static int nova_traverse_dir_inode_log(struct super_block *sb,
struct nova_inode *pi, struct scan_bitmap *bm)
{
struct nova_inode_log_page *curr_page;
u64 curr_p;
u64 next;
curr_p = pi->log_head;
if (curr_p == 0) {
nova_err(sb, "Dir %llu log is NULL!\n", pi->nova_ino);
BUG();
}
nova_dbg_verbose("Log head 0x%llx, tail 0x%llx\n",
curr_p, pi->log_tail);
BUG_ON(curr_p & (PAGE_SIZE - 1));
set_bm(curr_p >> PAGE_SHIFT, bm, BM_4K);
curr_page = (struct nova_inode_log_page *)nova_get_block(sb, curr_p);
while ((next = curr_page->page_tail.next_page) != 0) {
curr_p = next;
BUG_ON(curr_p & (PAGE_SIZE - 1));
set_bm(curr_p >> PAGE_SHIFT, bm, BM_4K);
curr_page = (struct nova_inode_log_page *)
nova_get_block(sb, curr_p);
}
return 0;
}
static u64 nova_append_range_node_entry(struct super_block *sb,
struct nova_range_node *curr, u64 tail, unsigned long cpuid)
{
u64 curr_p;
size_t size = sizeof(struct nova_range_node_lowhigh);
struct nova_range_node_lowhigh *entry;
curr_p = tail;
if (curr_p == 0 || (is_last_entry(curr_p, size) &&
next_log_page(sb, curr_p) == 0)) {
nova_dbg("%s: inode log reaches end?\n", __func__);
goto out;
}
if (is_last_entry(curr_p, size))
curr_p = next_log_page(sb, curr_p);
entry = (struct nova_range_node_lowhigh *)nova_get_block(sb, curr_p);
entry->range_low = cpu_to_le64(curr->range_low);
if (cpuid)
entry->range_low |= cpu_to_le64(cpuid << 56);
entry->range_high = cpu_to_le64(curr->range_high);
nova_dbgv("append entry block low 0x%lx, high 0x%lx\n",
curr->range_low, curr->range_high);
nova_flush_buffer(entry, sizeof(struct nova_range_node_lowhigh), 0);
out:
return curr_p;
}
/*
* Append a nova_dentry to the current nova_inode_log_page.
* Note unlike append_file_write_entry(), this method returns the tail pointer
* after append.
*/
static u64 nova_append_dir_inode_entry(struct super_block *sb,
struct nova_inode *pidir, struct inode *dir,
u64 ino, struct dentry *dentry, unsigned short de_len, u64 tail,
int link_change, u64 *curr_tail)
{
struct nova_inode_info *si = NOVA_I(dir);
struct nova_inode_info_header *sih = &si->header;
struct nova_dentry *entry;
u64 curr_p;
size_t size = de_len;
int extended = 0;
unsigned short links_count;
timing_t append_time;
NOVA_START_TIMING(append_dir_entry_t, append_time);
curr_p = nova_get_append_head(sb, pidir, sih, tail, size, &extended);
if (curr_p == 0)
BUG();
entry = (struct nova_dentry *)nova_get_block(sb, curr_p);
entry->entry_type = DIR_LOG;
entry->ino = cpu_to_le64(ino);
entry->name_len = dentry->d_name.len;
memcpy_to_pmem_nocache(entry->name, dentry->d_name.name,
dentry->d_name.len);
entry->name[dentry->d_name.len] = '\0';
entry->file_type = 0;
entry->invalid = 0;
entry->mtime = cpu_to_le32(dir->i_mtime.tv_sec);
entry->size = cpu_to_le64(dir->i_size);
links_count = cpu_to_le16(dir->i_nlink);
if (links_count == 0 && link_change == -1)
links_count = 0;
else
links_count += link_change;
entry->links_count = cpu_to_le16(links_count);
/* Update actual de_len */
entry->de_len = cpu_to_le16(de_len);
nova_dbg_verbose("dir entry @ 0x%llx: ino %llu, entry len %u, "
"name len %u, file type %u\n",
curr_p, entry->ino, entry->de_len,
entry->name_len, entry->file_type);
nova_flush_buffer(entry, de_len, 0);
*curr_tail = curr_p + de_len;
dir->i_blocks = pidir->i_blocks;
NOVA_END_TIMING(append_dir_entry_t, append_time);
return curr_p;
}
/* Append . and .. entries */
int nova_append_dir_init_entries(struct super_block *sb,
