ext4: Add inode version support in ext4

This patch adds 64-bit inode version support to ext4. The lower 32 bits
are stored in the osd1.linux1.l_i_version field while the high 32 bits
are stored in the i_version_hi field newly created in the ext4_inode.
This field is incremented in case the ext4_inode is large enough. A
i_version mount option has been added to enable the feature.

Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andreas Dilger <adilger@clusterfs.com>
Signed-off-by: Kalpak Shah <kalpak@clusterfs.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Jean Noel Cordenner <jean-noel.cordenner@bull.net>

fs/ext4/inode.c

@@ -2781,6 +2781,13 @@ void ext4_read_inode(struct inode * inode)
 	EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
 	EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
 
+	inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+			inode->i_version |=
+			(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+	}
+
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
@@ -2963,8 +2970,14 @@ static int ext4_do_update_inode(handle_t *handle,
 	} else for (block = 0; block < EXT4_N_BLOCKS; block++)
 		raw_inode->i_block[block] = ei->i_data[block];
 
-	if (ei->i_extra_isize)
+	raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+	if (ei->i_extra_isize) {
+		if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+			raw_inode->i_version_hi =
+			cpu_to_le32(inode->i_version >> 32);
 		raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+	}
+
 
 	BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
 	rc = ext4_journal_dirty_metadata(handle, bh);
@@ -3191,6 +3204,9 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
+	if (test_opt(inode->i_sb, I_VERSION))
+		inode_inc_iversion(inode);
+
 	/* the do_update_inode consumes one bh->b_count */
 	get_bh(iloc->bh);
 

fs/ext4/super.c

@@ -732,6 +732,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",nobh");
 	if (!test_opt(sb, EXTENTS))
 		seq_puts(seq, ",noextents");
+	if (test_opt(sb, I_VERSION))
+		seq_puts(seq, ",i_version");
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
 		seq_puts(seq, ",data=journal");
@@ -874,7 +876,7 @@ enum {
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
-	Opt_grpquota, Opt_extents, Opt_noextents,
+	Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
 };
 
 static match_table_t tokens = {
@@ -928,6 +930,7 @@ static match_table_t tokens = {
 	{Opt_barrier, "barrier=%u"},
 	{Opt_extents, "extents"},
 	{Opt_noextents, "noextents"},
+	{Opt_i_version, "i_version"},
 	{Opt_err, NULL},
 	{Opt_resize, "resize"},
 };
@@ -1273,6 +1276,10 @@ clear_qf_name:
 		case Opt_noextents:
 			clear_opt (sbi->s_mount_opt, EXTENTS);
 			break;
+		case Opt_i_version:
+			set_opt(sbi->s_mount_opt, I_VERSION);
+			sb->s_flags |= MS_I_VERSION;
+			break;
 		default:
 			printk (KERN_ERR
 				"EXT4-fs: Unrecognized mount option \"%s\" "
@@ -3197,7 +3204,6 @@ out:
 		i_size_write(inode, off+len-towrite);
 		EXT4_I(inode)->i_disksize = inode->i_size;
 	}
-	inode->i_version++;
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	ext4_mark_inode_dirty(handle, inode);
 	mutex_unlock(&inode->i_mutex);

fs/inode.c

@@ -1242,23 +1242,6 @@ void touch_atime(struct vfsmount *mnt, struct dentry *dentry)
 }
 EXPORT_SYMBOL(touch_atime);
 
-/**
- *     inode_inc_iversion      -       increments i_version
- *     @inode: inode that need to be updated
- *
- *     Every time the inode is modified, the i_version field
- *     will be incremented.
- *     The filesystem has to be mounted with i_version flag
- *
- */
-
-void inode_inc_iversion(struct inode *inode)
-{
-	spin_lock(&inode->i_lock);
-	inode->i_version++;
-	spin_unlock(&inode->i_lock);
-}
-
 /**
  *	file_update_time	-	update mtime and ctime time
  *	@file: file accessed

include/linux/ext4_fs.h

@@ -292,7 +292,7 @@ struct ext4_inode {
 	__le32	i_flags;	/* File flags */
 	union {
 		struct {
-			__u32  l_i_reserved1;
+			__le32  l_i_version;
 		} linux1;
 		struct {
 			__u32  h_i_translator;
@@ -334,6 +334,7 @@ struct ext4_inode {
 	__le32  i_atime_extra;  /* extra Access time      (nsec << 2 | epoch) */
 	__le32  i_crtime;       /* File Creation time */
 	__le32  i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
+	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
 };
 
 
@@ -407,6 +408,8 @@ do {									       \
 				       raw_inode->xtime ## _extra);	       \
 } while (0)
 
+#define i_disk_version osd1.linux1.l_i_version
+
 #if defined(__KERNEL__) || defined(__linux__)
 #define i_reserved1	osd1.linux1.l_i_reserved1
 #define i_file_acl_high	osd2.linux2.l_i_file_acl_high
@@ -469,6 +472,7 @@ do {									       \
 #define EXT4_MOUNT_EXTENTS		0x400000 /* Extents support */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt

include/linux/fs.h

@@ -1396,7 +1396,21 @@ static inline void inode_dec_link_count(struct inode *inode)
 	mark_inode_dirty(inode);
 }
 
-extern void inode_inc_iversion(struct inode *inode);
+/**
+ * inode_inc_iversion - increments i_version
+ * @inode: inode that need to be updated
+ *
+ * Every time the inode is modified, the i_version field will be incremented.
+ * The filesystem has to be mounted with i_version flag
+ */
+
+static inline void inode_inc_iversion(struct inode *inode)
+{
+       spin_lock(&inode->i_lock);
+       inode->i_version++;
+       spin_unlock(&inode->i_lock);
+}
+
 extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
 static inline void file_accessed(struct file *file)
 {