/* somewhat more expensive than our other checks, so use sparingly. */
static int ocfs2_check_group_descriptor(struct super_block *sb,
struct ocfs2_dinode *di,
struct ocfs2_group_desc *gd)
{
unsigned int max_bits;
if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(sb, gd);
return -EIO;
}
if (di->i_blkno != gd->bg_parent_dinode) {
ocfs2_error(sb, "Group descriptor # %llu has bad parent "
"pointer (%llu, expected %llu)",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
(unsigned long long)le64_to_cpu(gd->bg_parent_dinode),
(unsigned long long)le64_to_cpu(di->i_blkno));
return -EIO;
}
max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
if (le16_to_cpu(gd->bg_bits) > max_bits) {
ocfs2_error(sb, "Group descriptor # %llu has bit count of %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits));
return -EIO;
}
if (le16_to_cpu(gd->bg_chain) >=
le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) {
ocfs2_error(sb, "Group descriptor # %llu has bad chain %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_chain));
return -EIO;
}
if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) {
ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
"claims that %u are free",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
le16_to_cpu(gd->bg_free_bits_count));
return -EIO;
}
if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) {
ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
"max bitmap bits of %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
8 * le16_to_cpu(gd->bg_size));
return -EIO;
}
return 0;
}
static int ocfs2_block_group_fill(handle_t *handle,
struct inode *alloc_inode,
struct buffer_head *bg_bh,
u64 group_blkno,
u16 my_chain,
struct ocfs2_chain_list *cl)
{
int status = 0;
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
struct super_block * sb = alloc_inode->i_sb;
mlog_entry_void();
if (((unsigned long long) bg_bh->b_blocknr) != group_blkno) {
ocfs2_error(alloc_inode->i_sb, "group block (%llu) != "
"b_blocknr (%llu)",
(unsigned long long)group_blkno,
(unsigned long long) bg_bh->b_blocknr);
status = -EIO;
goto bail;
}
status = ocfs2_journal_access(handle,
alloc_inode,
bg_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (status < 0) {
mlog_errno(status);
goto bail;
}
memset(bg, 0, sb->s_blocksize);
strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE);
bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb));
bg->bg_bits = cpu_to_le16(ocfs2_bits_per_group(cl));
bg->bg_chain = cpu_to_le16(my_chain);
bg->bg_next_group = cl->cl_recs[my_chain].c_blkno;
bg->bg_parent_dinode = cpu_to_le64(OCFS2_I(alloc_inode)->ip_blkno);
bg->bg_blkno = cpu_to_le64(group_blkno);
/* set the 1st bit in the bitmap to account for the descriptor block */
ocfs2_set_bit(0, (unsigned long *)bg->bg_bitmap);
bg->bg_free_bits_count = cpu_to_le16(le16_to_cpu(bg->bg_bits) - 1);
status = ocfs2_journal_dirty(handle, bg_bh);
if (status < 0)
mlog_errno(status);
/* There is no need to zero out or otherwise initialize the
* other blocks in a group - All valid FS metadata in a block
* group stores the superblock fs_generation value at
* allocation time. */
bail:
mlog_exit(status);
return status;
}
int ocfs2_read_inline_data(struct inode *inode, struct page *page,
struct buffer_head *di_bh)
{
void *kaddr;
loff_t size;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
return -EROFS;
}
size = i_size_read(inode);
if (size > PAGE_CACHE_SIZE ||
size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
ocfs2_error(inode->i_sb,
"Inode %llu has with inline data has bad size: %Lu",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)size);
return -EROFS;
}
kaddr = kmap_atomic(page, KM_USER0);
if (size)
memcpy(kaddr, di->id2.i_data.id_data, size);
/* Clear the remaining part of the page */
memset(kaddr + size, 0, PAGE_CACHE_SIZE - size);
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
SetPageUptodate(page);
return 0;
}
static inline int ocfs2_block_group_set_bits(handle_t *handle,
struct inode *alloc_inode,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
unsigned int num_bits)
{
int status;
void *bitmap = bg->bg_bitmap;
int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
/* All callers get the descriptor via
* ocfs2_read_group_descriptor(). Any corruption is a code bug. */
BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
num_bits);
if (ocfs2_is_cluster_bitmap(alloc_inode))
journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
status = ocfs2_journal_access_gd(handle,
INODE_CACHE(alloc_inode),
group_bh,
journal_type);
if (status < 0) {
mlog_errno(status);
goto bail;
}
le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
" count %u but claims %u are freed. num_bits %d",
(unsigned long long)le64_to_cpu(bg->bg_blkno),
le16_to_cpu(bg->bg_bits),
le16_to_cpu(bg->bg_free_bits_count), num_bits);
return -EROFS;
}
while (num_bits--)
ocfs2_set_bit(bit_off++, bitmap);
ocfs2_journal_dirty(handle, group_bh);
bail:
return status;
}
/*
* make sure we've got at least bits_wanted contiguous bits in the
* local alloc. You lose them when you drop i_mutex.