struct nova_inode *pi, u64 self_ino, u64 parent_ino)
{
int allocated;
u64 new_block;
u64 curr_p;
struct nova_dentry *de_entry;
if (pi->log_head) {
nova_dbg("%s: log head exists @ 0x%llx!\n",
__func__, pi->log_head);
return - EINVAL;
}
allocated = nova_allocate_inode_log_pages(sb, pi, 1, &new_block);
if (allocated != 1) {
nova_err(sb, "ERROR: no inode log page available\n");
return - ENOMEM;
}
pi->log_tail = pi->log_head = new_block;
pi->i_blocks = 1;
nova_flush_buffer(&pi->log_head, CACHELINE_SIZE, 0);
de_entry = (struct nova_dentry *)nova_get_block(sb, new_block);
de_entry->entry_type = DIR_LOG;
de_entry->ino = cpu_to_le64(self_ino);
de_entry->name_len = 1;
de_entry->de_len = cpu_to_le16(NOVA_DIR_LOG_REC_LEN(1));
de_entry->mtime = CURRENT_TIME_SEC.tv_sec;
de_entry->size = sb->s_blocksize;
de_entry->links_count = 1;
strncpy(de_entry->name, ".\0", 2);
nova_flush_buffer(de_entry, NOVA_DIR_LOG_REC_LEN(1), 0);
curr_p = new_block + NOVA_DIR_LOG_REC_LEN(1);
de_entry = (struct nova_dentry *)((char *)de_entry +
le16_to_cpu(de_entry->de_len));
de_entry->entry_type = DIR_LOG;
de_entry->ino = cpu_to_le64(parent_ino);
de_entry->name_len = 2;
de_entry->de_len = cpu_to_le16(NOVA_DIR_LOG_REC_LEN(2));
de_entry->mtime = CURRENT_TIME_SEC.tv_sec;
de_entry->size = sb->s_blocksize;
de_entry->links_count = 2;
strncpy(de_entry->name, "..\0", 3);
nova_flush_buffer(de_entry, NOVA_DIR_LOG_REC_LEN(2), 0);
curr_p += NOVA_DIR_LOG_REC_LEN(2);
nova_update_tail(pi, curr_p);
return 0;
}
int nova_rebuild_inode(struct super_block *sb, struct nova_inode_info *si,
u64 pi_addr)
{
struct nova_inode_info_header *sih = &si->header;
struct nova_inode *pi;
unsigned long nova_ino;
pi = (struct nova_inode *)nova_get_block(sb, pi_addr);
if (!pi)
NOVA_ASSERT(0);
if (pi->valid == 0)
return -EINVAL;
nova_ino = pi->nova_ino;
nova_dbgv("%s: inode %lu, addr 0x%llx, valid %d, "
"head 0x%llx, tail 0x%llx\n",
__func__, nova_ino, pi_addr, pi->valid,
pi->log_head, pi->log_tail);
nova_init_header(sb, sih, __le16_to_cpu(pi->i_mode));
sih->ino = nova_ino;
switch (__le16_to_cpu(pi->i_mode) & S_IFMT) {
case S_IFLNK:
/* Treat symlink files as normal files */
/* Fall through */
case S_IFREG:
nova_rebuild_file_inode_tree(sb, pi, pi_addr, sih);
break;
case S_IFDIR:
nova_rebuild_dir_inode_tree(sb, pi, pi_addr, sih);
break;
default:
/* In case of special inode, walk the log */
if (pi->log_head)
nova_rebuild_file_inode_tree(sb, pi, pi_addr, sih);
sih->pi_addr = pi_addr;
break;
}
return 0;
}
/* adds a directory entry pointing to the inode. assumes the inode has
* already been logged for consistency
*/
int nova_add_dentry(struct dentry *dentry, u64 ino, int inc_link,
u64 tail, u64 *new_tail)
{
struct inode *dir = dentry->d_parent->d_inode;
struct super_block *sb = dir->i_sb;
struct nova_inode_info *si = NOVA_I(dir);
struct nova_inode_info_header *sih = &si->header;
struct nova_inode *pidir;
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
struct nova_dentry *direntry;
unsigned short loglen;
int ret;
u64 curr_entry, curr_tail;
timing_t add_dentry_time;
nova_dbg_verbose("%s: dir %lu new inode %llu\n",
__func__, dir->i_ino, ino);
nova_dbg_verbose("%s: %s %d\n", __func__, name, namelen);
NOVA_START_TIMING(add_dentry_t, add_dentry_time);
if (namelen == 0)
return -EINVAL;
pidir = nova_get_inode(sb, dir);
/*
* XXX shouldn't update any times until successful
* completion of syscall, but too many callers depend
* on this.
