Add support for new compat feature "sparse_super2"

In practice, it is **extremely** rare for users to try to use more
than the first backup superblock located at the beginning of block
group tytso#1.  (i.e., at block number 32768 for file systems with a 4k
block size).  This new compat feature restricts the backup superblock
to block group tytso#1 and the last block group in the file system.

Aside from reducing the overhead of the file system by a small number
of blocks, by eliminating the rest of the backup superblocks, it
allows us to have a much more flexible metadata layout.  For example,
we can force all of the allocation bitmaps and inode table blocks to
the beginning of the disk, which allows most of the disk to be
exclusively used for contiguous data blocks.

This simplifies taking advantage of certain HDD specific features,
such as Shingled Magnetic Recording (aka Shingled Drives), and the
TCG's OPAL Storage Specification where having a simple mapping between
LBA block ranges and the data blocks used by the file system can make
life much simpler.

Signed-off-by: "Theodore Ts'o" <[email protected]>

Author: tytso

debugfs/set_fields.c

@@ -150,6 +150,8 @@ static struct field_set_info super_fields[] = {
 	{ "usr_quota_inum", &set_sb.s_usr_quota_inum, NULL, 4, parse_uint },
 	{ "grp_quota_inum", &set_sb.s_grp_quota_inum, NULL, 4, parse_uint },
 	{ "overhead_blocks", &set_sb.s_overhead_blocks, NULL, 4, parse_uint },
+	{ "backup_bgs", &set_sb.s_backup_bgs[0], NULL, 4, parse_uint,
+	  FLAG_ARRAY, 2 },
 	{ "checksum", &set_sb.s_checksum, NULL, 4, parse_uint },
 	{ 0, 0, 0, 0 }
 };

lib/e2p/feature.c

@@ -43,6 +43,8 @@ static struct feature feature_list[] = {
 			"lazy_bg" },
 	{	E2P_FEATURE_COMPAT, EXT2_FEATURE_COMPAT_EXCLUDE_BITMAP,
 			"snapshot_bitmap" },
+	{	E2P_FEATURE_COMPAT, EXT4_FEATURE_COMPAT_SPARSE_SUPER2,
+			"sparse_super2" },
 
 	{	E2P_FEATURE_RO_INCOMPAT, EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER,
 			"sparse_super" },

lib/e2p/ls.c

@@ -368,6 +368,14 @@ void list_super2(struct ext2_super_block * sb, FILE *f)
 			fprintf(f, "type %u\n", sb->s_jnl_backup_type);
 		}
 	}
+	if (sb->s_backup_bgs[0] || sb->s_backup_bgs[1]) {
+		fprintf(f, "Backup block groups:      ");
+		if (sb->s_backup_bgs[0])
+			fprintf(f, "%u ", sb->s_backup_bgs[0]);
+		if (sb->s_backup_bgs[1])
+			fprintf(f, "%u ", sb->s_backup_bgs[1]);
+		fputc('\n', f);
+	}
 	if (sb->s_snapshot_inum) {
 		fprintf(f, "Snapshot inode:           %u\n",
 			sb->s_snapshot_inum);

lib/ext2fs/closefs.c

@@ -35,8 +35,16 @@ static int test_root(unsigned int a, unsigned int b)
 
 int ext2fs_bg_has_super(ext2_filsys fs, dgrp_t group)
 {
-	if (!(fs->super->s_feature_ro_compat &
-	      EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER) || group <= 1)
+	if (group == 0)
+		return 1;
+	if (fs->super->s_feature_compat & EXT4_FEATURE_COMPAT_SPARSE_SUPER2) {
+		if (group == fs->super->s_backup_bgs[0] ||
+		    group == fs->super->s_backup_bgs[1])
+			return 1;
+		return 0;
+	}
+	if ((group <= 1) || !(fs->super->s_feature_ro_compat &
+			      EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER))
 		return 1;
 	if (!(group & 1))
 		return 0;

lib/ext2fs/ext2_fs.h

@@ -645,7 +645,8 @@ struct ext2_super_block {
 	__u32	s_usr_quota_inum;	/* inode number of user quota file */
 	__u32	s_grp_quota_inum;	/* inode number of group quota file */
 	__u32	s_overhead_blocks;	/* overhead blocks/clusters in fs */
-	__u32   s_reserved[108];        /* Padding to the end of the block */
+	__u32	s_backup_bgs[2];	/* If sparse_super2 enabled */
+	__u32   s_reserved[106];        /* Padding to the end of the block */
 	__u32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -696,6 +697,7 @@ struct ext2_super_block {
 #define EXT2_FEATURE_COMPAT_LAZY_BG		0x0040
 /* #define EXT2_FEATURE_COMPAT_EXCLUDE_INODE	0x0080 not used, legacy */
 #define EXT2_FEATURE_COMPAT_EXCLUDE_BITMAP	0x0100
+#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
 
 
 #define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001

lib/ext2fs/ext2fs.h

@@ -550,7 +550,8 @@ typedef struct ext2_icount *ext2_icount_t;
 					 EXT3_FEATURE_COMPAT_HAS_JOURNAL|\
 					 EXT2_FEATURE_COMPAT_RESIZE_INODE|\
 					 EXT2_FEATURE_COMPAT_DIR_INDEX|\
-					 EXT2_FEATURE_COMPAT_EXT_ATTR)
+					 EXT2_FEATURE_COMPAT_EXT_ATTR|\
+					 EXT4_FEATURE_COMPAT_SPARSE_SUPER2)
 
 /* This #ifdef is temporary until compression is fully supported */
 #ifdef ENABLE_COMPRESSION

lib/ext2fs/initialize.c

@@ -173,6 +173,8 @@ errcode_t ext2fs_initialize(const char *name, int flags,
 	set_field(s_raid_stripe_width, 0);	/* default stripe width: 0 */
 	set_field(s_log_groups_per_flex, 0);
 	set_field(s_flags, 0);
+	assign_field(s_backup_bgs[0]);
+	assign_field(s_backup_bgs[1]);
 	if (super->s_feature_incompat & ~EXT2_LIB_FEATURE_INCOMPAT_SUPP) {
 		retval = EXT2_ET_UNSUPP_FEATURE;
 		goto cleanup;
@@ -422,6 +424,21 @@ errcode_t ext2fs_initialize(const char *name, int flags,
 	 * count.
 	 */
 
+	/* Set up the locations of the backup superblocks */
+	if (super->s_feature_compat & EXT4_FEATURE_COMPAT_SPARSE_SUPER2) {
+		if (super->s_backup_bgs[0] >= fs->group_desc_count)
+			super->s_backup_bgs[0] = fs->group_desc_count - 1;
+		if (super->s_backup_bgs[1] >= fs->group_desc_count)
+			super->s_backup_bgs[1] = fs->group_desc_count - 1;
+		if (super->s_backup_bgs[0] == super->s_backup_bgs[1])
+			super->s_backup_bgs[1] = 0;
+		if (super->s_backup_bgs[0] > super->s_backup_bgs[1]) {
+			__u32 t = super->s_backup_bgs[0];
+			super->s_backup_bgs[0] = super->s_backup_bgs[1];
+			super->s_backup_bgs[1] = t;
+		}
+	}
+
 	retval = ext2fs_get_mem(strlen(fs->device_name) + 80, &buf);
 	if (retval)
 		goto cleanup;

lib/ext2fs/res_gdt.c

@@ -31,6 +31,19 @@ static unsigned int list_backups(ext2_filsys fs, unsigned int *three,
 	int mult = 3;
 	unsigned int ret;
 