*
* We will add ourselves to the transaction passed in, but may start
* our own in order to shift windows.
*/
int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
u32 bits_wanted,
struct ocfs2_alloc_context *ac)
{
int status;
struct ocfs2_dinode *alloc;
struct inode *local_alloc_inode;
unsigned int free_bits;
BUG_ON(!ac);
local_alloc_inode =
ocfs2_get_system_file_inode(osb,
LOCAL_ALLOC_SYSTEM_INODE,
osb->slot_num);
if (!local_alloc_inode) {
status = -ENOENT;
mlog_errno(status);
goto bail;
}
inode_lock(local_alloc_inode);
/*
* We must double check state and allocator bits because
* another process may have changed them while holding i_mutex.
*/
spin_lock(&osb->osb_lock);
if (!ocfs2_la_state_enabled(osb) ||
(bits_wanted > osb->local_alloc_bits)) {
spin_unlock(&osb->osb_lock);
status = -ENOSPC;
goto bail;
}
spin_unlock(&osb->osb_lock);
alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
#ifdef CONFIG_OCFS2_DEBUG_FS
if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
ocfs2_local_alloc_count_bits(alloc)) {
ocfs2_error(osb->sb, "local alloc inode %llu says it has %u used bits, but a count shows %u\n",
(unsigned long long)le64_to_cpu(alloc->i_blkno),
le32_to_cpu(alloc->id1.bitmap1.i_used),
ocfs2_local_alloc_count_bits(alloc));
status = -EIO;
goto bail;
}
#endif
free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) -
le32_to_cpu(alloc->id1.bitmap1.i_used);
if (bits_wanted > free_bits) {
/* uhoh, window change time. */
status =
ocfs2_local_alloc_slide_window(osb, local_alloc_inode);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
/*
* Under certain conditions, the window slide code
* might have reduced the number of bits available or
* disabled the the local alloc entirely. Re-check
* here and return -ENOSPC if necessary.
*/
status = -ENOSPC;
if (!ocfs2_la_state_enabled(osb))
goto bail;
free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) -
le32_to_cpu(alloc->id1.bitmap1.i_used);
if (bits_wanted > free_bits)
goto bail;
}
ac->ac_inode = local_alloc_inode;
/* We should never use localalloc from another slot */
ac->ac_alloc_slot = osb->slot_num;
ac->ac_which = OCFS2_AC_USE_LOCAL;
get_bh(osb->local_alloc_bh);
ac->ac_bh = osb->local_alloc_bh;
status = 0;
bail:
if (status < 0 && local_alloc_inode) {
inode_unlock(local_alloc_inode);
iput(local_alloc_inode);
}
trace_ocfs2_reserve_local_alloc_bits(
(unsigned long long)ac->ac_max_block,
bits_wanted, osb->slot_num, status);
if (status)
mlog_errno(status);
return status;
}
int ocfs2_validate_inode_block(struct super_block *sb,
struct buffer_head *bh)
{
int rc;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
trace_ocfs2_validate_inode_block((unsigned long long)bh->b_blocknr);
BUG_ON(!buffer_uptodate(bh));
/*
* If the ecc fails, we return the error but otherwise
* leave the filesystem running. We know any error is
* local to this block.
*/
rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
if (rc) {
mlog(ML_ERROR, "Checksum failed for dinode %llu\n",
(unsigned long long)bh->b_blocknr);
goto bail;
}
/*
* Errors after here are fatal.
