btrfs: add support for 4-copy replication (raid1c4)

Add new block group profile to store 4 copies in a simliar way that
current RAID1 does.  The profile attributes and constraints are defined
in the raid table and used by the same code that already handles the 2-
and 3-copy RAID1.

The minimum number of devices is 4, the maximum number of devices/chunks
that can be lost/damaged is 3. There is no comparable traditional RAID
level, the profile is added for future needs to accompany triple-parity
and beyond.

Signed-off-by: David Sterba <[email protected]>

Author: kdave

fs/btrfs/ctree.h

@@ -57,9 +57,9 @@ struct btrfs_ref;
  * filesystem data as well that can be used to read data in order to repair
  * read errors on other disks.
  *
- * Current value is derived from RAID1C3 with 3 copies.
+ * Current value is derived from RAID1C4 with 4 copies.
  */
-#define BTRFS_MAX_MIRRORS (3 + 1)
+#define BTRFS_MAX_MIRRORS (4 + 1)
 
 #define BTRFS_MAX_LEVEL 8
 

fs/btrfs/super.c

@@ -1937,6 +1937,8 @@ static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 		num_stripes = 2;
 	else if (type & BTRFS_BLOCK_GROUP_RAID1C3)
 		num_stripes = 3;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1C4)
+		num_stripes = 4;
 	else if (type & BTRFS_BLOCK_GROUP_RAID10)
 		num_stripes = 4;
 

fs/btrfs/volumes.c

@@ -70,6 +70,18 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C3,
 		.mindev_error	= BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
 	},
+	[BTRFS_RAID_RAID1C4] = {
+		.sub_stripes	= 1,
+		.dev_stripes	= 1,
+		.devs_max	= 0,
+		.devs_min	= 4,
+		.tolerated_failures = 3,
+		.devs_increment	= 4,
+		.ncopies	= 4,
+		.raid_name	= "raid1c4",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C4,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
+	},
 	[BTRFS_RAID_DUP] = {
 		.sub_stripes	= 1,
 		.dev_stripes	= 2,

fs/btrfs/volumes.h

@@ -547,6 +547,8 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
 		return BTRFS_RAID_RAID1;
 	else if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
 		return BTRFS_RAID_RAID1C3;
+	else if (flags & BTRFS_BLOCK_GROUP_RAID1C4)
+		return BTRFS_RAID_RAID1C4;
 	else if (flags & BTRFS_BLOCK_GROUP_DUP)
 		return BTRFS_RAID_DUP;
 	else if (flags & BTRFS_BLOCK_GROUP_RAID0)

include/uapi/linux/btrfs.h

@@ -833,6 +833,7 @@ enum btrfs_err_code {
 	BTRFS_ERROR_DEV_ONLY_WRITABLE,
 	BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS,
 	BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
+	BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
 };
 
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \

include/uapi/linux/btrfs_tree.h

@@ -842,6 +842,7 @@ struct btrfs_dev_replace_item {
 #define BTRFS_BLOCK_GROUP_RAID5         (1ULL << 7)
 #define BTRFS_BLOCK_GROUP_RAID6         (1ULL << 8)
 #define BTRFS_BLOCK_GROUP_RAID1C3       (1ULL << 9)
+#define BTRFS_BLOCK_GROUP_RAID1C4       (1ULL << 10)
 #define BTRFS_BLOCK_GROUP_RESERVED	(BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
 					 BTRFS_SPACE_INFO_GLOBAL_RSV)
 
@@ -854,6 +855,7 @@ enum btrfs_raid_types {
 	BTRFS_RAID_RAID5,
 	BTRFS_RAID_RAID6,
 	BTRFS_RAID_RAID1C3,
+	BTRFS_RAID_RAID1C4,
 	BTRFS_NR_RAID_TYPES
 };
 
@@ -864,6 +866,7 @@ enum btrfs_raid_types {
 #define BTRFS_BLOCK_GROUP_PROFILE_MASK	(BTRFS_BLOCK_GROUP_RAID0 |   \
 					 BTRFS_BLOCK_GROUP_RAID1 |   \
 					 BTRFS_BLOCK_GROUP_RAID1C3 | \
+					 BTRFS_BLOCK_GROUP_RAID1C4 | \
 					 BTRFS_BLOCK_GROUP_RAID5 |   \
 					 BTRFS_BLOCK_GROUP_RAID6 |   \
 					 BTRFS_BLOCK_GROUP_DUP |     \
@@ -872,7 +875,8 @@ enum btrfs_raid_types {
 					 BTRFS_BLOCK_GROUP_RAID6)
 
 #define BTRFS_BLOCK_GROUP_RAID1_MASK	(BTRFS_BLOCK_GROUP_RAID1 |   \
-					 BTRFS_BLOCK_GROUP_RAID1C3)
+					 BTRFS_BLOCK_GROUP_RAID1C3 | \
+					 BTRFS_BLOCK_GROUP_RAID1C4)
 
 /*
  * We need a bit for restriper to be able to tell when chunks of type