+	if (fs->super->s_feature_compat & EXT4_FEATURE_COMPAT_SPARSE_SUPER2) {
+		if (*min == 1) {
+			*min += 1;
+			if (fs->super->s_backup_bgs[0])
+				return fs->super->s_backup_bgs[0];
+		}
+		if (*min == 2) {
+			*min += 1;
+			if (fs->super->s_backup_bgs[1])
+				return fs->super->s_backup_bgs[1];
+		}
+		return fs->group_desc_count;
+	}
 	if (!(fs->super->s_feature_ro_compat &
 	      EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
 		ret = *min;

lib/ext2fs/swapfs.c

@@ -99,6 +99,8 @@ void ext2fs_swap_super(struct ext2_super_block * sb)
 	}
 	for (; i < 17; i++)
 		sb->s_jnl_blocks[i] = ext2fs_swab32(sb->s_jnl_blocks[i]);
+	sb->s_backup_bgs[0] = ext2fs_swab32(sb->s_backup_bgs[0]);
+	sb->s_backup_bgs[1] = ext2fs_swab32(sb->s_backup_bgs[1]);
 }
 
 void ext2fs_swap_group_desc2(ext2_filsys fs, struct ext2_group_desc *gdp)

lib/ext2fs/tst_super_size.c

@@ -135,7 +135,8 @@ int main(int argc, char **argv)
 	check_field(s_usr_quota_inum, 4);
 	check_field(s_grp_quota_inum, 4);
 	check_field(s_overhead_blocks, 4);
-	check_field(s_reserved, 108 * 4);
+	check_field(s_backup_bgs, 8);
+	check_field(s_reserved, 106 * 4);
 	check_field(s_checksum, 4);
 	do_field("Superblock end", 0, 0, cur_offset, 1024);
 #endif

misc/ext4.5.in

@@ -171,6 +171,17 @@ kernels from mounting file systems that they could not understand.
 .\" .br
 .\" .B Future feature, available in e2fsprogs 1.43-WIP
 .TP
+.B sparse_super2
+.br
+This feature indicates that there will only at most two backup
+superblock and block group descriptors.  The block groups used to store
+the backup superblock and blockgroup descriptors are stored in the
+superblock, but typically, one will be located at the beginning of block
+group #1, and one in the last block group in the file system.  This is
+feature is essentially a more extreme version of sparse_super and is
+designed to allow the a much larger percentage of the disk to have
+contiguous blocks available for data files.
+.TP
 .B meta_bg
 .br
 This ext4 feature allows file systems to be resized on-line without explicitly

misc/mke2fs.8.in

@@ -274,6 +274,12 @@ small risk if the system crashes before the journal has been overwritten
 entirely one time.  If the option value is omitted, it defaults to 1 to
 enable lazy journal inode zeroing.
 .TP
+.BI num_backup_sb= <0|1|2>
+If the
+.B sparse_super2
+file system feature is enabled this option controls whether there will
+be 0, 1, or 2 backup superblocks created in the file system.
+.TP
 .BI root_owner [=uid:gid]
 Specify the numeric user and group ID of the root directory.  If no UID:GID
 is specified, use the user and group ID of the user running \fBmke2fs\fR.