*/
rc = -EINVAL;
if (!OCFS2_IS_VALID_DINODE(di)) {
ocfs2_error(sb, "Invalid dinode #%llu: signature = %.*s\n",
(unsigned long long)bh->b_blocknr, 7,
di->i_signature);
goto bail;
}
if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
ocfs2_error(sb, "Invalid dinode #%llu: i_blkno is %llu\n",
(unsigned long long)bh->b_blocknr,
(unsigned long long)le64_to_cpu(di->i_blkno));
goto bail;
}
if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
ocfs2_error(sb,
"Invalid dinode #%llu: OCFS2_VALID_FL not set\n",
(unsigned long long)bh->b_blocknr);
goto bail;
}
if (le32_to_cpu(di->i_fs_generation) !=
OCFS2_SB(sb)->fs_generation) {
ocfs2_error(sb,
"Invalid dinode #%llu: fs_generation is %u\n",
(unsigned long long)bh->b_blocknr,
le32_to_cpu(di->i_fs_generation));
goto bail;
}
rc = 0;
bail:
return rc;
}
/*
* TODO: Make this into a generic get_blocks function.
*
* From do_direct_io in direct-io.c:
* "So what we do is to permit the ->get_blocks function to populate
* bh.b_size with the size of IO which is permitted at this offset and
* this i_blkbits."
*
* This function is called directly from get_more_blocks in direct-io.c.
*
* called like this: dio->get_blocks(dio->inode, fs_startblk,
* fs_count, map_bh, dio->rw == WRITE);
*/
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
u64 p_blkno, inode_blocks, contig_blocks;
unsigned int ext_flags;
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
/* This function won't even be called if the request isn't all
* nicely aligned and of the right size, so there's no need
* for us to check any of that. */
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
/*
* Any write past EOF is not allowed because we'd be extending.
*/
if (create && (iblock + max_blocks) > inode_blocks) {
ret = -EIO;
goto bail;
}
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)) && !p_blkno && create) {
ocfs2_error(inode->i_sb,
"Inode %llu has a hole at block %llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)iblock);
ret = -EROFS;
goto bail;
}
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
*
* Consider an unwritten extent as a hole.
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
else {
/*
* ocfs2_prepare_inode_for_write() should have caught
* the case where we'd be filling a hole and triggered
* a buffered write instead.
*/
if (create) {
ret = -EIO;
mlog_errno(ret);
goto bail;
}
clear_buffer_mapped(bh_result);
}
/* make sure we don't map more than max_blocks blocks here as
that's all the kernel will handle at this point. */
if (max_blocks < contig_blocks)
contig_blocks = max_blocks;
bh_result->b_size = contig_blocks << blocksize_bits;
bail:
return ret;
}
static int ocfs2_extent_map_insert(struct inode *inode,
struct ocfs2_extent_rec *rec,
int tree_depth)
{
int ret;
struct ocfs2_em_insert_context ctxt = {0, };
if ((le32_to_cpu(rec->e_cpos) + le32_to_cpu(rec->e_clusters)) >
OCFS2_I(inode)->ip_map.em_clusters) {
ret = -EBADR;
mlog_errno(ret);
return ret;
}
/* Zero e_clusters means a truncated tail record. It better be EOF */
if (!rec->e_clusters) {
if ((le32_to_cpu(rec->e_cpos) + le32_to_cpu(rec->e_clusters)) !=
OCFS2_I(inode)->ip_map.em_clusters) {
ret = -EBADR;
mlog_errno(ret);
ocfs2_error(inode->i_sb,
"Zero e_clusters on non-tail extent record at e_blkno %llu on inode %llu\n",
(unsigned long long)le64_to_cpu(rec->e_blkno),
(unsigned long long)OCFS2_I(inode)->ip_blkno);
return ret;
}
/* Ignore the truncated tail */
return 0;
}
ret = -ENOMEM;
ctxt.new_ent = kmem_cache_alloc(ocfs2_em_ent_cachep,
GFP_NOFS);
if (!ctxt.new_ent) {
mlog_errno(ret);
return ret;
}
ctxt.new_ent->e_rec = *rec;
ctxt.new_ent->e_tree_depth = tree_depth;
do {
ret = -ENOMEM;
if (ctxt.need_left && !ctxt.left_ent) {
ctxt.left_ent =
kmem_cache_alloc(ocfs2_em_ent_cachep,
GFP_NOFS);
if (!ctxt.left_ent)
break;
}
if (ctxt.need_right && !ctxt.right_ent) {
ctxt.right_ent =
kmem_cache_alloc(ocfs2_em_ent_cachep,
GFP_NOFS);
if (!ctxt.right_ent)
break;
}
ret = ocfs2_extent_map_try_insert(inode, rec,
tree_depth, &ctxt);
} while (ret == -EAGAIN);
if ((ret < 0) && (ret != -EEXIST))
mlog_errno(ret);
if (ctxt.left_ent)
kmem_cache_free(ocfs2_em_ent_cachep, ctxt.left_ent);
if (ctxt.right_ent)
kmem_cache_free(ocfs2_em_ent_cachep, ctxt.right_ent);
if (ctxt.old_ent)
kmem_cache_free(ocfs2_em_ent_cachep, ctxt.old_ent);
if (ctxt.new_ent)
kmem_cache_free(ocfs2_em_ent_cachep, ctxt.new_ent);
return ret;
}
/*
* Find the leaf containing the interval we want. While we're on our
* way down the tree, fill in every record we see at any depth, because
* we might want it later.
