static void *logfs_write_commit(struct super_block *sb, void *h,
u16 *type, size_t *len)
{
struct logfs_super *super = logfs_super(sb);
*type = JE_COMMIT;
*len = super->s_no_je * sizeof(__be64);
return super->s_je_array;
}
void logfs_cleanup_journal(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
btree_grim_visitor32(&super->s_reserved_segments, 0, NULL);
kfree(super->s_compressed_je);
kfree(super->s_je);
}
static void read_erasecount(struct super_block *sb,
struct logfs_je_journal_ec *ec)
{
struct logfs_super *super = logfs_super(sb);
int i;
journal_for_each(i)
super->s_journal_ec[i] = be32_to_cpu(ec->ec[i]);
}
int logfs_erase_segment(struct super_block *sb, u32 segno, int ensure_erase)
{
struct logfs_super *super = logfs_super(sb);
super->s_gec++;
return super->s_devops->erase(sb, (u64)segno << super->s_segshift,
super->s_segsize, ensure_erase);
}
/* called with inode->i_lock held */
static int logfs_drop_inode(struct inode *inode)
{
struct logfs_super *super = logfs_super(inode->i_sb);
struct logfs_inode *li = logfs_inode(inode);
spin_lock(&logfs_inode_lock);
list_move(&li->li_freeing_list, &super->s_freeing_list);
spin_unlock(&logfs_inode_lock);
return generic_drop_inode(inode);
}
static int __logfs_create(struct inode *dir, struct dentry *dentry,
struct inode *inode, const char *dest, long destlen)
{
struct logfs_super *super = logfs_super(dir->i_sb);
struct logfs_inode *li = logfs_inode(inode);
struct logfs_transaction *ta;
int ret;
ta = kzalloc(sizeof(*ta), GFP_KERNEL);
if (!ta)
return -ENOMEM;
ta->state = CREATE_1;
ta->ino = inode->i_ino;
mutex_lock(&super->s_dirop_mutex);
logfs_add_transaction(inode, ta);
if (dest) {
/* symlink */
ret = logfs_inode_write(inode, dest, destlen, 0, WF_LOCK, NULL);
if (!ret)
ret = write_inode(inode);
} else {
/* creat/mkdir/mknod */
ret = write_inode(inode);
}
if (ret) {
abort_transaction(inode, ta);
li->li_flags |= LOGFS_IF_STILLBORN;
/* FIXME: truncate symlink */
inode->i_nlink--;
iput(inode);
goto out;
}
ta->state = CREATE_2;
logfs_add_transaction(dir, ta);
ret = logfs_write_dir(dir, dentry, inode);
/* sync directory */
if (!ret)
ret = write_inode(dir);
if (ret) {
logfs_del_transaction(dir, ta);
ta->state = CREATE_2;
logfs_add_transaction(inode, ta);
logfs_remove_inode(inode);
iput(inode);
goto out;
}
d_instantiate(dentry, inode);
out:
mutex_unlock(&super->s_dirop_mutex);
return ret;
}
static int logfs_write_je(struct super_block *sb,
void* (*write)(struct super_block *sb, void *scratch,
u16 *type, size_t *len))
{
void *buf;
size_t len;
u16 type;
buf = write(sb, logfs_super(sb)->s_je, &type, &len);
return logfs_write_je_buf(sb, buf, type, len);
}
static s64 logfs_get_free_bytes(struct logfs_area *area, size_t bytes)
{
s32 ofs;
logfs_open_area(area, bytes);
ofs = area->a_used_bytes;
area->a_used_bytes += bytes;
BUG_ON(area->a_used_bytes >= logfs_super(area->a_sb)->s_segsize);
return dev_ofs(area->a_sb, area->a_segno, ofs);
}
static void read_dynsb(struct super_block *sb,
struct logfs_je_dynsb *dynsb)
{
struct logfs_super *super = logfs_super(sb);
super->s_gec = be64_to_cpu(dynsb->ds_gec);
super->s_sweeper = be64_to_cpu(dynsb->ds_sweeper);
super->s_victim_ino = be64_to_cpu(dynsb->ds_victim_ino);
super->s_rename_dir = be64_to_cpu(dynsb->ds_rename_dir);
super->s_rename_pos = be64_to_cpu(dynsb->ds_rename_pos);
super->s_used_bytes = be64_to_cpu(dynsb->ds_used_bytes);
super->s_generation = be32_to_cpu(dynsb->ds_generation);
}
static void writeseg_end_io(struct bio *bio)
{
struct bio_vec *bvec;
int i;
struct super_block *sb = bio->bi_private;
struct logfs_super *super = logfs_super(sb);
BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */
bio_for_each_segment_all(bvec, bio, i) {
end_page_writeback(bvec->bv_page);
page_cache_release(bvec->bv_page);
}
static void *logfs_write_erasecount(struct super_block *sb, void *_ec,
u16 *type, size_t *len)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_je_journal_ec *ec = _ec;
int i;
journal_for_each(i)
ec->ec[i] = cpu_to_be32(super->s_journal_ec[i]);
*type = JE_ERASECOUNT;
*len = logfs_journal_erasecount_size(super);
return ec;
}
static int logfs_read_segment(struct super_block *sb, u32 segno)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_journal_header *jh = super->s_compressed_je;
u64 ofs, seg_ofs = dev_ofs(sb, segno, 0);
u32 h_ofs, last_ofs = 0;
u16 len, datalen, last_len = 0;
int i, err;
for (h_ofs = 0; h_ofs < super->s_segsize; h_ofs += sizeof(*jh)) {
ofs = seg_ofs + h_ofs;
err = __read_je_header(sb, ofs, jh);
if (err)
continue;
if (jh->h_type != cpu_to_be16(JE_COMMIT))
continue;
err = __read_je_payload(sb, ofs, jh);
if (err)
continue;
len = be16_to_cpu(jh->h_len);
datalen = be16_to_cpu(jh->h_datalen);
if ((datalen > sizeof(super->s_je_array)) ||
(datalen % sizeof(__be64)))
continue;
last_ofs = h_ofs;
last_len = datalen;
h_ofs += ALIGN(len, sizeof(*jh)) - sizeof(*jh);
}
if (last_ofs == 0)
return -ENOENT;
ofs = seg_ofs + last_ofs;
log_journal("Read commit from %llx\n", ofs);
err = __read_je(sb, ofs, jh);
BUG_ON(err);
if (err)
return err;
unpack(jh, super->s_je_array);
super->s_no_je = last_len / sizeof(__be64);
for (i = 0; i < super->s_no_je; i++) {
err = read_je(sb, be64_to_cpu(super->s_je_array[i]));
if (err)
return err;
}
super->s_journal_area->a_segno = segno;
return 0;
}
static int logfs_unlink(struct inode *dir, struct dentry *dentry)
{
struct logfs_super *super = logfs_super(dir->i_sb);
struct inode *inode = dentry->d_inode;
struct logfs_transaction *ta;
struct page *page;
pgoff_t index;
int ret;
ta = kzalloc(sizeof(*ta), GFP_KERNEL);
if (!ta)
return -ENOMEM;
ta->state = UNLINK_1;
ta->ino = inode->i_ino;
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
page = logfs_get_dd_page(dir, dentry);
if (!page) {
kfree(ta);
return -ENOENT;
}
if (IS_ERR(page)) {
kfree(ta);
return PTR_ERR(page);
}
index = page->index;
page_cache_release(page);
mutex_lock(&super->s_dirop_mutex);
logfs_add_transaction(dir, ta);
ret = logfs_delete(dir, index, NULL);
if (!ret)
ret = write_inode(dir);
if (ret) {
abort_transaction(dir, ta);
printk(KERN_ERR"LOGFS: unable to delete inode\n");
goto out;
}
ta->state = UNLINK_2;
logfs_add_transaction(inode, ta);
ret = logfs_remove_inode(inode);
out:
mutex_unlock(&super->s_dirop_mutex);
return ret;
}
/* No locking done here, as this is called before .get_sb() returns. */
int logfs_replay_journal(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct inode *inode;
u64 ino, pos;
int err;
if (super->s_victim_ino) {
/* delete victim inode */
ino = super->s_victim_ino;
printk(KERN_INFO"LogFS: delete unmapped inode #%llx\n", ino);
inode = logfs_iget(sb, ino);
if (IS_ERR(inode))
goto fail;
LOGFS_BUG_ON(i_size_read(inode) > 0, sb);
super->s_victim_ino = 0;
err = logfs_remove_inode(inode);
iput(inode);
if (err) {
super->s_victim_ino = ino;
goto fail;
}
}
if (super->s_rename_dir) {
/* delete old dd from rename */
ino = super->s_rename_dir;
pos = super->s_rename_pos;
printk(KERN_INFO"LogFS: delete unbacked dentry (%llx, %llx)\n",
ino, pos);
inode = logfs_iget(sb, ino);
if (IS_ERR(inode))
goto fail;
super->s_rename_dir = 0;
super->s_rename_pos = 0;
err = logfs_delete_dd(inode, pos);
iput(inode);
if (err) {
super->s_rename_dir = ino;
super->s_rename_pos = pos;
goto fail;
}
}
return 0;
fail:
LOGFS_BUG(sb);
return -EIO;
}
/*
* FIXME: There should be a reserve for root, similar to ext2.
