Hi,
This patch is on top of the nanosecond timestamp and i_version_hi
patches.
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.
We need to make sure that existing filesystems can also avail the new
fields that have been added to the inode. We use s_want_extra_isize and
s_min_extra_isize to decide by how much we should expand the inode. If
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand by
max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question
about whether users should be able to set s_*_extra_isize smaller than
the known fields or not.
This patch also adds the functionality to expand inodes to include the
newly added fields. We start by trying to expand by s_want_extra_isize
bytes and if its fails we try to expand by s_min_extra_isize bytes. This
is done by changing the i_extra_isize if enough space is available in
the inode and no EAs are present. If EAs are present and there is enough
space in the inode then the EAs in the inode are shifted to make space.
If enough space is not available in the inode due to the EAs then 1 or
more EAs are shifted to the external EA block. In the worst case when
even the external EA block does not have enough space we inform the user
that some EA would need to be deleted or s_min_extra_isize would have to
be reduced.
This would be online expansion of inodes. I am also working on adding an
"expand_inodes" option to e2fsck which will expand all the used inodes.
Signed-off-by: Andreas Dilger <adilger@xxxxxxxxxxxxx>
Signed-off-by: Kalpak Shah <kalpak@xxxxxxxxxxxxx>
Index: linux-2.6.20/fs/ext4/inode.c
===================================================================
--- linux-2.6.20.orig/fs/ext4/inode.c
+++ linux-2.6.20/fs/ext4/inode.c
@@ -2756,6 +2756,13 @@ void ext4_read_inode(struct inode * inod
EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
+ ei->i_fs_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))
+ ei->i_fs_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;
@@ -2898,8 +2905,14 @@ static int ext4_do_update_inode(handle_t
} 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(ei->i_fs_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(ei->i_fs_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);
@@ -3173,10 +3186,32 @@ ext4_reserve_inode_write(handle_t *handl
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
{
struct ext4_iloc iloc;
- int err;
+ int err, ret;
+ static int expand_message;
might_sleep();
err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (EXT4_I(inode)->i_extra_isize <
+ EXT4_SB(inode->i_sb)->s_want_extra_isize &&
+ !(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
+ /* We need extra buffer credits since we may write into EA block
+ * with this same handle */
+ if ((jbd2_journal_extend(handle,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) {
+ ret = ext4_expand_extra_isize(inode,
+ EXT4_SB(inode->i_sb)->s_want_extra_isize,
+ iloc, handle);
+ if (ret) {
+ EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+ if (!expand_message) {
+ ext4_warning(inode->i_sb, __FUNCTION__,
+ "Unable to expand inode %lu. Delete some"
+ " EAs or run e2fsck.", inode->i_ino);
+ expand_message = 1;
+ }
+ }
+ }
+ }
if (!err)
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
return err;
Index: linux-2.6.20/include/linux/ext4_fs.h
===================================================================
--- linux-2.6.20.orig/include/linux/ext4_fs.h
+++ linux-2.6.20/include/linux/ext4_fs.h
@@ -201,6 +201,7 @@ struct ext4_group_desc
#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */
#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */
#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
+#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
@@ -291,7 +292,7 @@ struct ext4_inode {
__le32 i_flags; /* File flags */
union {
struct {
- __u32 l_i_reserved1;
+ __u32 l_i_version;
} linux1;
struct {
__u32 h_i_translator;
@@ -399,6 +400,8 @@ 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_frag osd2.linux2.l_i_frag
Index: linux-2.6.20/include/linux/ext4_fs_i.h
===================================================================
--- linux-2.6.20.orig/include/linux/ext4_fs_i.h
+++ linux-2.6.20/include/linux/ext4_fs_i.h