*
* Note that this code is run without ip_lock. That's because it
* sleeps while reading. If someone is also filling the extent list at
* the same time we are, we might have to restart.
*/
static int ocfs2_extent_map_find_leaf(struct inode *inode,
u32 cpos, u32 clusters,
struct ocfs2_extent_list *el)
{
int i, ret;
struct buffer_head *eb_bh = NULL;
u64 blkno;
u32 rec_end;
struct ocfs2_extent_block *eb;
struct ocfs2_extent_rec *rec;
/*
* The bh data containing the el cannot change here, because
* we hold alloc_sem. So we can do this without other
* locks.
*/
while (el->l_tree_depth)
{
blkno = 0;
for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) {
rec = &el->l_recs[i];
rec_end = (le32_to_cpu(rec->e_cpos) +
le32_to_cpu(rec->e_clusters));
ret = -EBADR;
if (rec_end > OCFS2_I(inode)->ip_clusters) {
mlog_errno(ret);
ocfs2_error(inode->i_sb,
"Extent %d at e_blkno %llu of inode %llu goes past ip_clusters of %u\n",
i,
(unsigned long long)le64_to_cpu(rec->e_blkno),
(unsigned long long)OCFS2_I(inode)->ip_blkno,
OCFS2_I(inode)->ip_clusters);
goto out_free;
}
if (rec_end <= cpos) {
ret = ocfs2_extent_map_insert(inode, rec,
le16_to_cpu(el->l_tree_depth));
if (ret && (ret != -EEXIST)) {
mlog_errno(ret);
goto out_free;
}
continue;
}
if ((cpos + clusters) <= le32_to_cpu(rec->e_cpos)) {
ret = ocfs2_extent_map_insert(inode, rec,
le16_to_cpu(el->l_tree_depth));
if (ret && (ret != -EEXIST)) {
mlog_errno(ret);
goto out_free;
}
continue;
}
/*
* We've found a record that matches our
* interval. We don't insert it because we're
* about to traverse it.
*/
/* Check to see if we're stradling */
ret = -ESRCH;
if (!ocfs2_extent_rec_contains_clusters(rec,
cpos,
clusters)) {
mlog_errno(ret);
goto out_free;
}
/*
* If we've already found a record, the el has
* two records covering the same interval.
* EEEK!