*/
int logfs_statfs(struct dentry *dentry, struct kstatfs *stats)
{
struct super_block *sb = dentry->d_sb;
struct logfs_super *super = logfs_super(sb);
stats->f_type = LOGFS_MAGIC_U32;
stats->f_bsize = sb->s_blocksize;
stats->f_blocks = super->s_size >> LOGFS_BLOCK_BITS >> 3;
stats->f_bfree = super->s_free_bytes >> sb->s_blocksize_bits;
stats->f_bavail = super->s_free_bytes >> sb->s_blocksize_bits;
stats->f_files = 0;
stats->f_ffree = 0;
stats->f_namelen = LOGFS_MAX_NAMELEN;
return 0;
}
/*
* Cross-directory rename, target does not exist. Just a little nasty.
* Create a new dentry in the target dir, then remove the old dentry,
* all the while taking care to remember our operation in the journal.
*/
static int logfs_rename_cross(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct logfs_super *super = logfs_super(old_dir->i_sb);
struct logfs_disk_dentry dd;
struct logfs_transaction *ta;
loff_t pos;
int err;
/* 1. locate source dd */
err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
if (err)
return err;
ta = kzalloc(sizeof(*ta), GFP_KERNEL);
if (!ta)
return -ENOMEM;
ta->state = CROSS_RENAME_1;
ta->dir = old_dir->i_ino;
ta->pos = pos;
/* 2. write target dd */
mutex_lock(&super->s_dirop_mutex);
logfs_add_transaction(new_dir, ta);
err = logfs_write_dir(new_dir, new_dentry, old_dentry->d_inode);
if (!err)
err = write_inode(new_dir);
if (err) {
super->s_rename_dir = 0;
super->s_rename_pos = 0;
abort_transaction(new_dir, ta);
goto out;
}
/* 3. remove source dd */
ta->state = CROSS_RENAME_2;
logfs_add_transaction(old_dir, ta);
err = logfs_delete_dd(old_dir, pos);
if (!err)
err = write_inode(old_dir);
LOGFS_BUG_ON(err, old_dir->i_sb);
out:
mutex_unlock(&super->s_dirop_mutex);
return err;
}
static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
size_t nr_pages)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
struct bio *bio;
struct page *page;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
int i;
if (max_pages > BIO_MAX_PAGES)
max_pages = BIO_MAX_PAGES;
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
for (i = 0; i < nr_pages; i++) {
if (i >= max_pages) {
/* Block layer cannot split bios :( */
bio->bi_vcnt = i;
bio->bi_idx = 0;
bio->bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = writeseg_end_io;
atomic_inc(&super->s_pending_writes);
submit_bio(WRITE, bio);
ofs += i * PAGE_SIZE;
index += i;
nr_pages -= i;
i = 0;
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
}
page = find_lock_page(mapping, index + i);
BUG_ON(!page);
bio->bi_io_vec[i].bv_page = page;
bio->bi_io_vec[i].bv_len = PAGE_SIZE;
bio->bi_io_vec[i].bv_offset = 0;
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
}
static int logfs_read_sb(struct super_block *sb, int read_only)
{
struct logfs_super *super = logfs_super(sb);
int ret;
super->s_btree_pool = mempool_create(32, btree_alloc, btree_free, NULL);
if (!super->s_btree_pool)
return -ENOMEM;
btree_init_mempool64(&super->s_shadow_tree.new, super->s_btree_pool);
btree_init_mempool64(&super->s_shadow_tree.old, super->s_btree_pool);
btree_init_mempool32(&super->s_shadow_tree.segment_map,
super->s_btree_pool);
ret = logfs_init_mapping(sb);
if (ret)
return ret;
ret = __logfs_read_sb(sb);
if (ret)
return ret;
if (super->s_feature_incompat & ~LOGFS_FEATURES_INCOMPAT)
return -EIO;
