diff options
author | Linus Torvalds | 2018-06-05 12:49:17 -0700 |
---|---|---|
committer | Linus Torvalds | 2018-06-05 12:49:17 -0700 |
commit | 1434763ca5b300ad3b880954bd32dc339d16a833 (patch) | |
tree | a9a43ec1574e2df724c0c8573677255adf11bd92 | |
parent | 5037be168f0e4ee910602935b1180291082d3aac (diff) | |
parent | 4f2f76f751433908364ccff82f437a57d0e6e9b7 (diff) |
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o:
"A lot of cleanups and bug fixes, especially dealing with corrupted
file systems"
* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
ext4: fix fencepost error in check for inode count overflow during resize
ext4: correctly handle a zero-length xattr with a non-zero e_value_offs
ext4: bubble errors from ext4_find_inline_data_nolock() up to ext4_iget()
ext4: do not allow external inodes for inline data
ext4: report delalloc reserve as non-free in statfs for project quota
ext4: remove NULL check before calling kmem_cache_destroy()
jbd2: remove NULL check before calling kmem_cache_destroy()
jbd2: remove bunch of empty lines with jbd2 debug
ext4: handle errors on ext4_commit_super
ext4: do not update s_last_mounted of a frozen fs
ext4: factor out helper ext4_sample_last_mounted()
vfs: add the sb_start_intwrite_trylock() helper
ext4: update mtime in ext4_punch_hole even if no blocks are released
ext4: add verifier check for symlink with append/immutable flags
fs: ext4: add new return type vm_fault_t
ext4: fix hole length detection in ext4_ind_map_blocks()
ext4: mark block bitmap corrupted when found
ext4: mark inode bitmap corrupted when found
ext4: add new ext4_mark_group_bitmap_corrupted() helper
ext4: fix wrong return value in ext4_read_inode_bitmap()
...
-rw-r--r-- | fs/ext4/balloc.c | 33 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 7 | ||||
-rw-r--r-- | fs/ext4/extents_status.c | 3 | ||||
-rw-r--r-- | fs/ext4/file.c | 93 | ||||
-rw-r--r-- | fs/ext4/fsmap.c | 4 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 35 | ||||
-rw-r--r-- | fs/ext4/indirect.c | 14 | ||||
-rw-r--r-- | fs/ext4/inline.c | 6 | ||||
-rw-r--r-- | fs/ext4/inode.c | 77 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 23 | ||||
-rw-r--r-- | fs/ext4/resize.c | 2 | ||||
-rw-r--r-- | fs/ext4/super.c | 68 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 2 | ||||
-rw-r--r-- | fs/ext4/xattr_security.c | 2 | ||||
-rw-r--r-- | fs/jbd2/journal.c | 20 | ||||
-rw-r--r-- | fs/jbd2/revoke.c | 12 | ||||
-rw-r--r-- | fs/jbd2/transaction.c | 6 | ||||
-rw-r--r-- | include/linux/fs.h | 5 |
18 files changed, 245 insertions, 167 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 508b905d744d..b00481c475cb 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -185,25 +185,15 @@ static int ext4_init_block_bitmap(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; int flex_bg = 0; - struct ext4_group_info *grp; J_ASSERT_BH(bh, buffer_locked(bh)); /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - grp = ext4_get_group_info(sb, block_group); - if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) - percpu_counter_sub(&sbi->s_freeclusters_counter, - grp->bb_free); - set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); - if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { - int count; - count = ext4_free_inodes_count(sb, gdp); - percpu_counter_sub(&sbi->s_freeinodes_counter, - count); - } - set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT | + EXT4_GROUP_INFO_IBITMAP_CORRUPT); return -EFSBADCRC; } memset(bh->b_data, 0, sb->s_blocksize); @@ -375,7 +365,6 @@ static int ext4_validate_block_bitmap(struct super_block *sb, { ext4_fsblk_t blk; struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); - struct ext4_sb_info *sbi = EXT4_SB(sb); if (buffer_verified(bh)) return 0; @@ -387,10 +376,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, desc, bh))) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); - if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) - percpu_counter_sub(&sbi->s_freeclusters_counter, - grp->bb_free); - set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSBADCRC; } blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); @@ -398,10 +385,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: block %llu: invalid block bitmap", block_group, blk); - if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) - percpu_counter_sub(&sbi->s_freeclusters_counter, - grp->bb_free); - set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } set_buffer_verified(bh); @@ -436,6 +421,8 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) (bitmap_blk >= ext4_blocks_count(sbi->s_es))) { ext4_error(sb, "Invalid