*/
ret = -EBADR;
if (blkno) {
mlog_errno(ret);
ocfs2_error(inode->i_sb,
"Multiple extents for (cpos = %u, clusters = %u) on inode %llu; e_blkno %llu and rec %d at e_blkno %llu\n",
cpos, clusters,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)blkno, i,
(unsigned long long)le64_to_cpu(rec->e_blkno));
goto out_free;
}
blkno = le64_to_cpu(rec->e_blkno);
}
/*
* We don't support holes, and we're still up
* in the branches, so we'd better have found someone
*/
ret = -EBADR;
if (!blkno) {
ocfs2_error(inode->i_sb,
"No record found for (cpos = %u, clusters = %u) on inode %llu\n",
cpos, clusters,
(unsigned long long)OCFS2_I(inode)->ip_blkno);
mlog_errno(ret);
goto out_free;
}
if (eb_bh) {
brelse(eb_bh);
eb_bh = NULL;
}
ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
blkno, &eb_bh, OCFS2_BH_CACHED,
inode);
if (ret) {
mlog_errno(ret);
goto out_free;
}
eb = (struct ocfs2_extent_block *)eb_bh->b_data;
if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) {
OCFS2_RO_ON_INVALID_EXTENT_BLOCK(inode->i_sb, eb);
ret = -EIO;
goto out_free;
}
el = &eb->h_list;
}
BUG_ON(el->l_tree_depth);
for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) {
rec = &el->l_recs[i];
if ((le32_to_cpu(rec->e_cpos) + le32_to_cpu(rec->e_clusters)) >
OCFS2_I(inode)->ip_clusters) {
ret = -EBADR;
mlog_errno(ret);
ocfs2_error(inode->i_sb,
"Extent %d at e_blkno %llu of inode %llu goes past ip_clusters of %u\n",
i,
(unsigned long long)le64_to_cpu(rec->e_blkno),
(unsigned long long)OCFS2_I(inode)->ip_blkno,
OCFS2_I(inode)->ip_clusters);
return ret;
}
ret = ocfs2_extent_map_insert(inode, rec,
le16_to_cpu(el->l_tree_depth));
if (ret && (ret != -EEXIST)) {
mlog_errno(ret);
goto out_free;
}
}
ret = 0;
out_free:
if (eb_bh)
brelse(eb_bh);
return ret;
}
static int __ocfs2_move_extent(handle_t *handle,
struct ocfs2_move_extents_context *context,
u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
int ext_flags)
{
int ret = 0, index;
struct inode *inode = context->inode;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_extent_rec *rec, replace_rec;
struct ocfs2_path *path = NULL;
struct ocfs2_extent_list *el;
u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos,
p_cpos, new_p_cpos, len);
if (ret) {
mlog_errno(ret);
goto out;
}
memset(&replace_rec, 0, sizeof(replace_rec));
replace_rec.e_cpos = cpu_to_le32(cpos);
replace_rec.e_leaf_clusters = cpu_to_le16(len);
replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
new_p_cpos));
path = ocfs2_new_path_from_et(&context->et);
if (!path) {
ret = -ENOMEM;
mlog_errno(ret);
goto out;
}
ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
if (ret) {
mlog_errno(ret);
goto out;
}
el = path_leaf_el(path);
index = ocfs2_search_extent_list(el, cpos);
if (index == -1) {
ret = ocfs2_error(inode->i_sb,
"Inode %llu has an extent at cpos %u which can no longer be found\n",
(unsigned long long)ino, cpos);
goto out;
}
rec = &el->l_recs[index];
BUG_ON(ext_flags != rec->e_flags);
/*
* after moving/defraging to new location, the extent is not going
* to be refcounted anymore.
*/
replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
context->et.et_root_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_split_extent(handle, &context->et, path, index,
&replace_rec, context->meta_ac,
&context->dealloc);
if (ret) {
mlog_errno(ret);
goto out;
}
ocfs2_journal_dirty(handle, context->et.et_root_bh);
context->new_phys_cpos = new_p_cpos;
/*
* need I to append truncate log for old clusters?