if ((super->s_feature_ro_compat & ~LOGFS_FEATURES_RO_COMPAT) &&
!read_only)
return -EIO;
ret = logfs_init_rw(sb);
if (ret)
return ret;
ret = logfs_init_areas(sb);
if (ret)
return ret;
/*
ret = logfs_init_gc(sb);
if (ret)
return ret;
*/
ret = logfs_init_journal(sb);
if (ret)
return ret;
return 0;
}
static struct page *get_mapping_page(struct super_block *sb, pgoff_t index,
int use_filler)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
filler_t *filler = super->s_devops->readpage;
struct page *page;
BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS);
if (use_filler)
page = read_cache_page(mapping, index, filler, sb);
else {
page = find_or_create_page(mapping, index, GFP_NOFS);
unlock_page(page);
}
return page;
}
static void account_shadows(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct inode *inode = super->s_master_inode;
struct logfs_inode *li = logfs_inode(inode);
struct shadow_tree *tree = &super->s_shadow_tree;
btree_grim_visitor64(&tree->new, (unsigned long)sb, account_shadow);
btree_grim_visitor64(&tree->old, (unsigned long)sb, account_shadow);
btree_grim_visitor32(&tree->segment_map, 0, NULL);
tree->no_shadowed_segments = 0;
if (li->li_block) {
li->li_block->ops->free_block(sb, li->li_block);
}
BUG_ON((s64)li->li_used_bytes < 0);
}
static int bdev_readpage(void *_sb, struct page *page)
{
struct super_block *sb = _sb;
struct block_device *bdev = logfs_super(sb)->s_bdev;
int err;
err = sync_request(page, bdev, READ);
if (err) {
ClearPageUptodate(page);
SetPageError(page);
} else {
SetPageUptodate(page);
ClearPageError(page);
}
unlock_page(page);
return err;
}
static void read_anchor(struct super_block *sb,
struct logfs_je_anchor *da)
{
struct logfs_super *super = logfs_super(sb);
struct inode *inode = super->s_master_inode;
struct logfs_inode *li = logfs_inode(inode);
int i;
super->s_last_ino = be64_to_cpu(da->da_last_ino);
li->li_flags = 0;
li->li_height = da->da_height;
i_size_write(inode, be64_to_cpu(da->da_size));
li->li_used_bytes = be64_to_cpu(da->da_used_bytes);
for (i = 0; i < LOGFS_EMBEDDED_FIELDS; i++)
li->li_data[i] = be64_to_cpu(da->da_data[i]);
}
static void *logfs_write_dynsb(struct super_block *sb, void *_dynsb,
u16 *type, size_t *len)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_je_dynsb *dynsb = _dynsb;
dynsb->ds_gec = cpu_to_be64(super->s_gec);
dynsb->ds_sweeper = cpu_to_be64(super->s_sweeper);
dynsb->ds_victim_ino = cpu_to_be64(super->s_victim_ino);
dynsb->ds_rename_dir = cpu_to_be64(super->s_rename_dir);
dynsb->ds_rename_pos = cpu_to_be64(super->s_rename_pos);
dynsb->ds_used_bytes = cpu_to_be64(super->s_used_bytes);
dynsb->ds_generation = cpu_to_be32(super->s_generation);
*type = JE_DYNSB;
*len = sizeof(*dynsb);
return dynsb;
}
static int logfs_get_sb_final(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct inode *rootdir;
int err;
/* root dir */
rootdir = logfs_iget(sb, LOGFS_INO_ROOT);
if (IS_ERR(rootdir))
//goto fail;
return -EIO;
sb->s_root = d_make_root(rootdir);
if (!sb->s_root)
//goto fail;
return -EIO;
// at that point we know that ->put_super() will be called
super->s_erase_page = alloc_pages(GFP_KERNEL, 0);
if (!super->s_erase_page)
return -ENOMEM;
memset(page_address(super->s_erase_page), 0xFF, PAGE_SIZE);
/*
// FIXME: check for read-only mounts
err = logfs_make_writeable(sb);
