Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 bug fixes from Ted Ts'o:
"The following are all bug fixes and regressions. The most notable are
the ones which cause problems for ext4 on RAID --- a performance
problem when mounting very large filesystems, and a kernel OOPS when
doing an rm -rf on large directory hierarchies on fast devices."
* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: fix kernel BUG on large-scale rm -rf commands
ext4: fix long mount times on very big file systems
ext4: don't call ext4_error while block group is locked
ext4: avoid kmemcheck complaint from reading uninitialized memory
ext4: make sure the journal sb is written in ext4_clear_journal_err()
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index d23b31c..1b50890 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -280,14 +280,18 @@
return desc;
}
-static int ext4_valid_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- unsigned int block_group,
- struct buffer_head *bh)
+/*
+ * Return the block number which was discovered to be invalid, or 0 if
+ * the block bitmap is valid.
+ */
+static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *desc,
+ unsigned int block_group,
+ struct buffer_head *bh)
{
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
- ext4_fsblk_t bitmap_blk;
+ ext4_fsblk_t blk;
ext4_fsblk_t group_first_block;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
@@ -297,37 +301,33 @@
* or it has to also read the block group where the bitmaps
* are located to verify they are set.
*/
- return 1;
+ return 0;
}
group_first_block = ext4_group_first_block_no(sb, block_group);
/* check whether block bitmap block number is set */
- bitmap_blk = ext4_block_bitmap(sb, desc);
- offset = bitmap_blk - group_first_block;
+ blk = ext4_block_bitmap(sb, desc);
+ offset = blk - group_first_block;
if (!ext4_test_bit(offset, bh->b_data))
/* bad block bitmap */
- goto err_out;
+ return blk;
/* check whether the inode bitmap block number is set */
- bitmap_blk = ext4_inode_bitmap(sb, desc);
- offset = bitmap_blk - group_first_block;
+ blk = ext4_inode_bitmap(sb, desc);
+ offset = blk - group_first_block;
if (!ext4_test_bit(offset, bh->b_data))
/* bad block bitmap */
- goto err_out;
+ return blk;
/* check whether the inode table block number is set */
- bitmap_blk = ext4_inode_table(sb, desc);
- offset = bitmap_blk - group_first_block;
+ blk = ext4_inode_table(sb, desc);
+ offset = blk - group_first_block;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
offset + EXT4_SB(sb)->s_itb_per_group,
offset);
- if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
- /* good bitmap for inode tables */
- return 1;
-
-err_out:
- ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
- block_group, bitmap_blk);
+ if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group)
+ /* bad bitmap for inode tables */
+ return blk;
return 0;
}
@@ -336,14 +336,26 @@
unsigned int block_group,
struct buffer_head *bh)
{
+ ext4_fsblk_t blk;
+
if (buffer_verified(bh))
return;
ext4_lock_group(sb, block_group);
- if (ext4_valid_block_bitmap(sb, desc, block_group, bh) &&
- ext4_block_bitmap_csum_verify(sb, block_group, desc, bh,
- EXT4_BLOCKS_PER_GROUP(sb) / 8))
- set_buffer_verified(bh);
+ blk = ext4_valid_block_bitmap(sb, desc, block_group, bh);
+ if (unlikely(blk != 0)) {
+ ext4_unlock_group(sb, block_group);
+ ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
+ block_group, blk);
+ return;
+ }
+ if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
+ desc, bh, EXT4_BLOCKS_PER_GROUP(sb) / 8))) {
+ ext4_unlock_group(sb, block_group);
+ ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+ return;
+ }
+ set_buffer_verified(bh);
ext4_unlock_group(sb, block_group);
}
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index f8716ea..5c2d181 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -79,7 +79,6 @@
if (provided == calculated)
return 1;
- ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group);
return 0;
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index cd0c7ed..aabbb3f 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2662,6 +2662,7 @@
}
path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
+ i = 0;
if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
err = -EIO;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3e0851e..c6e0cb3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -948,6 +948,7 @@
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
+ ei->i_da_metadata_calc_last_lblock = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
@@ -3108,6 +3109,10 @@
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
int s, j, count = 0;
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC))
+ return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) +
+ sbi->s_itb_per_group + 2);
+
first_block = le32_to_cpu(sbi->s_es->s_first_data_block) +
(grp * EXT4_BLOCKS_PER_GROUP(sb));
last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1;
@@ -4419,6 +4424,7 @@
ext4_commit_super(sb, 1);
jbd2_journal_clear_err(journal);
+ jbd2_journal_update_sb_errno(journal);
}
}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 8625da2..e149b99 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1377,7 +1377,7 @@
* Update a journal's errno. Write updated superblock to disk waiting for IO
* to complete.
*/
-static void jbd2_journal_update_sb_errno(journal_t *journal)
+void jbd2_journal_update_sb_errno(journal_t *journal)
{
journal_superblock_t *sb = journal->j_superblock;
@@ -1390,6 +1390,7 @@
jbd2_write_superblock(journal, WRITE_SYNC);
}
+EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
/*
* Read the superblock for a given journal, performing initial
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index f334c7f..3efc43f 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1125,6 +1125,7 @@
extern int jbd2_journal_recover (journal_t *journal);
extern int jbd2_journal_wipe (journal_t *, int);
extern int jbd2_journal_skip_recovery (journal_t *);
+extern void jbd2_journal_update_sb_errno(journal_t *);
extern void jbd2_journal_update_sb_log_tail (journal_t *, tid_t,
unsigned long, int);
extern void __jbd2_journal_abort_hard (journal_t *);