*/
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
loglen = NOVA_DIR_LOG_REC_LEN(namelen);
curr_entry = nova_append_dir_inode_entry(sb, pidir, dir, ino,
dentry, loglen, tail, inc_link,
&curr_tail);
direntry = (struct nova_dentry *)nova_get_block(sb, curr_entry);
ret = nova_insert_dir_radix_tree(sb, sih, name, namelen, direntry);
*new_tail = curr_tail;
NOVA_END_TIMING(add_dentry_t, add_dentry_time);
return ret;
}
static int nova_init_inode_list_from_inode(struct super_block *sb)
{
struct nova_sb_info *sbi = NOVA_SB(sb);
struct nova_inode *pi = nova_get_inode_by_ino(sb, NOVA_INODELIST1_INO);
struct nova_range_node_lowhigh *entry;
struct nova_range_node *range_node;
struct inode_map *inode_map;
size_t size = sizeof(struct nova_range_node_lowhigh);
unsigned long num_inode_node = 0;
u64 curr_p;
unsigned long cpuid;
int ret;
sbi->s_inodes_used_count = 0;
curr_p = pi->log_head;
if (curr_p == 0) {
nova_dbg("%s: pi head is 0!\n", __func__);
return -EINVAL;
}
while (curr_p != pi->log_tail) {
if (is_last_entry(curr_p, size)) {
curr_p = next_log_page(sb, curr_p);
}
if (curr_p == 0) {
nova_dbg("%s: curr_p is NULL!\n", __func__);
NOVA_ASSERT(0);
}
entry = (struct nova_range_node_lowhigh *)nova_get_block(sb,
curr_p);
range_node = nova_alloc_inode_node(sb);
if (range_node == NULL)
NOVA_ASSERT(0);
cpuid = (entry->range_low & CPUID_MASK) >> 56;
if (cpuid >= sbi->cpus) {
nova_err(sb, "Invalid cpuid %lu\n", cpuid);
nova_free_inode_node(sb, range_node);
NOVA_ASSERT(0);
nova_destroy_inode_trees(sb);
goto out;
}
range_node->range_low = entry->range_low & ~CPUID_MASK;
range_node->range_high = entry->range_high;
ret = nova_insert_inodetree(sbi, range_node, cpuid);
if (ret) {
nova_err(sb, "%s failed, %d\n", __func__, cpuid);
nova_free_inode_node(sb, range_node);
NOVA_ASSERT(0);
nova_destroy_inode_trees(sb);
goto out;
}
sbi->s_inodes_used_count +=
range_node->range_high - range_node->range_low + 1;
num_inode_node++;
inode_map = &sbi->inode_maps[cpuid];
inode_map->num_range_node_inode++;
if (!inode_map->first_inode_range)
inode_map->first_inode_range = range_node;
curr_p += sizeof(struct nova_range_node_lowhigh);
}
nova_dbg("%s: %lu inode nodes\n", __func__, num_inode_node);
out:
nova_free_inode_log(sb, pi);
return ret;
}
static int nova_init_blockmap_from_inode(struct super_block *sb)
{
struct nova_sb_info *sbi = NOVA_SB(sb);
struct nova_inode *pi = nova_get_inode_by_ino(sb, NOVA_BLOCKNODE_INO);
struct free_list *free_list;
struct nova_range_node_lowhigh *entry;
struct nova_range_node *blknode;
size_t size = sizeof(struct nova_range_node_lowhigh);
u64 curr_p;
u64 cpuid;
int ret = 0;
curr_p = pi->log_head;
if (curr_p == 0) {
nova_dbg("%s: pi head is 0!\n", __func__);
return -EINVAL;
}
while (curr_p != pi->log_tail) {