block bitmap block %llu in " "block_group %u", bitmap_blk, block_group); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); return ERR_PTR(-EFSCORRUPTED); } bh = sb_getblk(sb, bitmap_blk); @@ -514,6 +501,8 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, ext4_error(sb, "Cannot read block bitmap - " "block_group = %u, block_bitmap = %llu", block_group, (unsigned long long) bh->b_blocknr); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EIO; } clear_buffer_new(bh); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 229ea4da6785..df95412915ea 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2530,6 +2530,9 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup); extern const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]); +extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, + ext4_group_t block_group, + unsigned int flags); extern __printf(4, 5) void __ext4_error(struct super_block *, const char *, unsigned int, @@ -2857,6 +2860,10 @@ struct ext4_group_info { #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 #define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3 +#define EXT4_GROUP_INFO_BBITMAP_CORRUPT \ + (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT) +#define EXT4_GROUP_INFO_IBITMAP_CORRUPT \ + (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT) #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 763ef185dd17..c4e6fb15101b 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -162,8 +162,7 @@ int __init ext4_init_es(void) void ext4_exit_es(void) { - if (ext4_es_cachep) - kmem_cache_destroy(ext4_es_cachep); + kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index fb6f023622fe..7f8023340eb8 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -277,10 +277,11 @@ out: } #ifdef CONFIG_FS_DAX -static int ext4_dax_huge_fault(struct vm_fault *vmf, +static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size) { - int result, error = 0; + int error = 0; + vm_fault_t result; int retries = 0; handle_t *handle = NULL; struct inode *inode = file_inode(vmf->vma->vm_file); @@ -335,7 +336,7 @@ retry: return result; } -static int ext4_dax_fault(struct vm_fault *vmf) +static vm_fault_t ext4_dax_fault(struct vm_fault *vmf) { return ext4_dax_huge_fault(vmf, PE_SIZE_PTE); } @@ -380,50 +381,64 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static int ext4_file_open(struct inode * inode, struct file * filp) +static int ext4_sample_last_mounted(struct super_block *sb, + struct vfsmount *mnt) { - struct super_block *sb = inode->i_sb; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct vfsmount *mnt = filp->f_path.mnt; + struct ext4_sb_info *sbi = EXT4_SB(sb); struct path path; char buf[64], *cp; + handle_t *handle; + int err; + + if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED)) + return 0; + + if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb)) + return 0; + + sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; + /* + * Sample where the filesystem has been mounted and + * store it in the superblock for sysadmin convenience + * when trying to sort through large numbers of block + * devices or filesystem images. + */ + memset(buf, 0, sizeof(buf)); + path.mnt = mnt; + path.dentry = mnt->mnt_root; + cp = d_path(&path, buf, sizeof(buf)); + err = 0; + if (IS_ERR(cp)) + goto out; + + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); + err = PTR_ERR(handle); + if (IS_ERR(handle)) + goto out; + BUFFER_TRACE(sbi->s_sbh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) + goto out_journal; + strlcpy(sbi->s_es->s_last_mounted, cp, + sizeof(sbi->s_es->s_last_mounted)); + ext4_handle_dirty_super(handle, sb); +out_journal: + ext4_journal_stop(handle); +out: + sb_end_intwrite(sb); + return err; +} + +static int ext4_file_open(struct inode * inode, struct file * filp) +{ int ret; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) && - !sb_rdonly(sb))) { - sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; - /* - * Sample where the filesystem has been mounted and - * store it in the superblock for sysadmin convenience - * when trying to sort through large numbers of block - * devices or filesystem images. - */ - memset(buf, 0, sizeof(buf)); - path.mnt = mnt; - path.dentry = mnt->mnt_root; - cp = d_path(&path, buf, sizeof(buf)); - if (!IS_ERR(cp)) { - handle_t *handle; - int err; - - handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); - if (IS_ERR(handle)) - return PTR_ERR(handle); - BUFFER_TRACE(sbi->s_sbh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sbi->s_sbh); - if (err) { - ext4_journal_stop(handle); - return