + errno = -EINVAL; goto out_bdev; } sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev, blocksize); - if (!(bh = __bread(bdev, sb_block, blocksize))) { + bh = __bread(bdev, sb_block, blocksize); + if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " "external journal"); + errno = -EINVAL; goto out_bdev; } @@ -5861,57 +5890,74 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { - ext4_msg(sb, KERN_ERR, "external journal has " - "bad superblock"); - brelse(bh); - goto out_bdev; + ext4_msg(sb, KERN_ERR, "external journal has bad superblock"); + errno = -EFSCORRUPTED; + goto out_bh; } if ((le32_to_cpu(es->s_feature_ro_compat) & EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && es->s_checksum != ext4_superblock_csum(sb, es)) { - ext4_msg(sb, KERN_ERR, "external journal has " - "corrupt superblock"); - brelse(bh); - goto out_bdev; + ext4_msg(sb, KERN_ERR, "external journal has corrupt superblock"); + errno = -EFSCORRUPTED; + goto out_bh; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { ext4_msg(sb, KERN_ERR, "journal UUID does not match"); - brelse(bh); - goto out_bdev; + errno = -EFSCORRUPTED; + goto out_bh; } - len = ext4_blocks_count(es); - start = sb_block + 1; - brelse(bh); /* we're done with the superblock */ + *j_start = sb_block + 1; + *j_len = ext4_blocks_count(es); + brelse(bh); + return bdev; - journal = jbd2_journal_init_dev(bdev, sb->s_bdev, - start, len, blocksize); - if (!journal) { +out_bh: + brelse(bh); +out_bdev: + blkdev_put(bdev, sb); + return ERR_PTR(errno); +} + +static journal_t *ext4_open_dev_journal(struct super_block *sb, + dev_t j_dev) +{ + journal_t *journal; + ext4_fsblk_t j_start; + ext4_fsblk_t j_len; + struct block_device *journal_bdev; + int errno = 0; + + journal_bdev = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); + if (IS_ERR(journal_bdev)) + return ERR_CAST(journal_bdev); + + journal = jbd2_journal_init_dev(journal_bdev, sb->s_bdev, j_start, + j_len, sb->s_blocksize); + if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); + errno = PTR_ERR(journal); goto out_bdev; } - journal->j_private = sb; - if (ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO, true)) { - ext4_msg(sb, KERN_ERR, "I/O error on journal device"); - goto out_journal; - } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { ext4_msg(sb, KERN_ERR, "External journal has more than one " "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); + errno = -EINVAL; goto out_journal; } - EXT4_SB(sb)->s_journal_bdev = bdev; + journal->j_private = sb; + EXT4_SB(sb)->s_journal_bdev = journal_bdev; ext4_init_journal_params(sb, journal); return journal; out_journal: jbd2_journal_destroy(journal); out_bdev: - blkdev_put(bdev, sb); - return NULL; + blkdev_put(journal_bdev, sb); + return ERR_PTR(errno); } static int ext4_load_journal(struct super_block *sb, @@ -5943,13 +5989,13 @@ static int ext4_load_journal(struct super_block *sb, } if (journal_inum) { - journal = ext4_get_journal(sb, journal_inum); - if (!journal) - return -EINVAL; + journal = ext4_open_inode_journal(sb, journal_inum); + if (IS_ERR(journal)) + return PTR_ERR(journal); } else { - journal = ext4_get_dev_journal(sb, journal_dev); - if (!journal) - return -EINVAL; + journal = ext4_open_dev_journal(sb, journal_dev); + if (IS_ERR(journal)) + return PTR_ERR(journal); } journal_dev_ro = bdev_read_only(journal->j_dev); @@ -6066,7 +6112,7 @@ static void ext4_update_super(struct super_block *sb) * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ - if (!