Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Miscellaneous ext4 bug fixes (all stable fodder)"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: improve explanation of a mount failure caused by a misconfigured kernel
  jbd2: do not clear the BH_Mapped flag when forgetting a metadata buffer
  jbd2: move the clearing of b_modified flag to the journal_unmap_buffer()
  ext4: add cond_resched() to ext4_protect_reserved_inode
  ext4: fix checksum errors with indexed dirs
  ext4: fix support for inode sizes > 1024 bytes
  ext4: simplify checking quota limits in ext4_statfs()
  ext4: don't assume that mmp_nodename/bdevname have NUL

Author: torvalds

fs/ext4/block_validity.c

@@ -207,6 +207,7 @@ static int ext4_protect_reserved_inode(struct super_block *sb,
 		return PTR_ERR(inode);
 	num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
 	while (i < num) {
+		cond_resched();
 		map.m_lblk = i;
 		map.m_len = num - i;
 		n = ext4_map_blocks(NULL, inode, &map, 0);

fs/ext4/dir.c

@@ -129,12 +129,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 		if (err != ERR_BAD_DX_DIR) {
 			return err;
 		}
-		/*
-		 * We don't set the inode dirty flag since it's not
-		 * critical that it get flushed back to the disk.
-		 */
-		ext4_clear_inode_flag(file_inode(file),
-				      EXT4_INODE_INDEX);
+		/* Can we just clear INDEX flag to ignore htree information? */
+		if (!ext4_has_metadata_csum(sb)) {
+			/*
+			 * We don't set the inode dirty flag since it's not
+			 * critical that it gets flushed back to the disk.
+			 */
+			ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+		}
 	}
 
 	if (ext4_has_inline_data(inode)) {

fs/ext4/ext4.h

@@ -2544,8 +2544,11 @@ void ext4_insert_dentry(struct inode *inode,
 			struct ext4_filename *fname);
 static inline void ext4_update_dx_flag(struct inode *inode)
 {
-	if (!ext4_has_feature_dir_index(inode->i_sb))
+	if (!ext4_has_feature_dir_index(inode->i_sb)) {
+		/* ext4_iget() should have caught this... */
+		WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
 		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+	}
 }
 static const unsigned char ext4_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK

fs/ext4/inode.c

@@ -4644,6 +4644,18 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	}
+	/*
+	 * If dir_index is not enabled but there's dir with INDEX flag set,
+	 * we'd normally treat htree data as empty space. But with metadata
+	 * checksumming that corrupts checksums so forbid that.
+	 */
+	if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
+		ext4_error_inode(inode, function, line, 0,
+			 "iget: Dir with htree data on filesystem without dir_index feature.");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_disksize = inode->i_size;
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;

fs/ext4/mmp.c

@@ -120,10 +120,10 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
 {
 	__ext4_warning(sb, function, line, "%s", msg);
 	__ext4_warning(sb, function, line,
-		       "MMP failure info: last update time: %llu, last update "
-		       "node: %s, last update device: %s",
-		       (long long unsigned int) le64_to_cpu(mmp->mmp_time),
-		       mmp->mmp_nodename, mmp->mmp_bdevname);
+		       "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s",
+		       (unsigned long long)le64_to_cpu(mmp->mmp_time),
+		       (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename,
+		       (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname);
 }
 
 /*
@@ -154,6 +154,7 @@ static int kmmpd(void *data)
 	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
 				 EXT4_MMP_MIN_CHECK_INTERVAL);
 	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
 	bdevname(bh->b_bdev, mmp->mmp_bdevname);
 
 	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
@@ -379,7 +380,8 @@ int ext4_multi_mount_protect(struct super_block *sb,
 	/*
 	 * Start a kernel thread to update the MMP block periodically.
 	 */
-	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s",
+					     (int)sizeof(mmp->mmp_bdevname),
 					     bdevname(bh->b_bdev,
 						      mmp->mmp_bdevname));
 	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {

fs/ext4/namei.c

@@ -2213,6 +2213,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		retval = ext4_dx_add_entry(handle, &fname, dir, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
 			goto out;
+		/* Can we just ignore htree data? */
+		if (ext4_has_metadata_csum(sb)) {
+			EXT4_ERROR_INODE(dir,
+				"Directory has corrupted htree index.");
+			retval = -EFSCORRUPTED;
+			goto out;
+		}
 		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);

fs/ext4/super.c

@@ -3009,17 +3009,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 		return 0;
 	}
 
-#ifndef CONFIG_QUOTA
-	if (ext4_has_feature_quota(sb) && !readonly) {
+#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2)
+	if (!readonly && (ext4_has_feature_quota(sb) ||
+			  ext4_has_feature_project(sb))) {
 		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
-		return 0;
-	}
-	if (ext4_has_feature_project(sb) && !readonly) {
-		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with project quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
+			 "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2");
 		return 0;
 	}
 #endif  /* CONFIG_QUOTA */
@@ -3814,6 +3808,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
+	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
+	    blocksize > EXT4_MAX_BLOCK_SIZE) {
+		ext4_msg(sb, KERN_ERR,
+		       "Unsupported filesystem blocksize %d (%d log_block_size)",
+			 blocksize, le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
 		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
 		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
@@ -3831,6 +3834,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			ext4_msg(sb, KERN_ERR,
 			       "unsupported inode size: %d",
 			       sbi->s_inode_size);
+			ext4_msg(sb, KERN_ERR, "blocksize: %d", blocksize);
 			goto failed_mount;
 		}
 		/*
@@ -4033,14 +4037,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ext4_feature_set_ok(sb, (sb_rdonly(sb))))
 		goto failed_mount;
 