err; - } - strlcpy(sbi->s_es->s_last_mounted, cp, - sizeof(sbi->s_es->s_last_mounted)); - ext4_handle_dirty_super(handle, sb); - ext4_journal_stop(handle); - } - } + ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt); + if (ret) + return ret; ret = fscrypt_file_open(inode, filp); if (ret) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index e871c4bf18e9..4b99e2db95b8 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -402,8 +402,8 @@ static void ext4_getfsmap_free_fixed_metadata(struct list_head *meta_list) } /* Find all the fixed metadata in the filesystem. */ -int ext4_getfsmap_find_fixed_metadata(struct super_block *sb, - struct list_head *meta_list) +static int ext4_getfsmap_find_fixed_metadata(struct super_block *sb, + struct list_head *meta_list) { struct ext4_group_desc *gdp; ext4_group_t agno; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index df92e3ec9913..4d6e007f3569 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -83,7 +83,6 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, { ext4_fsblk_t blk; struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); - struct ext4_sb_info *sbi = EXT4_SB(sb); if (buffer_verified(bh)) return 0; @@ -97,14 +96,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, ext4_unlock_group(sb, block_group); ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " "inode_bitmap = %llu", block_group, blk); - grp = ext4_get_group_info(sb, block_group); - if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { - int count; - count = ext4_free_inodes_count(sb, desc); - percpu_counter_sub(&sbi->s_freeinodes_counter, - count); - } - set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_IBITMAP_CORRUPT); return -EFSBADCRC; } set_buffer_verified(bh); @@ -136,6 +129,8 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) (bitmap_blk >= ext4_blocks_count(sbi->s_es))) { ext4_error(sb, "Invalid inode bitmap blk %llu in " "block_group %u", bitmap_blk, block_group); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EFSCORRUPTED); } bh = sb_getblk(sb, bitmap_blk); @@ -143,7 +138,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); - return ERR_PTR(-EIO); + return ERR_PTR(-ENOMEM); } if (bitmap_uptodate(bh)) goto verify; @@ -190,6 +185,8 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EIO); } @@ -337,13 +334,8 @@ out: fatal = err; } else { ext4_error(sb, "bit already cleared for inode %lu", ino); - if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { - int count; - count = ext4_free_inodes_count(sb, gdp); - percpu_counter_sub(&sbi->s_freeinodes_counter, - count); - } - set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_IBITMAP_CORRUPT); } error_return: @@ -914,6 +906,8 @@ repeat_in_this_group: if (group == 0 && (ino + 1) < EXT4_FIRST_INO(sb)) { ext4_error(sb, "reserved inode found cleared - " "inode=%lu", ino + 1); + ext4_mark_group_bitmap_corrupted(sb, group, + EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto next_group; } @@ -1105,6 +1099,8 @@ got: err = -EIO; ext4_error(sb, "failed to insert inode %lu: doubly allocated?", inode->i_ino); + ext4_mark_group_bitmap_corrupted(sb, group, + EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto out; } inode->i_generation = prandom_u32(); @@ -1206,11 +1202,8 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); - if (IS_ERR(bitmap_bh)) { - ext4_error(sb, "inode bitmap error %ld for orphan %lu", - ino, PTR_ERR(bitmap_bh)); + if (IS_ERR(bitmap_bh)) return (struct inode *) bitmap_bh; - } /* Having the inode bit set should be a 100% indicator that this * is a valid orphan (no e2fsck run on fs). Orphans also include diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index c32802c956d5..bf7fa1507e81 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -561,10 +561,16 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, unsigned epb = inode->i_sb->s_blocksize / sizeof(u32); int i; - /* Count number blocks in a subtree under 'partial' */ - count = 1; - for (i = 0; partial + i != chain + depth - 1; i++) - count *= epb; + /* + * Count number blocks in a subtree under 'partial'. At each + * level we count number of complete empty subtrees beyond + * current offset and then descend into the subtree only + * partially beyond current offset. + */ + count = 0; + for (i = partial - chain + 1; i < depth; i++) + count = count * epb + (epb - offsets[i] - 1); + count++; /* Fill in size of a hole we found */ map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, count); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 70cf4c7b268a..44b4fcdc3755 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -144,6 +144,12 @@ int ext4_find_inline_data_nolock(struct inode *inode) goto out; if (!is.s.not_found) { + if (is.s.here->e_value_inum) { + EXT4_ERROR_INODE(inode, "inline data xattr refers " + "to an external xattr inode"); + error = -EFSCORRUPTED; + goto out; + } EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1e50c5efae67..2ea07efbe016 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4298,28 +4298,28 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) EXT4_BLOCK_SIZE_BITS(sb); stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); - /* If there are no blocks to remove, return now */ - if (first_block >= stop_block) - goto out_stop; + /* If there are blocks to remove, do it */ + if (stop_block > first_block) { - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + down_write(&EXT4_I(inode)->i_data_sem); + ext4_discard_preallocations(inode); - ret = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - if (ret) { - up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; - } + ret = ext4_es_remove_extent(inode, first_block, + stop_block - first_block); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_remove_space(inode, first_block, - stop_block - 1); - else - ret = ext4_ind_remove_space(handle, inode, first_block, - stop_block); + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + ret = ext4_ext_remove_space(inode, first_block, + stop_block - 1); + else + ret = ext4_ind_remove_space(handle, inode, first_block, + stop_block); - up_write(&EXT4_I(inode)->i_data_sem); + up_write(&EXT4_I(inode)->i_data_sem); + } if (IS_SYNC(inode)) ext4_handle_sync(handle); @@ -4701,19 +4701,21 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, } } -static inline void ext4_iget_extra_inode(struct inode *inode, +static inline int ext4_iget_extra_inode(struct inode *inode, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; + if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <= EXT4_INODE_SIZE(inode->i_sb) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { ext4_set_inode_state(inode, EXT4_STATE_XATTR); - ext4_find_inline_data_nolock(inode); + return ext4_find_inline_data_nolock(inode); } else EXT4_I(inode)->i_inline_off = 0; + return 0; } int ext4_get_projid(struct inode *inode, kprojid_t *projid) @@ -4724,6 +4726,26 @@ int ext4_get_projid(struct inode *inode, kprojid_t *projid) return 0; } +/* + * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of + * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag + * set. + */ +static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) +{ + if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + inode_set_iversion_raw(inode, val); + else + inode_set_iversion_queried(inode, val); +} +static inline u64 ext4_inode_peek_iversion(const struct inode *inode) +{ + if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return inode_peek_iversion_raw(inode); + else + return inode_peek_iversion(inode); +} + struct inode *ext4_iget(struct super_block *sb, unsigned long ino) { struct ext4_iloc iloc; @@ -4893,7 +4915,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; } else { - ext4_iget_extra_inode(inode, raw_inode, ei); + ret = ext4_iget_extra_inode(inode, raw_inode, ei); + if (ret) + goto bad_inode; } } @@ -4910,7 +4934,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ivers |= (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32; } - inode_set_iversion_queried(inode, ivers); + ext4_inode_set_iversion_queried(inode, ivers); } ret = 0; @@ -4945,6 +4969,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { + /* VFS does not allow setting these so must be corruption */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + EXT4_ERROR_INODE(inode, + "immutable or append flags not allowed on symlinks"); + ret = -EFSCORRUPTED; + goto bad_inode; + } if (ext4_encrypted_inode(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; ext4_set_aops(inode); @@ -5196,7 +5227,7 @@ static int ext4_do_update_inode(handle_t *handle, } if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { - u64 ivers = inode_peek_iversion(inode); + u64 ivers = ext4_inode_peek_iversion(inode); raw_inode->i_disk_version = cpu_to_le32(ivers); if (ei->i_extra_isize) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 6884e81c1465..6eae2b91aafa 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -470,6 +470,8 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, "freeing block already freed " "(bit %u)", first + i); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } @@ -747,10 +749,8 @@ void ext4_mb_generate_buddy(struct super_block *sb, * corrupt and update bb_free using bitmap value */ grp->bb_free = free; - if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) - percpu_counter_sub(&sbi->s_freeclusters_counter, - grp->bb_free); - set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + ext4_mark_group_bitmap_corrupted(sb, group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); @@ -1454,12 +1454,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, "freeing already freed block " "(bit %u); block bitmap corrupt.", block); - if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)) - percpu_counter_sub(&sbi->s_freeclusters_counter, - e4b->bd_info->bb_free); - /* Mark the block group as corrupt. */ - set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, - &e4b->bd_info->bb_state); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); mb_regenerate_buddy(e4b); goto done; } @@ -1956,6 +1952,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, "%d free clusters as per " "group info. But bitmap says 0", free); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } @@ -1966,6 +1964,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit @@ -2516,8 +2516,7 @@ static void ext4_groupinfo_destroy_slabs(void) int i; for (i = 0; i < NR_GRPINFO_CACHES; i++) { - if (ext4_groupinfo_caches[i]) - kmem_cache_destroy(ext4_groupinfo_caches[i]); + kmem_cache_destroy(ext4_groupinfo_caches[i]); ext4_groupinfo_caches[i] = NULL; } } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index b6bec270a8e4..d792b7689d92 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1933,7 +1933,7 @@ retry: return 0; n_group = ext4_get_group_number(sb, n_blocks_count - 1); - if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) { + if (n_group >= (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) { ext4_warning(sb, "resize would cause inodes_count overflow"); return -EINVAL; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eb104e8476f0..c1c5c8775ae7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -763,6 +763,36 @@ __acquires(bitlock) return; } +void ext4_mark_group_bitmap_corrupted(struct super_block *sb, + ext4_group_t group, + unsigned int flags) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); + + if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) && + !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) { + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, + &grp->bb_state); + } + + if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) && + !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + if (gdp) { + int count; + + count = ext4_free_inodes_count(sb, gdp); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, + &grp->bb_state); + } +} + void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; @@ -2116,12 +2146,12 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { struct ext4_sb_info *sbi = EXT4_SB(sb); - int res = 0; + int err = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); - res = SB_RDONLY; + err = -EROFS; } if (read_only) goto done; @@ -2154,7 +2184,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (sbi->s_journal) ext4_set_feature_journal_needs_recovery(sb); - ext4_commit_super(sb, 1); + err = ext4_commit_super(sb, 1); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " @@ -2166,7 +2196,7 @@ done: sbi->s_mount_opt, sbi->s_mount_opt2); cleancache_init_fs(sb); - return res; + return err; } int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) @@ -4224,8 +4254,12 @@ no_journal: goto failed_mount4; } - if (ext4_setup_super(sb, es, sb_rdonly(sb))) + ret = ext4_setup_super(sb, es, sb_rdonly(sb)); + if (ret == -EROFS) { sb->s_flags |= SB_RDONLY; + ret = 0; + } else if (ret) + goto failed_mount4a; /* determine the minimum size of new large inodes, if present */ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE && @@ -4760,11 +4794,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) unlock_buffer(sbh); error = __sync_dirty_buffer(sbh, REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); - if (error) - return error; - - error = buffer_write_io_error(sbh); - if (error) { + if (buffer_write_io_error(sbh)) { ext4_msg(sb, KERN_ERR, "I/O error while writing " "superblock"); clear_buffer_write_io_error(sbh); @@ -5165,8 +5195,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_clear_journal_err(sb, es); sbi->s_mount_state = le16_to_cpu(es->s_state); - if (!ext4_setup_super(sb, es, 0)) - sb->s_flags &= ~SB_RDONLY; + + err = ext4_setup_super(sb, es, 0); + if (err) + goto restore_opts; + + sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) { @@ -5190,8 +5224,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } ext4_setup_system_zone(sb); - if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) - ext4_commit_super(sb, 1); + if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { + err = ext4_commit_super(sb, 1); + if (err) + goto restore_opts; + } #ifdef CONFIG_QUOTA /* Release old quota file names */ @@ -5252,7 +5289,8 @@ static int ext4_statfs_project(struct super_block *sb, dquot->dq_dqb.dqb_bsoftlimit : dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits; if (limit && buf->f_blocks > limit) { - curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits; + curblock = (dquot->dq_dqb.dqb_curspace + + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; buf->f_blocks = limit; buf->f_bfree = buf->f_bavail = (buf->f_blocks > curblock) ? diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 499cb4b1fbd2..fc4ced59c565 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1688,7 +1688,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, /* No failures allowed past this point. */ - if (!s->not_found && here->e_value_offs) { + if (!s->not_found && here->e_value_size && here->e_value_offs) { /* Remove the old value. */ void *first_val = s->base + min_offs; size_t offs = le16_to_cpu(here->e_value_offs); diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 629001b28632..197a9d8a15ef 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -43,7 +43,7 @@ ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array, err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY, xattr->name, xattr->value, - xattr->value_len, 0); + xattr->value_len, XATTR_CREATE); if (err < 0) break; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index dfb057900e79..8ef6b6daaa7a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -114,7 +114,7 @@ void __jbd2_debug(int level, const char *file, const char *func, va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf); + printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf); va_end(args); } EXPORT_SYMBOL(__jbd2_debug); @@ -2302,8 +2302,7 @@ static void jbd2_journal_destroy_slabs(void) int i; for (i = 0; i < JBD2_MAX_SLABS; i++) { - if (jbd2_slab[i]) - kmem_cache_destroy(jbd2_slab[i]); + kmem_cache_destroy(jbd2_slab[i]); jbd2_slab[i] = NULL; } } @@ -2404,10 +2403,8 @@ static int jbd2_journal_init_journal_head_cache(void) static void jbd2_journal_destroy_journal_head_cache(void) { - if (jbd2_journal_head_cache) { - kmem_cache_destroy(jbd2_journal_head_cache); - jbd2_journal_head_cache = NULL; - } + kmem_cache_destroy(jbd2_journal_head_cache); + jbd2_journal_head_cache = NULL; } /* @@ -2665,11 +2662,10 @@ static int __init jbd2_journal_init_handle_cache(void) static void jbd2_journal_destroy_handle_cache(void) { - if (jbd2_handle_cache) - kmem_cache_destroy(jbd2_handle_cache); - if (jbd2_inode_cache) - kmem_cache_destroy(jbd2_inode_cache); - + kmem_cache_destroy(jbd2_handle_cache); + jbd2_handle_cache = NULL; + kmem_cache_destroy(jbd2_inode_cache); + jbd2_inode_cache = NULL; } /* diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 696ef15ec942..240779e4689c 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -180,14 +180,10 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal, void jbd2_journal_destroy_revoke_caches(void) { - if (jbd2_revoke_record_cache) { - kmem_cache_destroy(jbd2_revoke_record_cache); - jbd2_revoke_record_cache = NULL; - } - if (jbd2_revoke_table_cache) { - kmem_cache_destroy(jbd2_revoke_table_cache); - jbd2_revoke_table_cache = NULL; - } + kmem_cache_destroy(jbd2_revoke_record_cache); + jbd2_revoke_record_cache = NULL; + kmem_cache_destroy(jbd2_revoke_table_cache); + jbd2_revoke_table_cache = NULL; } int __init jbd2_journal_init_revoke_caches(void) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 8aa453784402..51dd68e67b0f 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -49,10 +49,8 @@ int __init jbd2_journal_init_transaction_cache(void) void jbd2_journal_destroy_transaction_cache(void) { - if (transaction_cache) { - kmem_cache_destroy(transaction_cache); - transaction_cache = NULL; - } + kmem_cache_destroy(transaction_cache); + transaction_cache = NULL; } void jbd2_journal_free_transaction(transaction_t *transaction) diff --git a/include/linux/fs.h b/include/linux/fs.h index d4c37d371da5..f4b8c8dc67e3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1597,6 +1597,11 @@ static inline void sb_start_intwrite(struct super_block *sb) __sb_start_write(sb, SB_FREEZE_FS, true); } +static inline int sb_start_intwrite_trylock(struct super_block *sb) +{ + return __sb_start_write(sb, SB_FREEZE_FS, false); +} + extern bool inode_owner_or_capable(const struct inode *inode); |