(sb->s_flags & SB_RDONLY)) + if (!sb_rdonly(sb)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written + @@ -6264,13 +6310,7 @@ static int ext4_clear_journal_err(struct super_block *sb, */ int ext4_force_commit(struct super_block *sb) { - journal_t *journal; - - if (sb_rdonly(sb)) - return 0; - - journal = EXT4_SB(sb)->s_journal; - return ext4_journal_force_commit(journal); + return ext4_journal_force_commit(EXT4_SB(sb)->s_journal); } static int ext4_sync_fs(struct super_block *sb, int wait) @@ -6280,7 +6320,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (unlikely(ext4_forced_shutdown(sbi))) + if (unlikely(ext4_forced_shutdown(sb))) return 0; trace_ext4_sync_fs(sb, wait); @@ -6329,12 +6369,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) static int ext4_freeze(struct super_block *sb) { int error = 0; - journal_t *journal; - - if (sb_rdonly(sb)) - return 0; - - journal = EXT4_SB(sb)->s_journal; + journal_t *journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ @@ -6368,7 +6403,7 @@ out: */ static int ext4_unfreeze(struct super_block *sb) { - if (sb_rdonly(sb) || ext4_forced_shutdown(EXT4_SB(sb))) + if (ext4_forced_shutdown(sb)) return 0; if (EXT4_SB(sb)->s_journal) { @@ -6484,7 +6519,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) goto restore_opts; } - if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) + if (test_opt2(sb, ABORT)) ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -6498,10 +6533,10 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } /* Flush outstanding errors before changing fs state */ - flush_work(&sbi->s_error_work); + flush_work(&sbi->s_sb_upd_work); if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { - if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { + if (ext4_forced_shutdown(sb)) { err = -EROFS; goto restore_opts; } @@ -6662,7 +6697,7 @@ restore_opts: * If there was a failing r/w to ro transition, we may need to * re-enable quota */ - if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); sb->s_flags = old_sb_flags; @@ -7071,6 +7106,13 @@ static int ext4_quota_off(struct super_block *sb, int type) err = dquot_quota_off(sb, type); if (err || ext4_has_feature_quota(sb)) goto out_put; + /* + * When the filesystem was remounted read-only first, we cannot cleanup + * inode flags here. Bad luck but people should be using QUOTA feature + * these days anyway. + */ + if (sb_rdonly(sb)) + goto out_put; inode_lock(inode); /* diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 281e1bfbbe3e..92ba28cebac6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -701,7 +701,7 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name, { int error; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (strlen(name) > 255) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 9ec91017a7f3..118699fff2f9 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -41,18 +41,6 @@ static inline void __buffer_unlink(struct journal_head *jh) } /* - * Check a checkpoint buffer could be release or not. - * - * Requires j_list_lock - */ -static inline bool __cp_buffer_busy(struct journal_head *jh) -{ - struct buffer_head *bh = jh2bh(jh); - - return (jh->b_transaction || buffer_locked(bh) || buffer_dirty(bh)); -} - -/* * __jbd2_log_wait_for_space: wait until there is space in the journal. * * Called under j-state_lock *only*. It will be unlocked if we have to wait @@ -349,6 +337,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* Checkpoint list management */ +enum shrink_type {SHRINK_DESTROY, SHRINK_BUSY_STOP, SHRINK_BUSY_SKIP}; + /* * journal_shrink_one_cp_list * @@ -360,7 +350,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * Called with j_list_lock held. */ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, - bool destroy, bool *released) + enum shrink_type type, + bool *released) { struct journal_head *last_jh; struct journal_head *next_jh = jh; @@ -376,12 +367,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, jh = next_jh; next_jh = jh->b_cpnext; - if (destroy) { + if (type == SHRINK_DESTROY) { ret = __jbd2_journal_remove_checkpoint(jh); } else { ret = jbd2_journal_try_remove_checkpoint(jh); - if (ret < 0) - continue; + if (ret < 0) { + if (type == SHRINK_BUSY_SKIP) + continue; + break; + } } nr_freed++; @@ -445,7 +439,7 @@ again: tid = transaction->t_tid; freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, - false, &released); + SHRINK_BUSY_SKIP, &released); nr_freed += freed; (*nr_to_scan) -= min(*nr_to_scan, freed); if (*nr_to_scan == 0) @@ -485,19 +479,21 @@ out: void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) { transaction_t *transaction, *last_transaction, *next_transaction; + enum shrink_type type; bool released; transaction = journal->j_checkpoint_transactions; if (!transaction) return; + type = destroy ? SHRINK_DESTROY : SHRINK_BUSY_STOP; last_transaction = transaction->t_cpprev; next_transaction = transaction; do { transaction = next_transaction; next_transaction = transaction->t_cpnext; journal_shrink_one_cp_list(transaction->t_checkpoint_list, - destroy, &released); + type, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if @@ -631,6 +627,8 @@ int jbd2_journal_try_remove_checkpoint(struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); + if (jh->b_transaction) + return -EBUSY; if (!trylock_buffer(bh)) return -EBUSY; if (buffer_dirty(bh)) { 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; } diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 0184931d47f7..c269a7d29a46 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -230,12 +230,8 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) /* Make sure we wrap around the log correctly! */ #define wrap(journal, var) \ do { \ - unsigned long _wrap_last = \ - jbd2_has_feature_fast_commit(journal) ? \ - (journal)->j_fc_last : (journal)->j_last; \ - \ - if (var >= _wrap_last) \ - var -= (_wrap_last - (journal)->j_first); \ + if (var >= (journal)->j_last) \ + var -= ((journal)->j_last - (journal)->j_first); \ } while (0) static int fc_do_one_pass(journal_t *journal, @@ -524,9 +520,7 @@ static int do_one_pass(journal_t *journal, break; jbd2_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", - next_commit_ID, next_log_block, - jbd2_has_feature_fast_commit(journal) ? - journal->j_fc_last : journal->j_last); + next_commit_ID, next_log_block, journal->j_last); /* Skip over each chunk of the transaction looking * either the next descriptor block or the final commit diff --git a/fs/libfs.c b/fs/libfs.c index da78eb64831e..a4eb12757886 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1648,16 +1648,6 @@ bool is_empty_dir_inode(struct inode *inode) } #if IS_ENABLED(CONFIG_UNICODE) -/* - * Determine if the name of a dentry should be casefolded. - * - * Return: if names will need casefolding - */ -static bool needs_casefold(const struct inode *dir) -{ - return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding; -} - /** * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems * @dentry: dentry whose name we are checking against @@ -1678,7 +1668,7 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, char strbuf[DNAME_INLINE_LEN]; int ret; - if (!dir || !needs_casefold(dir)) + if (!dir || !IS_CASEFOLDED(dir)) goto fallback; /* * If the dentry name is stored in-line, then it may be concurrently @@ -1720,7 +1710,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) const struct unicode_map *um = sb->s_encoding; int ret = 0; - if (!dir || !needs_casefold(dir)) + if (!dir || !IS_CASEFOLDED(dir)) return 0; ret = utf8_casefold_hash(um, dentry, str); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index e8e7d47265aa..ce215565d061 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -908,9 +908,9 @@ int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) /* call the kernels journal init function now */ j_journal = jbd2_journal_init_inode(inode); - if (j_journal == NULL) { + if (IS_ERR(j_journal)) { mlog(ML_ERROR, "Linux journal layer error\n"); - status = -EINVAL; + status = PTR_ERR(j_journal); goto done; } @@ -1684,9 +1684,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb, } journal = jbd2_journal_init_inode(inode); - if (journal == NULL) { + if (IS_ERR(journal)) { mlog(ML_ERROR, "Linux journal layer error\n"); - status = -EIO; + status = PTR_ERR(journal); goto done; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 44c298aa58d4..52772c826c86 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -631,11 +631,6 @@ struct transaction_s struct list_head t_inode_list; /* - * Protects info related to handles - */ - spinlock_t t_handle_lock; - - /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; |