-	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
-	    blocksize > EXT4_MAX_BLOCK_SIZE) {
-		ext4_msg(sb, KERN_ERR,
-		       "Unsupported filesystem blocksize %d (%d log_block_size)",
-			 blocksize, le32_to_cpu(es->s_log_block_size));
-		goto failed_mount;
-	}
 	if (le32_to_cpu(es->s_log_block_size) >
 	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
 		ext4_msg(sb, KERN_ERR,
@@ -5585,10 +5581,7 @@ static int ext4_statfs_project(struct super_block *sb,
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = 0;
-	if (dquot->dq_dqb.dqb_bsoftlimit &&
-	    (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit))
-		limit = dquot->dq_dqb.dqb_bsoftlimit;
+	limit = dquot->dq_dqb.dqb_bsoftlimit;
 	if (dquot->dq_dqb.dqb_bhardlimit &&
 	    (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
 		limit = dquot->dq_dqb.dqb_bhardlimit;
@@ -5603,10 +5596,7 @@ static int ext4_statfs_project(struct super_block *sb,
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = 0;
-	if (dquot->dq_dqb.dqb_isoftlimit &&
-	    (!limit || dquot->dq_dqb.dqb_isoftlimit < limit))
-		limit = dquot->dq_dqb.dqb_isoftlimit;
+	limit = dquot->dq_dqb.dqb_isoftlimit;
 	if (dquot->dq_dqb.dqb_ihardlimit &&
 	    (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
 		limit = dquot->dq_dqb.dqb_ihardlimit;

fs/jbd2/commit.c

@@ -976,29 +976,33 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 * it. */
 
 		/*
-		* A buffer which has been freed while still being journaled by
-		* a previous transaction.
-		*/
-		if (buffer_freed(bh)) {
+		 * A buffer which has been freed while still being journaled
+		 * by a previous transaction, refile the buffer to BJ_Forget of
+		 * the running transaction. If the just committed transaction
+		 * contains "add to orphan" operation, we can completely
+		 * invalidate the buffer now. We are rather through in that
+		 * since the buffer may be still accessible when blocksize <
+		 * pagesize and it is attached to the last partial page.
+		 */
+		if (buffer_freed(bh) && !jh->b_next_transaction) {
+			struct address_space *mapping;
+
+			clear_buffer_freed(bh);
+			clear_buffer_jbddirty(bh);
+
 			/*
-			 * If the running transaction is the one containing
-			 * "add to orphan" operation (b_next_transaction !=
-			 * NULL), we have to wait for that transaction to
-			 * commit before we can really get rid of the buffer.
-			 * So just clear b_modified to not confuse transaction
-			 * credit accounting and refile the buffer to
-			 * BJ_Forget of the running transaction. If the just
-			 * committed transaction contains "add to orphan"
-			 * operation, we can completely invalidate the buffer
-			 * now. We are rather through in that since the
-			 * buffer may be still accessible when blocksize <
-			 * pagesize and it is attached to the last partial
-			 * page.
+			 * Block device buffers need to stay mapped all the
+			 * time, so it is enough to clear buffer_jbddirty and
+			 * buffer_freed bits. For the file mapping buffers (i.e.
+			 * journalled data) we need to unmap buffer and clear
+			 * more bits. We also need to be careful about the check
+			 * because the data page mapping can get cleared under
+			 * out hands, which alse need not to clear more bits
+			 * because the page and buffers will be freed and can
+			 * never be reused once we are done with them.
 			 */
-			jh->b_modified = 0;
-			if (!jh->b_next_transaction) {
-				clear_buffer_freed(bh);
-				clear_buffer_jbddirty(bh);
+			mapping = READ_ONCE(bh->b_page->mapping);
+			if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) {
 				clear_buffer_mapped(bh);
 				clear_buffer_new(bh);
 				clear_buffer_req(bh);

fs/jbd2/transaction.c

@@ -2329,14 +2329,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 			return -EBUSY;
 		}
 		/*
-		 * OK, buffer won't be reachable after truncate. We just set
-		 * j_next_transaction to the running transaction (if there is
-		 * one) and mark buffer as freed so that commit code knows it
-		 * should clear dirty bits when it is done with the buffer.
+		 * OK, buffer won't be reachable after truncate. We just clear
+		 * b_modified to not confuse transaction credit accounting, and
+		 * set j_next_transaction to the running transaction (if there
+		 * is one) and mark buffer as freed so that commit code knows
+		 * it should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
 			jh->b_next_transaction = journal->j_running_transaction;
+		jh->b_modified = 0;
 		spin_unlock(&journal->j_list_lock);
 		spin_unlock(&jh->b_state_lock);
 		write_unlock(&journal->j_state_lock);