if (is_last_entry(curr_p, size)) {
curr_p = next_log_page(sb, curr_p);
}
if (curr_p == 0) {
nova_dbg("%s: curr_p is NULL!\n", __func__);
NOVA_ASSERT(0);
ret = -EINVAL;
break;
}
entry = (struct nova_range_node_lowhigh *)nova_get_block(sb,
curr_p);
blknode = nova_alloc_blocknode(sb);
if (blknode == NULL)
NOVA_ASSERT(0);
blknode->range_low = le64_to_cpu(entry->range_low);
blknode->range_high = le64_to_cpu(entry->range_high);
cpuid = get_cpuid(sbi, blknode->range_low);
/* FIXME: Assume NR_CPUS not change */
free_list = nova_get_free_list(sb, cpuid);
ret = nova_insert_blocktree(sbi,
&free_list->block_free_tree, blknode);
if (ret) {
nova_err(sb, "%s failed\n", __func__);
nova_free_blocknode(sb, blknode);
NOVA_ASSERT(0);
nova_destroy_blocknode_trees(sb);
goto out;
}
free_list->num_blocknode++;
if (free_list->num_blocknode == 1)
free_list->first_node = blknode;
free_list->num_free_blocks +=
blknode->range_high - blknode->range_low + 1;
curr_p += sizeof(struct nova_range_node_lowhigh);
}
out:
nova_free_inode_log(sb, pi);
return ret;
}
static int nova_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
struct nova_inode *pidir;
struct nova_inode_info *si = NOVA_I(inode);
struct nova_inode_info_header *sih = &si->header;
struct nova_inode *child_pi;
struct nova_inode *prev_child_pi = NULL;
struct nova_dentry *entry = NULL;
struct nova_dentry *prev_entry = NULL;
unsigned short de_len;
u64 pi_addr;
unsigned long pos = 0;
ino_t ino;
void *addr;
u64 curr_p;
u8 type;
int ret;
timing_t readdir_time;
NOVA_START_TIMING(readdir_t, readdir_time);
pidir = nova_get_inode(sb, inode);
nova_dbgv("%s: ino %llu, size %llu, pos 0x%llx\n",
__func__, (u64)inode->i_ino,
pidir->i_size, ctx->pos);
if (pidir->log_head == 0) {
nova_err(sb, "Dir %lu log is NULL!\n", inode->i_ino);
BUG();
return -EINVAL;
}
pos = ctx->pos;
if (pos == 0) {
curr_p = pidir->log_head;
} else if (pos == READDIR_END) {
goto out;
} else {
curr_p = nova_find_next_dentry_addr(sb, sih, pos);
if (curr_p == 0)
goto out;
}
while (curr_p != pidir->log_tail) {
if (goto_next_page(sb, curr_p)) {
curr_p = next_log_page(sb, curr_p);
}
if (curr_p == 0) {
nova_err(sb, "Dir %lu log is NULL!\n", inode->i_ino);
BUG();
return -EINVAL;
}
addr = (void *)nova_get_block(sb, curr_p);
type = nova_get_entry_type(addr);
switch (type) {
case SET_ATTR:
curr_p += sizeof(struct nova_setattr_logentry);
continue;
case LINK_CHANGE:
curr_p += sizeof(struct nova_link_change_entry);
continue;
case DIR_LOG:
break;
default:
nova_dbg("%s: unknown type %d, 0x%llx\n",
__func__, type, curr_p);
BUG();
return -EINVAL;
}
entry = (struct nova_dentry *)nova_get_block(sb, curr_p);
nova_dbgv("curr_p: 0x%llx, type %d, ino %llu, "
"name %s, namelen %u, rec len %u\n", curr_p,
