[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20120306204807.1663.62824.stgit@elm3b70.beaverton.ibm.com>
Date: Tue, 06 Mar 2012 12:48:07 -0800
From: "Darrick J. Wong" <djwong@...ibm.com>
To: Andreas Dilger <adilger.kernel@...ger.ca>,
Theodore Tso <tytso@....edu>,
"Darrick J. Wong" <djwong@...ibm.com>
Cc: Sunil Mushran <sunil.mushran@...cle.com>,
Martin K Petersen <martin.petersen@...cle.com>,
Greg Freemyer <greg.freemyer@...il.com>,
Amir Goldstein <amir73il@...il.com>,
linux-kernel <linux-kernel@...r.kernel.org>,
Andi Kleen <andi@...stfloor.org>,
Mingming Cao <cmm@...ibm.com>,
Joel Becker <jlbec@...lplan.org>,
linux-fsdevel <linux-fsdevel@...r.kernel.org>,
linux-ext4@...r.kernel.org, Coly Li <colyli@...il.com>
Subject: [PATCH 02/23] ext4: Change on-disk layout to support extended
metadata checksumming
Define flags and change structure definitions to allow checksumming of ext4
metadata.
Signed-off-by: Darrick J. Wong <djwong@...ibm.com>
---
fs/ext4/ext4.h | 47 +++++++++++++++++++++++++++++++++++++++--------
fs/ext4/ext4_extents.h | 13 +++++++++++++
fs/ext4/namei.c | 8 ++++++++
fs/ext4/xattr.h | 4 +++-
4 files changed, 63 insertions(+), 9 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 513004f..0f0b0d5 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -289,7 +289,9 @@ struct ext4_group_desc
__le16 bg_free_inodes_count_lo;/* Free inodes count */
__le16 bg_used_dirs_count_lo; /* Directories count */
__le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */
- __u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */
+ __le32 bg_exclude_bitmap_lo; /* Exclude bitmap for snapshots */
+ __le16 bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */
+ __le16 bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */
__le16 bg_itable_unused_lo; /* Unused inodes count */
__le16 bg_checksum; /* crc16(sb_uuid+group+desc) */
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
@@ -299,7 +301,10 @@ struct ext4_group_desc
__le16 bg_free_inodes_count_hi;/* Free inodes count MSB */
__le16 bg_used_dirs_count_hi; /* Directories count MSB */
__le16 bg_itable_unused_hi; /* Unused inodes count MSB */
- __u32 bg_reserved2[3];
+ __le32 bg_exclude_bitmap_hi; /* Exclude bitmap block MSB */
+ __le16 bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */
+ __le16 bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */
+ __u32 bg_reserved;
};
/*
@@ -641,7 +646,8 @@ struct ext4_inode {
__le16 l_i_file_acl_high;
__le16 l_i_uid_high; /* these 2 fields */
__le16 l_i_gid_high; /* were reserved2[0] */
- __u32 l_i_reserved2;
+ __le16 l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
+ __le16 l_i_reserved;
} linux2;
struct {
__le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */
@@ -657,7 +663,7 @@ struct ext4_inode {
} masix2;
} osd2; /* OS dependent 2 */
__le16 i_extra_isize;
- __le16 i_pad1;
+ __le16 i_checksum_hi; /* crc32c(uuid+inum+inode) BE */
__le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */
__le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */
__le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */
@@ -759,7 +765,7 @@ do { \
#define i_gid_low i_gid
#define i_uid_high osd2.linux2.l_i_uid_high
#define i_gid_high osd2.linux2.l_i_gid_high
-#define i_reserved2 osd2.linux2.l_i_reserved2
+#define i_checksum_lo osd2.linux2.l_i_checksum_lo
#elif defined(__GNU__)
@@ -992,6 +998,9 @@ extern void ext4_set_bits(void *bm, int cur, int len);
#define EXT4_ERRORS_PANIC 3 /* Panic */
#define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE
+/* Metadata checksum algorithm codes */
+#define EXT4_CRC32C_CHKSUM 1
+
/*
* Structure of the super block
*/
@@ -1078,7 +1087,7 @@ struct ext4_super_block {
__le64 s_mmp_block; /* Block for multi-mount protection */
__le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
__u8 s_log_groups_per_flex; /* FLEX_BG group size */
- __u8 s_reserved_char_pad;
+ __u8 s_checksum_type; /* metadata checksum algorithm used */
__le16 s_reserved_pad;
__le64 s_kbytes_written; /* nr of lifetime kilobytes written */
__le32 s_snapshot_inum; /* Inode number of active snapshot */
@@ -1104,7 +1113,8 @@ struct ext4_super_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 */
+ __le32 s_reserved[108]; /* Padding to the end of the block */
+ __le32 s_checksum; /* crc32c(superblock) */
};
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
@@ -1407,6 +1417,12 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200
+/*
+ * METADATA_CSUM also enables group descriptor checksums (GDT_CSUM). When
+ * METADATA_CSUM is set, group descriptor checksums use the same algorithm as
+ * all other data structures' checksums. However, the METADATA_CSUM and
+ * GDT_CSUM bits are mutually exclusive.