@@ -154,6 +154,7 @@ struct ext4_inode_info {
unsigned long i_ext_generation;
struct ext4_ext_cache i_cached_extent;
struct timespec i_crtime;
+ __u64 i_fs_version;
};
#endif /* _LINUX_EXT4_FS_I */
Index: linux-2.6.20/fs/ext4/xattr.c
===================================================================
--- linux-2.6.20.orig/fs/ext4/xattr.c
+++ linux-2.6.20/fs/ext4/xattr.c
@@ -502,6 +502,20 @@ ext4_xattr_release_block(handle_t *handl
}
}
+static inline size_t ext3_xattr_free_space(struct ext4_xattr_entry *last,
+ size_t *min_offs, void *base, int *total)
+{
+ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ *total += EXT4_XATTR_LEN(last->e_name_len);
+ if (!last->e_value_block && last->e_value_size) {
+ size_t offs = le16_to_cpu(last->e_value_offs);
+ if (offs < *min_offs)
+ *min_offs = offs;
+ }
+ }
+ return (*min_offs - ((void *)last - base) - sizeof(__u32));
+}
+
struct ext4_xattr_info {
int name_index;
const char *name;
@@ -600,6 +614,7 @@ ext4_xattr_set_entry(struct ext4_xattr_i
memmove(s->here, (void *)s->here + size,
(void *)last - (void *)s->here + sizeof(__u32));
memset(last, 0, size);
+
}
}
@@ -1005,6 +1020,8 @@ ext4_xattr_set_handle(handle_t *handle,
if (!error) {
ext4_xattr_update_super_block(handle, inode->i_sb);
inode->i_ctime = ext4_current_time(inode);
+ if(!value)
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
/*
* The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1057,6 +1074,251 @@ retry:
return error;
}
+static void ext3_xattr_shift_entries(struct ext4_xattr_entry *entry,
+ int value_offs_shift, void *to,
+ void *from, size_t n, int blocksize)
+{
+ struct ext4_xattr_entry *last = entry;
+ int new_offs;
+
+ /* Adjust the value offsets of the entries */
+ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ if (!last->e_value_block && last->e_value_size) {
+ new_offs = le16_to_cpu(last->e_value_offs) +
+ value_offs_shift;
+ BUG_ON(new_offs + le32_to_cpu(last->e_value_size) > blocksize);
+ last->e_value_offs = cpu_to_le16(new_offs);
+ }
+ }
+ /* Shift the entries by n bytes */
+ memmove(to, from, n);
+}
+
+/* Expand an inode by new_extra_isize bytes.
+ * Returns 0 on success or negative error number on failure.
+ */
+int ext4_expand_extra_isize(struct inode *inode, int new_extra_isize,
+ struct ext4_iloc iloc, handle_t *handle)
+{
+ struct ext4_inode *raw_inode;
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_entry *entry, *last, *first;
+ struct buffer_head *bh = NULL;
+ struct ext4_xattr_ibody_find *is = NULL;
+ struct ext4_xattr_block_find *bs = NULL;
+ char *buffer = NULL, *b_entry_name = NULL;
+ size_t min_offs, free;
+ int total_ino, total_blk;
+ void *base, *start, *end;
+ int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+ int s_min_extra_isize = EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize;
+
+ down_write(&EXT4_I(inode)->xattr_sem);
+
+retry:
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
+ up_write(&EXT4_I(inode)->xattr_sem);
+ return 0;
+ }
+
+ raw_inode = ext4_raw_inode(&iloc);
+
+ header = IHDR(inode, raw_inode);
+ entry = IFIRST(header);
+
+ /* No extended attributes present */
+ if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR) ||
+ header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
+ new_extra_isize);
+ EXT4_I(inode)->i_extra_isize = new_extra_isize;
+ goto cleanup;
+ }
+
+ /*
+ * Check if enough free space is available in the inode to shift the
+ * entries ahead by new_extra_isize.
+ */
+
+ base = start = entry;
+ end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+ min_offs = end - base;
+ last = entry;
+ total_ino = sizeof(struct ext4_xattr_ibody_header);
+
+ free = ext3_xattr_free_space(last, &min_offs, base, &total_ino);
+ if (free >= new_extra_isize) {
+ entry = IFIRST(header);
+ ext3_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize
+ - new_extra_isize, (void *)raw_inode +
+ EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
+ (void *)header, total_ino,
+ inode->i_sb->s_blocksize);
+ EXT4_I(inode)->i_extra_isize = new_extra_isize;
+ error = 0;
+ goto cleanup;
+ }
+
+ /*
+ * Enough free space isn't available in the inode, check if
+ * EA block can hold new_extra_isize bytes.