entry->entry_type, le64_to_cpu(entry->ino),
entry->name, entry->name_len,
le16_to_cpu(entry->de_len));
de_len = le16_to_cpu(entry->de_len);
if (entry->ino > 0 && entry->invalid == 0) {
ino = __le64_to_cpu(entry->ino);
pos = BKDRHash(entry->name, entry->name_len);
ret = nova_get_inode_address(sb, ino, &pi_addr, 0);
if (ret) {
nova_dbg("%s: get child inode %lu address "
"failed %d\n", __func__, ino, ret);
ctx->pos = READDIR_END;
return ret;
}
child_pi = nova_get_block(sb, pi_addr);
nova_dbgv("ctx: ino %llu, name %s, "
"name_len %u, de_len %u\n",
(u64)ino, entry->name, entry->name_len,
entry->de_len);
if (prev_entry && !dir_emit(ctx, prev_entry->name,
prev_entry->name_len, ino,
IF2DT(le16_to_cpu(prev_child_pi->i_mode)))) {
nova_dbgv("Here: pos %llu\n", ctx->pos);
return 0;
}
prev_entry = entry;
prev_child_pi = child_pi;
}
ctx->pos = pos;
curr_p += de_len;
}
if (prev_entry && !dir_emit(ctx, prev_entry->name,
prev_entry->name_len, ino,
IF2DT(le16_to_cpu(prev_child_pi->i_mode))))
return 0;
ctx->pos = READDIR_END;
out:
NOVA_END_TIMING(readdir_t, readdir_time);
nova_dbgv("%s return\n", __func__);
return 0;
}
static int nova_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
struct nova_inode *pidir;
struct nova_inode_info *si = NOVA_I(inode);
struct nova_inode_info_header *sih = &si->header;
struct nova_inode *child_pi;
struct nova_dentry *entry;
struct nova_dentry *entries[FREE_BATCH];
int nr_entries;
u64 pi_addr;
unsigned long pos = 0;
ino_t ino;
int i;
int ret;
timing_t readdir_time;
NOVA_START_TIMING(readdir_t, readdir_time);
pidir = nova_get_inode(sb, inode);
nova_dbgv("%s: ino %llu, size %llu, pos %llu\n",
__func__, (u64)inode->i_ino,
pidir->i_size, ctx->pos);
if (!sih) {
nova_dbg("%s: inode %lu sih does not exist!\n",
__func__, inode->i_ino);
ctx->pos = READDIR_END;
return 0;
}
pos = ctx->pos;
if (pos == READDIR_END)
goto out;
do {
nr_entries = radix_tree_gang_lookup(&sih->tree,
(void **)entries, pos, FREE_BATCH);
for (i = 0; i < nr_entries; i++) {
entry = entries[i];
pos = BKDRHash(entry->name, entry->name_len);
ino = __le64_to_cpu(entry->ino);
if (ino == 0)
continue;
ret = nova_get_inode_address(sb, ino, &pi_addr, 0);
if (ret) {
nova_dbg("%s: get child inode %lu address "
"failed %d\n", __func__, ino, ret);
ctx->pos = READDIR_END;
return ret;
}
child_pi = nova_get_block(sb, pi_addr);
nova_dbgv("ctx: ino %llu, name %s, "
"name_len %u, de_len %u\n",
(u64)ino, entry->name, entry->name_len,
entry->de_len);
if (!dir_emit(ctx, entry->name, entry->name_len,
ino, IF2DT(le16_to_cpu(child_pi->i_mode)))) {
nova_dbgv("Here: pos %llu\n", ctx->pos);
return 0;
}
ctx->pos = pos + 1;
}
pos++;
} while (nr_entries == FREE_BATCH);
out:
NOVA_END_TIMING(readdir_t, readdir_time);
return 0;
}