misc/mke2fs.c

@@ -88,6 +88,7 @@ static int	discard = 1;	/* attempt to discard device before fs creation */
 static int	direct_io;
 static int	force;
 static int	noaction;
+static int	num_backups = 2; /* number of backup bg's for sparse_super2 */
 static uid_t	root_uid;
 static gid_t	root_gid;
 int	journal_size;
@@ -739,6 +740,21 @@ static void parse_extended_opts(struct ext2_super_block *param,
 				r_usage++;
 				continue;
 			}
+		} else if (strcmp(token, "num_backup_sb") == 0) {
+			if (!arg) {
+				r_usage++;
+				badopt = token;
+				continue;
+			}
+			num_backups = strtoul(arg, &p, 0);
+			if (*p || num_backups > 2) {
+				fprintf(stderr,
+					_("Invalid # of backup "
+					  "superbocks: %s\n"),
+					arg);
+				r_usage++;
+				continue;
+			}
 		} else if (strcmp(token, "stride") == 0) {
 			if (!arg) {
 				r_usage++;
@@ -895,6 +911,7 @@ static void parse_extended_opts(struct ext2_super_block *param,
 			"\tis set off by an equals ('=') sign.\n\n"
 			"Valid extended options are:\n"
 			"\tmmp_update_interval=<interval>\n"
+			"\tnum_backup_sb=<0|1|2>\n"
 			"\tstride=<RAID per-disk data chunk in blocks>\n"
 			"\tstripe-width=<RAID stride * data disks in blocks>\n"
 			"\toffset=<offset to create the file system>\n"
@@ -925,7 +942,8 @@ static __u32 ok_features[3] = {
 	EXT3_FEATURE_COMPAT_HAS_JOURNAL |
 		EXT2_FEATURE_COMPAT_RESIZE_INODE |
 		EXT2_FEATURE_COMPAT_DIR_INDEX |
-		EXT2_FEATURE_COMPAT_EXT_ATTR,
+		EXT2_FEATURE_COMPAT_EXT_ATTR |
+		EXT4_FEATURE_COMPAT_SPARSE_SUPER2,
 	/* Incompat */
 	EXT2_FEATURE_INCOMPAT_FILETYPE|
 		EXT3_FEATURE_INCOMPAT_EXTENTS|
@@ -1975,6 +1993,8 @@ static void PRS(int argc, char *argv[])
 	}
 #endif
 
+	num_backups = get_int_from_profile(fs_types, "num_backup_sb", 2);
+
 	blocksize = EXT2_BLOCK_SIZE(&fs_param);
 
 	/*
@@ -2171,6 +2191,13 @@ static void PRS(int argc, char *argv[])
 	ext2fs_r_blocks_count_set(&fs_param, reserved_ratio *
 				  ext2fs_blocks_count(&fs_param) / 100.0);
 
+	if (fs_param.s_feature_compat & EXT4_FEATURE_COMPAT_SPARSE_SUPER2) {
+		if (num_backups >= 1)
+			fs_param.s_backup_bgs[0] = 1;
+		if (num_backups >= 2)
+			fs_param.s_backup_bgs[1] = ~0;
+	}
+
 	free(fs_type);
 	free(usage_types);
 }
@@ -2603,8 +2630,8 @@ int main (int argc, char *argv[])
 		read_bb_file(fs, &bb_list, bad_blocks_filename);
 	if (cflag)
 		test_disk(fs, &bb_list);
-
 	handle_bad_blocks(fs, bb_list);
+
 	fs->stride = fs_stride = fs->super->s_raid_stride;
 	if (!quiet)
 		printf("%s", _("Allocating group tables: "));

misc/mke2fs.conf.5.in

@@ -360,6 +360,11 @@ first mounted.
 .I journal_location
 This relation specifies the location of the journal.
 .TP
+.I num_backup_sb
+This relation indicates whether file systems with the
+.B sparse_super2
+feature enabled should be created with 0, 1, or 2 backup superblocks.
+.TP
 .I inode_ratio
 This relation specifies the default inode ratio if the user does not
 specify one on the command line.

resize/online.c

@@ -76,6 +76,14 @@ errcode_t online_resize_fs(ext2_filsys fs, const char *mtpt,
 			no_resize_ioctl = 1;
 	}
 
+	if (EXT2_HAS_COMPAT_FEATURE(fs->super,
+				    EXT4_FEATURE_COMPAT_SPARSE_SUPER2) &&
+	    (access("/sys/fs/ext4/features/sparse_super2", R_OK) != 0)) {
+		com_err(program_name, 0, _("kernel does not support online "
+					   "resize with sparse_super2"));
+		exit(1);
+	}
+
 	printf(_("Filesystem at %s is mounted on %s; "
 		 "on-line resizing required\n"), fs->device_name, mtpt);