ext4: read-only support for bigalloc file systems

This adds supports for bigalloc file systems.  It teaches the mount
code just enough about bigalloc superblock fields that it will mount
the file system without freaking out that the number of blocks per
group is too big.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/ext4.h

@@ -239,8 +239,11 @@ struct ext4_io_submit {
 # define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
 #endif
 #define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
+#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
+					 EXT4_SB(s)->s_cluster_bits)
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
+# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
 #else
 # define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
 #endif
@@ -306,6 +309,7 @@ struct flex_groups {
 #define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
 #ifdef __KERNEL__
 # define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
+# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
 # define EXT4_DESC_PER_BLOCK(s)		(EXT4_SB(s)->s_desc_per_block)
 # define EXT4_INODES_PER_GROUP(s)	(EXT4_SB(s)->s_inodes_per_group)
 # define EXT4_DESC_PER_BLOCK_BITS(s)	(EXT4_SB(s)->s_desc_per_block_bits)
@@ -975,9 +979,9 @@ struct ext4_super_block {
 /*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
 	__le32	s_first_data_block;	/* First Data Block */
 	__le32	s_log_block_size;	/* Block size */
-	__le32	s_obso_log_frag_size;	/* Obsoleted fragment size */
+	__le32	s_log_cluster_size;	/* Allocation cluster size */
 /*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
-	__le32	s_obso_frags_per_group;	/* Obsoleted fragments per group */
+	__le32	s_clusters_per_group;	/* # Clusters per group */
 	__le32	s_inodes_per_group;	/* # Inodes per group */
 	__le32	s_mtime;		/* Mount time */
 /*30*/	__le32	s_wtime;		/* Write time */
@@ -1073,7 +1077,10 @@ struct ext4_super_block {
 	__u8	s_last_error_func[32];	/* function where the error happened */
 #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
 	__u8	s_mount_opts[64];
-	__le32	s_reserved[112];        /* Padding to the end of the block */
+	__le32	s_usr_quota_inum;	/* inode for tracking user quota */
+	__le32	s_grp_quota_inum;	/* inode for tracking group quota */
+	__le32	s_overhead_clusters;	/* overhead blocks/clusters in fs */
+	__le32  s_reserved[109];        /* Padding to the end of the block */
 };
 
 #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
@@ -1093,6 +1100,7 @@ struct ext4_sb_info {
 	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
 	unsigned long s_inodes_per_block;/* Number of inodes per block */
 	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_clusters_per_group; /* Number of clusters in a group */
 	unsigned long s_inodes_per_group;/* Number of inodes in a group */
 	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
 	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
@@ -1101,6 +1109,8 @@ struct ext4_sb_info {
 	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
 	unsigned long s_overhead_last;  /* Last calculated overhead */
 	unsigned long s_blocks_last;    /* Last seen block count */
+	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
+	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
 	struct buffer_head * s_sbh;	/* Buffer containing the super block */
 	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
@@ -1367,6 +1377,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
 #define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
+#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
 
 #define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
 #define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002

fs/ext4/super.c

@@ -1953,7 +1953,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		res = MS_RDONLY;
 	}
 	if (read_only)
-		return res;
+		goto done;
 	if (!(sbi->s_mount_state & EXT4_VALID_FS))
 		ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
 			 "running e2fsck is recommended");
@@ -1984,6 +1984,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 
 	ext4_commit_super(sb, 1);
+done:
 	if (test_opt(sb, DEBUG))
 		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
 				"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
@@ -3105,10 +3106,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	char *cp;
 	const char *descr;
 	int ret = -ENOMEM;
-	int blocksize;
+	int blocksize, clustersize;
 	unsigned int db_count;
 	unsigned int i;
-	int needs_recovery, has_huge_files;
+	int needs_recovery, has_huge_files, has_bigalloc;
 	__u64 blocks_count;
 	int err;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
@@ -3412,12 +3413,53 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sb->s_dirt = 1;
 	}
 
-	if (sbi->s_blocks_per_group > blocksize * 8) {
-		ext4_msg(sb, KERN_ERR,
-		       "#blocks per group too big: %lu",
-		       sbi->s_blocks_per_group);
-		goto failed_mount;
+	/* Handle clustersize */
+	clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
+	has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				EXT4_FEATURE_RO_COMPAT_BIGALLOC);
+	if (has_bigalloc) {
+		if (clustersize < blocksize) {
+			ext4_msg(sb, KERN_ERR,
+				 "cluster size (%d) smaller than "
+				 "block size (%d)", clustersize, blocksize);
+			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 =
+			le32_to_cpu(es->s_clusters_per_group);
+		if (sbi->s_clusters_per_group > blocksize * 8) {
+			ext4_msg(sb, KERN_ERR,
+				 "#clusters per group too big: %lu",
+				 sbi->s_clusters_per_group);
+			goto failed_mount;
+		}
+		if (sbi->s_blocks_per_group !=
+		    (sbi->s_clusters_per_group * (clustersize / blocksize))) {
+			ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
+				 "clusters per group (%lu) inconsistent",
+				 sbi->s_blocks_per_group,
+				 sbi->s_clusters_per_group);
+			goto failed_mount;
+		}
+	} else {
+		if (clustersize != blocksize) {
+			ext4_warning(sb, "fragment/cluster size (%d) != "
+				     "block size (%d)", clustersize,
+				     blocksize);
+			clustersize = blocksize;
+		}
+		if (sbi->s_blocks_per_group > blocksize * 8) {
+			ext4_msg(sb, KERN_ERR,
+				 "#blocks per group too big: %lu",
+				 sbi->s_blocks_per_group);
+			goto failed_mount;
+		}
+		sbi->s_clusters_per_group = sbi->s_blocks_per_group;
+		sbi->s_cluster_bits = 0;
 	}
+	sbi->s_cluster_ratio = clustersize / blocksize;
+
 	if (sbi->s_inodes_per_group > blocksize * 8) {
 		ext4_msg(sb, KERN_ERR,
 		       "#inodes per group too big: %lu",