int nova_rebuild_dir_inode_tree(struct super_block *sb,
struct nova_inode *pi, u64 pi_addr,
struct nova_inode_info_header *sih)
{
struct nova_dentry *entry = NULL;
struct nova_setattr_logentry *attr_entry = NULL;
struct nova_link_change_entry *link_change_entry = NULL;
struct nova_inode_log_page *curr_page;
u64 ino = pi->nova_ino;
unsigned short de_len;
timing_t rebuild_time;
void *addr;
u64 curr_p;
u64 next;
u8 type;
int ret;
NOVA_START_TIMING(rebuild_dir_t, rebuild_time);
nova_dbg_verbose("Rebuild dir %llu tree\n", ino);
sih->pi_addr = pi_addr;
curr_p = pi->log_head;
if (curr_p == 0) {
nova_err(sb, "Dir %llu log is NULL!\n", ino);
BUG();
}
nova_dbg_verbose("Log head 0x%llx, tail 0x%llx\n",
curr_p, pi->log_tail);
sih->log_pages = 1;
while (curr_p != pi->log_tail) {
if (goto_next_page(sb, curr_p)) {
sih->log_pages++;
curr_p = next_log_page(sb, curr_p);
}
if (curr_p == 0) {
nova_err(sb, "Dir %llu log is NULL!\n", ino);
BUG();
}
addr = (void *)nova_get_block(sb, curr_p);
type = nova_get_entry_type(addr);
switch (type) {
case SET_ATTR:
attr_entry =
(struct nova_setattr_logentry *)addr;
nova_apply_setattr_entry(sb, pi, sih,
attr_entry);
sih->last_setattr = curr_p;
curr_p += sizeof(struct nova_setattr_logentry);
continue;
case LINK_CHANGE:
link_change_entry =
(struct nova_link_change_entry *)addr;
nova_apply_link_change_entry(pi,
link_change_entry);
sih->last_link_change = curr_p;
curr_p += sizeof(struct nova_link_change_entry);
continue;
case DIR_LOG:
break;
default:
nova_dbg("%s: unknown type %d, 0x%llx\n",
__func__, type, curr_p);
NOVA_ASSERT(0);
}
entry = (struct nova_dentry *)nova_get_block(sb, curr_p);
nova_dbgv("curr_p: 0x%llx, type %d, ino %llu, "
"name %s, namelen %u, rec len %u\n", curr_p,
entry->entry_type, le64_to_cpu(entry->ino),
entry->name, entry->name_len,
le16_to_cpu(entry->de_len));
if (entry->ino > 0) {
if (entry->invalid == 0) {
/* A valid entry to add */
ret = nova_replay_add_dentry(sb, sih, entry);
}
} else {
/* Delete the entry */
ret = nova_replay_remove_dentry(sb, sih, entry);
}
if (ret) {
nova_err(sb, "%s ERROR %d\n", __func__, ret);
break;
}
nova_rebuild_dir_time_and_size(sb, pi, entry);
de_len = le16_to_cpu(entry->de_len);
curr_p += de_len;
}
sih->i_size = le64_to_cpu(pi->i_size);
sih->i_mode = le64_to_cpu(pi->i_mode);
nova_flush_buffer(pi, sizeof(struct nova_inode), 0);
/* Keep traversing until log ends */
curr_p &= PAGE_MASK;
curr_page = (struct nova_inode_log_page *)nova_get_block(sb, curr_p);
while ((next = curr_page->page_tail.next_page) != 0) {
sih->log_pages++;
curr_p = next;
curr_page = (struct nova_inode_log_page *)
nova_get_block(sb, curr_p);
}
pi->i_blocks = sih->log_pages;
// nova_print_dir_tree(sb, sih, ino);
NOVA_END_TIMING(rebuild_dir_t, rebuild_time);
return 0;
}