if (err) {
__free_page(super->s_erase_page);
return err;
}
*/
log_super("LogFS: Finished mounting\n");
return 0;
/*
fail:
iput(super->s_master_inode);
iput(super->s_segfile_inode);
iput(super->s_mapping_inode);
return -EIO;
*/
}
static void *logfs_write_area(struct super_block *sb, void *_a,
u16 *type, size_t *len)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_area *area = super->s_area[super->s_sum_index];
struct logfs_je_area *a = _a;
a->vim = VIM_DEFAULT;
a->gc_level = super->s_sum_index;
a->used_bytes = cpu_to_be32(area->a_used_bytes);
a->segno = cpu_to_be32(area->a_segno);
if (super->s_writesize > 1)
write_wbuf(sb, area, a + 1);
*type = JE_AREA;
*len = sizeof(*a) + super->s_writesize;
return a;
}
static int logfs_write_obj_aliases(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
int err;
log_journal("logfs_write_obj_aliases: %d aliases to write\n",
super->s_no_object_aliases);
super->s_je_fill = 0;
err = logfs_write_obj_aliases_pagecache(sb);
if (err)
return err;
if (super->s_je_fill)
err = logfs_write_je_buf(sb, super->s_je, JE_OBJ_ALIAS,
super->s_je_fill
* sizeof(struct logfs_obj_alias));
return err;
}
static void logfs_set_ino_generation(struct super_block *sb,
struct inode *inode)
{
struct logfs_super *super = logfs_super(sb);
u64 ino;
mutex_lock(&super->s_journal_mutex);
ino = logfs_seek_hole(super->s_master_inode, super->s_last_ino + 1);
super->s_last_ino = ino;
super->s_inos_till_wrap--;
if (super->s_inos_till_wrap < 0) {
super->s_last_ino = LOGFS_RESERVED_INOS;
super->s_generation++;
super->s_inos_till_wrap = INOS_PER_WRAP;
}
inode->i_ino = ino;
inode->i_generation = super->s_generation;
mutex_unlock(&super->s_journal_mutex);
}
static void *__logfs_write_anchor(struct super_block *sb, void *_da,
u16 *type, size_t *len)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_je_anchor *da = _da;
struct inode *inode = super->s_master_inode;
struct logfs_inode *li = logfs_inode(inode);
int i;
da->da_height = li->li_height;
da->da_last_ino = cpu_to_be64(super->s_last_ino);
da->da_size = cpu_to_be64(i_size_read(inode));
da->da_used_bytes = cpu_to_be64(li->li_used_bytes);
for (i = 0; i < LOGFS_EMBEDDED_FIELDS; i++)
da->da_data[i] = cpu_to_be64(li->li_data[i]);
*type = JE_ANCHOR;
*len = sizeof(*da);
return da;
}
void logfs_cleanup_gc(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
int i;
if (!super->s_free_list.count)
return;
/*
* FIXME: The btree may still contain a single empty node. So we
* call the grim visitor to clean up that mess. Btree code should
* do it for us, really.
*/
btree_grim_visitor32(&super->s_cand_tree, 0, NULL);
logfs_cleanup_list(sb, &super->s_free_list);
logfs_cleanup_list(sb, &super->s_reserve_list);
for_each_area(i)
logfs_cleanup_list(sb, &super->s_low_list[i]);
logfs_cleanup_list(sb, &super->s_ec_list);
}
static void write_wbuf(struct super_block *sb, struct logfs_area *area,
void *wbuf)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
u64 ofs;
pgoff_t index;
int page_ofs;
struct page *page;
ofs = dev_ofs(sb, area->a_segno,
area->a_used_bytes & ~(super->s_writesize - 1));
index = ofs >> PAGE_SHIFT;
page_ofs = ofs & (PAGE_SIZE - 1);
page = find_lock_page(mapping, index);
BUG_ON(!page);
memcpy(wbuf, page_address(page) + page_ofs, super->s_writesize);
unlock_page(page);
}