+ */
+ if (EXT4_I(inode)->i_file_acl) {
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ if (!bh)
+ goto cleanup;
+ if (ext4_xattr_check_block(bh)) {
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: bad block %llu", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ goto cleanup;
+ }
+ base = BHDR(bh);
+ first = BFIRST(bh);
+ end = bh->b_data + bh->b_size;
+ min_offs = end - base;
+ free = ext3_xattr_free_space(first, &min_offs, base,
+ &total_blk);
+ if (free < new_extra_isize) {
+ if (!tried_min_extra_isize && s_min_extra_isize) {
+ tried_min_extra_isize++;
+ new_extra_isize = s_min_extra_isize;
+ goto retry;
+ }
+ error = -1;
+ goto cleanup;
+ }
+ }
+ else {
+ free = inode->i_sb->s_blocksize;
+ }
+
+ while (new_extra_isize > 0) {
+ size_t offs, size, entry_size;
+ struct ext4_xattr_entry *small_entry = NULL;
+ struct ext4_xattr_info i = {
+ .value = NULL,
+ .value_len = 0,
+ };
+ unsigned int total_size, shift_bytes, temp = ~0U;
+
+ is = (struct ext4_xattr_ibody_find *) kmalloc(sizeof(struct
+ ext4_xattr_ibody_find), GFP_KERNEL);
+ bs = (struct ext4_xattr_block_find *) kmalloc(sizeof(struct
+ ext4_xattr_block_find), GFP_KERNEL);
+ memset((void *)is, 0, sizeof(struct ext4_xattr_ibody_find));
+ memset((void *)bs, 0, sizeof(struct ext4_xattr_block_find));
+
+ is->s.not_found = bs->s.not_found = -ENODATA;
+ is->iloc.bh = NULL;
+ bs->bh = NULL;
+
+ last = IFIRST(header);
+ /* Find the entry best suited to be pushed into EA block */
+ entry = NULL;
+ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ total_size = EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
+ EXT4_XATTR_LEN(last->e_name_len);
+ if (total_size <= free && total_size < temp) {
+ if (total_size < new_extra_isize) {
+ small_entry = last;
+ }
+ else {
+ entry = last;
+ temp = total_size;
+ }
+ }
+ }
+
+ if (entry == NULL) {
+ if (small_entry) {
+ entry = small_entry;
+ }
+ else {
+ if (!tried_min_extra_isize &&
+ s_min_extra_isize) {
+ tried_min_extra_isize++;
+ new_extra_isize = s_min_extra_isize;
+ goto retry;
+ }
+ error = -1;
+ goto cleanup;
+ }
+ }
+ offs = le16_to_cpu(entry->e_value_offs);
+ size = le32_to_cpu(entry->e_value_size);
+ entry_size = EXT4_XATTR_LEN(entry->e_name_len);
+ i.name_index = entry->e_name_index,
+ buffer = kmalloc(EXT4_XATTR_SIZE(size), GFP_KERNEL);
+ b_entry_name = kmalloc(entry->e_name_len + 1, GFP_KERNEL);
+ /* Save the entry name and the entry value */
+ memcpy((void *)buffer, (void *)IFIRST(header) + offs,
+ EXT4_XATTR_SIZE(size));
+ memcpy((void *)b_entry_name, (void *)entry->e_name,
+ entry->e_name_len);
+ b_entry_name[entry->e_name_len] = '\0';
+ i.name = b_entry_name;
+
+ error = ext4_get_inode_loc(inode, &is->iloc);
+ if (error)
+ goto cleanup;
+
+ error = ext4_xattr_ibody_find(inode, &i, is);
+ if (error)
+ goto cleanup;
+
+ /* Remove the chosen entry from the inode */
+ error = ext4_xattr_ibody_set(handle, inode, &i, is);
+
+ entry = IFIRST(header);
+ if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
+ shift_bytes = new_extra_isize;
+ else
+ shift_bytes = entry_size + size;
+ /* Adjust the offsets and shift the remaining entries ahead */
+ ext3_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
+ shift_bytes, (void *)raw_inode +
+ EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
+ (void *)header, total_ino - entry_size,
+ inode->i_sb->s_blocksize);
+
+ extra_isize += shift_bytes;
+ new_extra_isize -= shift_bytes;
+ EXT4_I(inode)->i_extra_isize = extra_isize;
+
+ i.name = b_entry_name;
+ i.value = buffer;
+ i.value_len = cpu_to_le32(size);
+ error = ext4_xattr_block_find(inode, &i, bs);
+ if (error)
+ goto cleanup;
+
+ /* Add entry which was removed from the inode into the block */
+ error = ext4_xattr_block_set(handle, inode, &i, bs);
+ if (error)
+ goto cleanup;
+ }
+
+cleanup:
+ if (b_entry_name)
+ kfree(b_entry_name);
+ if (buffer)
+ kfree(buffer);
+ if (is) {
+ brelse(is->iloc.bh);
+ kfree(is);
+ }
+ if (bs)
+ kfree(bs);
+ brelse(bh);
+ up_write(&EXT4_I(inode)->xattr_sem);
+ return error;
+}
+
+
+
/*
* ext4_xattr_delete_inode()
*
Index: linux-2.6.20/fs/ext4/xattr.h
===================================================================
--- linux-2.6.20.orig/fs/ext4/xattr.h
+++ linux-2.6.20/fs/ext4/xattr.h
@@ -74,6 +74,9 @@ extern int ext4_xattr_set_handle(handle_
extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
extern void ext4_xattr_put_super(struct super_block *);
+int ext4_expand_extra_isize(struct inode *inode, int new_extra_isize,
+ struct ext4_iloc iloc, handle_t *handle);
+
extern int init_ext4_xattr(void);
extern void exit_ext4_xattr(void);
Thanks,
Kalpak Shah.
-
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