*/
if (old_blkno) {
if (ext_flags & OCFS2_EXT_REFCOUNTED)
ret = ocfs2_decrease_refcount(inode, handle,
ocfs2_blocks_to_clusters(osb->sb,
old_blkno),
len, context->meta_ac,
&context->dealloc, 1);
else
ret = ocfs2_truncate_log_append(osb, handle,
old_blkno, len);
}
ocfs2_update_inode_fsync_trans(handle, inode, 0);
out:
ocfs2_free_path(path);
return ret;
}
int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
u32 bits_wanted,
struct ocfs2_alloc_context *ac)
{
int status;
struct ocfs2_dinode *alloc;
struct inode *local_alloc_inode;
unsigned int free_bits;
BUG_ON(!ac);
local_alloc_inode =
ocfs2_get_system_file_inode(osb,
LOCAL_ALLOC_SYSTEM_INODE,
osb->slot_num);
if (!local_alloc_inode) {
status = -ENOENT;
mlog_errno(status);
goto bail;
}
mutex_lock(&local_alloc_inode->i_mutex);
/*
*/
spin_lock(&osb->osb_lock);
if (!ocfs2_la_state_enabled(osb) ||
(bits_wanted > osb->local_alloc_bits)) {
spin_unlock(&osb->osb_lock);
status = -ENOSPC;
goto bail;
}
spin_unlock(&osb->osb_lock);
alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
#ifdef CONFIG_OCFS2_DEBUG_FS
if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
ocfs2_local_alloc_count_bits(alloc)) {
ocfs2_error(osb->sb, "local alloc inode %llu says it has "
"%u free bits, but a count shows %u",
(unsigned long long)le64_to_cpu(alloc->i_blkno),
le32_to_cpu(alloc->id1.bitmap1.i_used),
ocfs2_local_alloc_count_bits(alloc));
status = -EIO;
goto bail;
}
#endif
free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) -
le32_to_cpu(alloc->id1.bitmap1.i_used);
if (bits_wanted > free_bits) {
/* */
status =
ocfs2_local_alloc_slide_window(osb, local_alloc_inode);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
/*
*/
status = -ENOSPC;
if (!ocfs2_la_state_enabled(osb))
goto bail;
free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) -
le32_to_cpu(alloc->id1.bitmap1.i_used);
if (bits_wanted > free_bits)
goto bail;
}
ac->ac_inode = local_alloc_inode;
/* */
ac->ac_alloc_slot = osb->slot_num;
ac->ac_which = OCFS2_AC_USE_LOCAL;
get_bh(osb->local_alloc_bh);
ac->ac_bh = osb->local_alloc_bh;
status = 0;
bail:
if (status < 0 && local_alloc_inode) {
mutex_unlock(&local_alloc_inode->i_mutex);
iput(local_alloc_inode);
}
trace_ocfs2_reserve_local_alloc_bits(
(unsigned long long)ac->ac_max_block,
bits_wanted, osb->slot_num, status);
if (status)
mlog_errno(status);
return status;
}
static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac,
int type,
u32 slot)
{
int status;
u32 bits_wanted = ac->ac_bits_wanted;
struct inode *alloc_inode;
struct buffer_head *bh = NULL;
struct ocfs2_dinode *fe;
u32 free_bits;
mlog_entry_void();
alloc_inode = ocfs2_get_system_file_inode(osb, type, slot);
if (!alloc_inode) {
mlog_errno(-EINVAL);
return -EINVAL;
}
mutex_lock(&alloc_inode->i_mutex);
status = ocfs2_meta_lock(alloc_inode, &bh, 1);
if (status < 0) {
mutex_unlock(&alloc_inode->i_mutex);
iput(alloc_inode);
mlog_errno(status);
return status;
}
ac->ac_inode = alloc_inode;
fe = (struct ocfs2_dinode *) bh->b_data;
if (!OCFS2_IS_VALID_DINODE(fe)) {
OCFS2_RO_ON_INVALID_DINODE(alloc_inode->i_sb, fe);
status = -EIO;
goto bail;
}
if (!(fe->i_flags & cpu_to_le32(OCFS2_CHAIN_FL))) {
ocfs2_error(alloc_inode->i_sb, "Invalid chain allocator %llu",
(unsigned long long)le64_to_cpu(fe->i_blkno));
status = -EIO;
goto bail;
}
free_bits = le32_to_cpu(fe->id1.bitmap1.i_total) -
le32_to_cpu(fe->id1.bitmap1.i_used);
if (bits_wanted > free_bits) {
/* cluster bitmap never grows */
if (ocfs2_is_cluster_bitmap(alloc_inode)) {
mlog(0, "Disk Full: wanted=%u, free_bits=%u\n",
bits_wanted, free_bits);