+ */
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400
#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
@@ -1519,6 +1535,18 @@ struct ext4_dir_entry_2 {
};
/*
+ * This is a bogus directory entry at the end of each leaf block that
+ * records checksums.
+ */
+struct ext4_dir_entry_tail {
+ __le32 det_reserved_zero1; /* Pretend to be unused */
+ __le16 det_rec_len; /* 12 */
+ __u8 det_reserved_zero2; /* Zero name length */
+ __u8 det_reserved_ft; /* 0xDE, fake file type */
+ __le32 det_checksum; /* crc32c(uuid+inum+dirblock) */
+};
+
+/*
* Ext4 directory file types. Only the low 3 bits are used. The
* other bits are reserved for now.
*/
@@ -1533,6 +1561,8 @@ struct ext4_dir_entry_2 {
#define EXT4_FT_MAX 8
+#define EXT4_FT_DIR_CSUM 0xDE
+
/*
* EXT4_DIR_PAD defines the directory entries boundaries
*
@@ -1729,7 +1759,8 @@ struct mmp_struct {
__le16 mmp_check_interval;
__le16 mmp_pad1;
- __le32 mmp_pad2[227];
+ __le32 mmp_pad2[226];
+ __le32 mmp_checksum; /* crc32c(uuid+mmp_block) */
};
/* arguments passed to the mmp thread */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index a52db3a..5c7fbade 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -63,9 +63,22 @@
* ext4_inode has i_block array (60 bytes total).
* The first 12 bytes store ext4_extent_header;
* the remainder stores an array of ext4_extent.
+ * For non-inode extent blocks, ext4_extent_tail
+ * follows the array.
*/
/*
+ * This is the extent tail on-disk structure.
+ * All other extent structures are 12 bytes long. It turns out that
+ * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which
+ * covers all valid ext4 block sizes. Therefore, this tail structure can be
+ * crammed into the end of the block without having to rebalance the tree.
+ */
+struct ext4_extent_tail {
+ __le32 et_checksum; /* crc32c(uuid+inum+extent_block) */
+};
+
+/*
* This is the extent on-disk structure.
* It's used at the bottom of the tree.
*/
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2043f48..8b56fdf 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -145,6 +145,14 @@ struct dx_map_entry
u16 size;
};
+/*
+ * This goes at the end of each htree block.
+ */
+struct dx_tail {
+ u32 dt_reserved;
+ __le32 dt_checksum; /* crc32c(uuid+inum+dirblock) */
+};
+
static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
static inline unsigned dx_get_hash(struct dx_entry *entry);
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 25b7387..91f31ca 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -27,7 +27,9 @@ struct ext4_xattr_header {
__le32 h_refcount; /* reference count */
__le32 h_blocks; /* number of disk blocks used */
__le32 h_hash; /* hash value of all attributes */
- __u32 h_reserved[4]; /* zero right now */
+ __le32 h_checksum; /* crc32c(uuid+id+xattrblock) */
+ /* id = inum if refcount=1, blknum otherwise */
+ __u32 h_reserved[3]; /* zero right now */
};
struct ext4_xattr_ibody_header {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists