From 44de022c4382541cebdd6de4465d1f4f465ff1dd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 8 Jul 2018 19:35:02 -0400 Subject: ext4: fix false negatives *and* false positives in ext4_check_descriptors() Ext4_check_descriptors() was getting called before s_gdb_count was initialized. So for file systems w/o the meta_bg feature, allocation bitmaps could overlap the block group descriptors and ext4 wouldn't notice. For file systems with the meta_bg feature enabled, there was a fencepost error which would cause the ext4_check_descriptors() to incorrectly believe that the block allocation bitmap overlaps with the block group descriptor blocks, and it would reject the mount. Fix both of these problems. Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/super.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba2396a7bd04..eff5c983e067 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2342,7 +2342,7 @@ static int ext4_check_descriptors(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; - ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0) + 1; + ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; @@ -4085,14 +4085,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } + sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; } - sbi->s_gdb_count = db_count; - timer_setup(&sbi->s_err_report, print_daily_error_info, 0); /* Register extent status tree shrinker */ -- cgit v1.2.3-58-ga151 From 2dca60d98e241bea686004168f85208f215fc697 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 8 Jul 2018 19:36:02 -0400 Subject: ext4: clear mmp sequence number when remounting read-only Previously, when an MMP-protected file system is remounted read-only, the kmmpd thread would exit the next time it woke up (a few seconds later), without resetting the MMP sequence number back to EXT4_MMP_SEQ_CLEAN. Fix this by explicitly killing the MMP thread when the file system is remounted read-only. Signed-off-by: Theodore Ts'o Cc: Andreas Dilger --- fs/ext4/mmp.c | 7 ++----- fs/ext4/super.c | 2 ++ 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 27b9a76a0dfa..638ad4743477 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -186,11 +186,8 @@ static int kmmpd(void *data) goto exit_thread; } - if (sb_rdonly(sb)) { - ext4_warning(sb, "kmmpd being stopped since filesystem " - "has been remounted as readonly."); - goto exit_thread; - } + if (sb_rdonly(sb)) + break; diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eff5c983e067..680526e9ee96 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5212,6 +5212,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); + if (sbi->s_mmp_tsk) + kthread_stop(sbi->s_mmp_tsk); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || -- cgit v1.2.3-58-ga151 From 362eca70b53389bddf3143fe20f53dcce2cfdf61 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 10 Jul 2018 01:07:43 -0400 Subject: ext4: fix inline data updates with checksums enabled The inline data code was updating the raw inode directly; this is problematic since if metadata checksums are enabled, ext4_mark_inode_dirty() must be called to update the inode's checksum. In addition, the jbd2 layer requires that get_write_access() be called before the metadata buffer is modified. Fix both of these problems. https://bugzilla.kernel.org/show_bug.cgi?id=200443 Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/inline.c | 19 +++++++++++-------- fs/ext4/inode.c | 16 +++++++--------- 2 files changed, 18 insertions(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e55a8bc870bd..3543fe80a3c4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -682,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto convert; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out; + flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); @@ -710,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, out_up_read: up_read(&EXT4_I(inode)->xattr_sem); out: - if (handle) + if (handle && (ret != 1)) ext4_journal_stop(handle); brelse(iloc.bh); return ret; @@ -752,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); + mark_inode_dirty(inode); out: return copied; } @@ -898,7 +903,6 @@ retry_journal: goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; @@ -916,6 +920,9 @@ retry_journal: if (ret < 0) goto out_release_page; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); *pagep = page; @@ -936,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int i_size_changed = 0; int ret; ret = ext4_write_inline_data_end(inode, pos, len, copied, page); @@ -954,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ - if (pos+copied > inode->i_size) { + if (pos+copied > inode->i_size) i_size_write(inode, pos+copied); - i_size_changed = 1; - } unlock_page(page); put_page(page); @@ -967,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) - mark_inode_dirty(inode); + mark_inode_dirty(inode); return copied; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7d6c10017bdf..4efe77286ecd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) + if (i_size_changed || inline_data) ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && ext4_can_truncate(inode)) @@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); @@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); - if (size_changed) { + if (size_changed || inline_data) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page, } if (inline_data) { - BUFFER_TRACE(inode_bh, "get write access"); - ret = ext4_journal_get_write_access(handle, inode_bh); - - err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - + ret = ext4_mark_inode_dirty(handle, inode); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); -- cgit v1.2.3-58-ga151 From 8d5a803c6a6ce4ec258e31f76059ea5153ba46ef Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 12 Jul 2018 19:08:05 -0400 Subject: ext4: check for allocation block validity with block group locked With commit 044e6e3d74a3: "ext4: don't update checksum of new initialized bitmaps" the buffer valid bit will get set without actually setting up the checksum for the allocation bitmap, since the checksum will get calculated once we actually allocate an inode or block. If we are doing this, then we need to (re-)check the verified bit after we take the block group lock. Otherwise, we could race with another process reading and verifying the bitmap, which would then complain about the checksum being invalid. https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1780137 Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- fs/ext4/balloc.c | 3 +++ fs/ext4/ialloc.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'fs') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e68cefe08261..aa52d87985aa 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -368,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, desc, bh))) { ext4_unlock_group(sb, block_group); @@ -386,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index fb83750c1a14..e9d8e2667ab5 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, EXT4_INODES_PER_GROUP(sb) / 8)) { @@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSBADCRC; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } -- cgit v1.2.3-58-ga151 From 5012284700775a4e6e3fbe7eac4c543c4874b559 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 28 Jul 2018 08:12:04 -0400 Subject: ext4: fix check to prevent initializing reserved inodes Commit 8844618d8aa7: "ext4: only look at the bg_flags field if it is valid" will complain if block group zero does not have the EXT4_BG_INODE_ZEROED flag set. Unfortunately, this is not correct, since a freshly created file system has this flag cleared. It gets almost immediately after the file system is mounted read-write --- but the following somewhat unlikely sequence will end up triggering a false positive report of a corrupted file system: mkfs.ext4 /dev/vdc mount -o ro /dev/vdc /vdc mount -o remount,rw /dev/vdc Instead, when initializing the inode table for block group zero, test to make sure that itable_unused count is not too large, since that is the case that will result in some or all of the reserved inodes getting cleared. This fixes the failures reported by Eric Whiteney when running generic/230 and generic/231 in the the nojournal test case. Fixes: 8844618d8aa7 ("ext4: only look at the bg_flags field if it is valid") Reported-by: Eric Whitney Signed-off-by: Theodore Ts'o --- fs/ext4/ialloc.c | 5 ++++- fs/ext4/super.c | 8 +------- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index e9d8e2667ab5..f336cbc6e932 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1388,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, ext4_itable_unused_count(sb, gdp)), sbi->s_inodes_per_block); - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || + ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)) < + EXT4_FIRST_INO(sb)))) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 680526e9ee96..b7f7922061be 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3141,14 +3141,8 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) if (!gdp) continue; - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) - continue; - if (group != 0) + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; - ext4_error(sb, "Inode table for bg 0 marked as " - "needing zeroing"); - if (sb_rdonly(sb)) - return ngroups; } return group; -- cgit v1.2.3-58-ga151