1 files changed, 144 insertions, 40 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index eb104e8476f0..ba2396a7bd04 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -405,6 +405,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 
 static void ext4_handle_error(struct super_block *sb)
 {
+	if (test_opt(sb, WARN_ON_ERROR))
+		WARN_ON_ONCE(1);
+
 	if (sb_rdonly(sb))
 		return;
 
@@ -740,6 +743,9 @@ __acquires(bitlock)
 		va_end(args);
 	}
 
+	if (test_opt(sb, WARN_ON_ERROR))
+		WARN_ON_ONCE(1);
+
 	if (test_opt(sb, ERRORS_CONT)) {
 		ext4_commit_super(sb, 0);
 		return;
@@ -763,6 +769,36 @@ __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;
@@ -1237,19 +1273,13 @@ static bool ext4_dummy_context(struct inode *inode)
 	return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
 }
 
-static unsigned ext4_max_namelen(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
-		EXT4_NAME_LEN;
-}
-
 static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
 	.set_context		= ext4_set_context,
 	.dummy_context		= ext4_dummy_context,
 	.empty_dir		= ext4_empty_dir,
-	.max_namelen		= ext4_max_namelen,
+	.max_namelen		= EXT4_NAME_LEN,
 };
 #endif
 
@@ -1347,7 +1377,8 @@ enum {
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
-	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
+	Opt_nowarn_on_error, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
@@ -1414,6 +1445,8 @@ static const match_table_t tokens = {
 	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
+	{Opt_warn_on_error, "warn_on_error"},
+	{Opt_nowarn_on_error, "nowarn_on_error"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
 	{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
@@ -1578,6 +1611,8 @@ static const struct mount_opts {
 	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
 	{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
+	{Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
+	{Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
 	{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
 	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
@@ -2116,12 +2151,12 @@ 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 +2189,7 @@ 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 +2201,7 @@ 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)
@@ -2307,6 +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 block_bitmap;
 	ext4_fsblk_t inode_bitmap;
 	ext4_fsblk_t inode_table;
@@ -2339,6 +2375,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (block_bitmap >= sb_block + 1 &&
+		    block_bitmap <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Block bitmap for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Block bitmap for group %u not in group "
@@ -2353,6 +2397,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (inode_bitmap >= sb_block + 1 &&
+		    inode_bitmap <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode bitmap for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode bitmap for group %u not in group "
@@ -2367,6 +2419,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (inode_table >= sb_block + 1 &&
+		    inode_table <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode table for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -3073,13 +3133,22 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
 	ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
 	struct ext4_group_desc *gdp = NULL;
 
+	if (!ext4_has_group_desc_csum(sb))
+		return ngroups;
+
 	for (group = 0; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp)
 			continue;
 
-		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+			continue;
+		if (group != 0)
 			break;
+		ext4_error(sb, "Inode table for bg 0 marked as "
+			   "needing zeroing");
+		if (sb_rdonly(sb))
+			return ngroups;
 	}
 
 	return group;
@@ -3718,6 +3787,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 le32_to_cpu(es->s_log_block_size));
 		goto failed_mount;
 	}
+	if (le32_to_cpu(es->s_log_cluster_size) >
+	    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid log cluster size: %u",
+			 le32_to_cpu(es->s_log_cluster_size));
+		goto failed_mount;
+	}
 
 	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
 		ext4_msg(sb, KERN_ERR,
@@ -3732,8 +3808,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 					" that may contain inline data");
 			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
 		}
-		err = bdev_dax_supported(sb, blocksize);
-		if (err) {
+		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
 			ext4_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
@@ -3783,6 +3858,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	} else {
 		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
 		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+		if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
+			ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
+				 sbi->s_first_ino);
+			goto failed_mount;
+		}
 		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
 		    (!is_power_of_2(sbi->s_inode_size)) ||
 		    (sbi->s_inode_size > blocksize)) {
@@ -3859,13 +3939,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "block size (%d)", clustersize, blocksize);
 			goto failed_mount;
 		}
-		if (le32_to_cpu(es->s_log_cluster_size) >
-		    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Invalid log cluster size: %u",
-				 le32_to_cpu(es->s_log_cluster_size));
-			goto failed_mount;
-		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
 		sbi->s_clusters_per_group =
@@ -3886,10 +3959,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	} else {
 		if (clustersize != blocksize) {
-			ext4_warning(sb, "fragment/cluster size (%d) != "
-				     "block size (%d)", clustersize,
-				     blocksize);
-			clustersize = blocksize;
+			ext4_msg(sb, KERN_ERR,
+				 "fragment/cluster size (%d) != "
+				 "block size (%d)", clustersize, blocksize);
+			goto failed_mount;
 		}
 		if (sbi->s_blocks_per_group > blocksize * 8) {
 			ext4_msg(sb, KERN_ERR,
@@ -3943,6 +4016,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 ext4_blocks_count(es));
 		goto failed_mount;
 	}
+	if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) &&
+	    (sbi->s_cluster_ratio == 1)) {
+		ext4_msg(sb, KERN_WARNING, "bad geometry: first data "
+			 "block is 0 with a 1k block and cluster size");
+		goto failed_mount;
+	}
+
 	blocks_count = (ext4_blocks_count(es) -
 			le32_to_cpu(es->s_first_data_block) +
 			EXT4_BLOCKS_PER_GROUP(sb) - 1);
@@ -3970,14 +4050,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount;
 		}
 	}
-	sbi->s_group_desc = kvmalloc(db_count *
-					  sizeof(struct buffer_head *),
-					  GFP_KERNEL);
+	sbi->s_group_desc = kvmalloc_array(db_count,
+					   sizeof(struct buffer_head *),
+					   GFP_KERNEL);
 	if (sbi->s_group_desc == NULL) {
 		ext4_msg(sb, KERN_ERR, "not enough memory");
 		ret = -ENOMEM;
 		goto failed_mount;
 	}
+	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+		ret = -EINVAL;
+		goto failed_mount;
+	}
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
@@ -4224,8 +4312,12 @@ 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 &&
@@ -4709,6 +4801,14 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 
 	if (!sbh || block_device_ejected(sb))
 		return error;
+
+	/*
+	 * The superblock bh should be mapped, but it might not be if the
+	 * device was hot-removed. Not much we can do but fail the I/O.
+	 */
+	if (!buffer_mapped(sbh))
+		return error;
+
 	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
@@ -4760,11 +4860,7 @@ 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 +5261,12 @@ 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 +5290,11 @@ 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 +5355,8 @@ 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) ?