status = -ENOSPC;
goto bail;
}
status = ocfs2_block_group_alloc(osb, alloc_inode, bh);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
atomic_inc(&osb->alloc_stats.bg_extends);
/* You should never ask for this much metadata */
BUG_ON(bits_wanted >
(le32_to_cpu(fe->id1.bitmap1.i_total)
- le32_to_cpu(fe->id1.bitmap1.i_used)));
}
get_bh(bh);
ac->ac_bh = bh;
bail:
if (bh)
brelse(bh);
mlog_exit(status);
return status;
}
/* will give out up to bits_wanted contiguous bits. */
static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac,
handle_t *handle,
u32 bits_wanted,
u32 min_bits,
u16 *bit_off,
unsigned int *num_bits,
u64 *bg_blkno)
{
int status;
u16 victim, i;
u16 bits_left = 0;
u64 hint_blkno = ac->ac_last_group;
struct ocfs2_chain_list *cl;
struct ocfs2_dinode *fe;
mlog_entry_void();
BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
BUG_ON(bits_wanted > (ac->ac_bits_wanted - ac->ac_bits_given));
BUG_ON(!ac->ac_bh);
fe = (struct ocfs2_dinode *) ac->ac_bh->b_data;
if (!OCFS2_IS_VALID_DINODE(fe)) {
OCFS2_RO_ON_INVALID_DINODE(osb->sb, fe);
status = -EIO;
goto bail;
}
if (le32_to_cpu(fe->id1.bitmap1.i_used) >=
le32_to_cpu(fe->id1.bitmap1.i_total)) {
ocfs2_error(osb->sb, "Chain allocator dinode %llu has %u used "
"bits but only %u total.",
(unsigned long long)le64_to_cpu(fe->i_blkno),
le32_to_cpu(fe->id1.bitmap1.i_used),
le32_to_cpu(fe->id1.bitmap1.i_total));
status = -EIO;
goto bail;
}
if (hint_blkno) {
/* Attempt to short-circuit the usual search mechanism
* by jumping straight to the most recently used
* allocation group. This helps us mantain some
* contiguousness across allocations. */
status = ocfs2_search_one_group(ac, handle, bits_wanted,
min_bits, bit_off, num_bits,
hint_blkno, &bits_left);
if (!status) {
/* Be careful to update *bg_blkno here as the
* caller is expecting it to be filled in, and
* ocfs2_search_one_group() won't do that for
* us. */
*bg_blkno = hint_blkno;
goto set_hint;
}
if (status < 0 && status != -ENOSPC) {
mlog_errno(status);
goto bail;
}
}
cl = (struct ocfs2_chain_list *) &fe->id2.i_chain;
victim = ocfs2_find_victim_chain(cl);
ac->ac_chain = victim;
ac->ac_allow_chain_relink = 1;
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, bit_off,
num_bits, bg_blkno, &bits_left);
if (!status)
goto set_hint;
if (status < 0 && status != -ENOSPC) {
mlog_errno(status);
goto bail;
}
mlog(0, "Search of victim chain %u came up with nothing, "
"trying all chains now.\n", victim);
/* If we didn't pick a good victim, then just default to
* searching each chain in order. Don't allow chain relinking
* because we only calculate enough journal credits for one
* relink per alloc. */
ac->ac_allow_chain_relink = 0;
for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
if (i == victim)
continue;
if (!cl->cl_recs[i].c_free)
continue;
ac->ac_chain = i;
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
bit_off, num_bits, bg_blkno,
&bits_left);
if (!status)
break;
if (status < 0 && status != -ENOSPC) {
mlog_errno(status);
goto bail;
}
}
set_hint:
if (status != -ENOSPC) {
/* If the next search of this group is not likely to
* yield a suitable extent, then we reset the last
* group hint so as to not waste a disk read */
if (bits_left < min_bits)
ac->ac_last_group = 0;
else
ac->ac_last_group = *bg_blkno;
}
bail:
mlog_exit(status);
return status;
}
static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac,
int type,
u32 slot,
u64 *last_alloc_group,
int flags)
{
int status;
u32 bits_wanted = ac->ac_bits_wanted;
struct inode *alloc_inode;
struct buffer_head *bh = NULL;
struct ocfs2_dinode *fe;
u32 free_bits;
alloc_inode = ocfs2_get_system_file_inode(osb, type, slot);
if (!alloc_inode) {
mlog_errno(-EINVAL);
return -EINVAL;
}
mutex_lock(&alloc_inode->i_mutex);
status = ocfs2_inode_lock(alloc_inode, &bh, 1);
if (status < 0) {
mutex_unlock(&alloc_inode->i_mutex);
iput(alloc_inode);
mlog_errno(status);
return status;
}
ac->ac_inode = alloc_inode;
ac->ac_alloc_slot = slot;
fe = (struct ocfs2_dinode *) bh->b_data;
/* The bh was validated by the inode read inside
* ocfs2_inode_lock(). Any corruption is a code bug. */
BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
if (!(fe->i_flags & cpu_to_le32(OCFS2_CHAIN_FL))) {
status = ocfs2_error(alloc_inode->i_sb,
"Invalid chain allocator %llu\n",
(unsigned long long)le64_to_cpu(fe->i_blkno));
goto bail;
}
free_bits = le32_to_cpu(fe->id1.bitmap1.i_total) -
le32_to_cpu(fe->id1.bitmap1.i_used);
if (bits_wanted > free_bits) {
/* cluster bitmap never grows */
if (ocfs2_is_cluster_bitmap(alloc_inode)) {
trace_ocfs2_reserve_suballoc_bits_nospc(bits_wanted,
free_bits);
status = -ENOSPC;
goto bail;
}
if (!(flags & ALLOC_NEW_GROUP)) {
trace_ocfs2_reserve_suballoc_bits_no_new_group(
slot, bits_wanted, free_bits);
status = -ENOSPC;
goto bail;
}
status = ocfs2_block_group_alloc(osb, alloc_inode, bh,
ac->ac_max_block,
last_alloc_group, flags);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
atomic_inc(&osb->alloc_stats.bg_extends);
/* You should never ask for this much metadata */
BUG_ON(bits_wanted >
(le32_to_cpu(fe->id1.bitmap1.i_total)
- le32_to_cpu(fe->id1.bitmap1.i_used)));
}
get_bh(bh);
ac->ac_bh = bh;
bail:
brelse(bh);
if (status)
mlog_errno(status);
return status;
}
/*
* make sure we've got at least bitswanted contiguous bits in the
* local alloc. You lose them when you drop i_mutex.
*
* We will add ourselves to the transaction passed in, but may start
* our own in order to shift windows.
*/
int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
struct ocfs2_journal_handle *passed_handle,
u32 bits_wanted,
struct ocfs2_alloc_context *ac)
{
int status;
struct ocfs2_dinode *alloc;
struct inode *local_alloc_inode;
unsigned int free_bits;
mlog_entry_void();
BUG_ON(!passed_handle);
BUG_ON(!ac);
BUG_ON(passed_handle->flags & OCFS2_HANDLE_STARTED);
local_alloc_inode =
ocfs2_get_system_file_inode(osb,
LOCAL_ALLOC_SYSTEM_INODE,
osb->slot_num);
if (!local_alloc_inode) {
status = -ENOENT;
mlog_errno(status);
goto bail;
}
ocfs2_handle_add_inode(passed_handle, local_alloc_inode);
if (osb->local_alloc_state != OCFS2_LA_ENABLED) {
status = -ENOSPC;
goto bail;
}
if (bits_wanted > ocfs2_local_alloc_window_bits(osb)) {
mlog(0, "Asking for more than my max window size!\n");
status = -ENOSPC;
goto bail;
}
alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
ocfs2_local_alloc_count_bits(alloc)) {
ocfs2_error(osb->sb, "local alloc inode %"MLFu64" says it has "
"%u free bits, but a count shows %u",
le64_to_cpu(alloc->i_blkno),
le32_to_cpu(alloc->id1.bitmap1.i_used),
ocfs2_local_alloc_count_bits(alloc));
status = -EIO;
goto bail;
}
free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) -
le32_to_cpu(alloc->id1.bitmap1.i_used);
if (bits_wanted > free_bits) {
/* uhoh, window change time. */
status =
ocfs2_local_alloc_slide_window(osb, local_alloc_inode);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
}
ac->ac_inode = igrab(local_alloc_inode);
get_bh(osb->local_alloc_bh);
ac->ac_bh = osb->local_alloc_bh;
ac->ac_which = OCFS2_AC_USE_LOCAL;
status = 0;
bail:
if (local_alloc_inode)
iput(local_alloc_inode);
mlog_exit(status);
return status;
}
