static bool nova_can_skip_full_scan(struct super_block *sb)
{
struct nova_inode *pi = nova_get_inode_by_ino(sb, NOVA_BLOCKNODE_INO);
int ret;
if (pi->log_head == 0 || pi->log_tail == 0)
return false;
ret = nova_init_blockmap_from_inode(sb);
if (ret) {
nova_err(sb, "init blockmap failed, "
"fall back to failure recovery\n");
return false;
}
ret = nova_init_inode_list_from_inode(sb);
if (ret) {
nova_err(sb, "init inode list failed, "
"fall back to failure recovery\n");
nova_destroy_blocknode_trees(sb);
return false;
}
return true;
}
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 int nova_insert_blocknode_map(struct super_block *sb,
int cpuid, unsigned long low, unsigned long high)
{
struct nova_sb_info *sbi = NOVA_SB(sb);
struct free_list *free_list;
struct rb_root *tree;
struct nova_range_node *blknode = NULL;
unsigned long num_blocks = 0;
int ret;
num_blocks = high - low + 1;
nova_dbgv("%s: cpu %d, low %lu, high %lu, num %lu\n",
__func__, cpuid, low, high, num_blocks);
free_list = nova_get_free_list(sb, cpuid);
tree = &(free_list->block_free_tree);
blknode = nova_alloc_blocknode(sb);
if (blknode == NULL)
return -ENOMEM;
blknode->range_low = low;
blknode->range_high = high;
ret = nova_insert_blocktree(sbi, tree, blknode);
if (ret) {
nova_err(sb, "%s failed\n", __func__);
nova_free_blocknode(sb, blknode);
goto out;
}
if (!free_list->first_node)
free_list->first_node = blknode;
free_list->num_blocknode++;
free_list->num_free_blocks += num_blocks;
out:
return ret;
}
static int nova_get_block_info(struct super_block *sb,
struct nova_sb_info *sbi)
{
void *virt_addr = NULL;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 5, 0)
pfn_t __pfn_t;
#else
unsigned long pfn;
#endif
long size;
if (!sb->s_bdev->bd_disk->fops->direct_access) {
nova_err(sb, "device does not support DAX\n");
return -EINVAL;
}
sbi->s_bdev = sb->s_bdev;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 5, 0)
size = sb->s_bdev->bd_disk->fops->direct_access(sb->s_bdev,
0, &virt_addr, &__pfn_t);
#else
size = sb->s_bdev->bd_disk->fops->direct_access(sb->s_bdev,
0, &virt_addr, &pfn);
#endif
if (size <= 0) {
nova_err(sb, "direct_access failed\n");
return -EINVAL;
}
sbi->virt_addr = virt_addr;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 5, 0)
sbi->phys_addr = pfn_t_to_pfn(__pfn_t) << PAGE_SHIFT;
#else
sbi->phys_addr = pfn << PAGE_SHIFT;
#endif
sbi->initsize = size;
nova_dbg("%s: dev %s, phys_addr 0x%llx, virt_addr %p, size %ld\n",
__func__, sbi->s_bdev->bd_disk->disk_name,
sbi->phys_addr, sbi->virt_addr, sbi->initsize);
return 0;
}
void nova_init_blockmap(struct super_block *sb, int recovery)
{
struct nova_sb_info *sbi = NOVA_SB(sb);
struct rb_root *tree;
unsigned long num_used_block;
struct nova_range_node *blknode;
struct free_list *free_list;
unsigned long per_list_blocks;
int i;
int ret;
num_used_block = sbi->reserved_blocks;
/* Divide the block range among per-CPU free lists */
per_list_blocks = sbi->num_blocks / sbi->cpus;
sbi->per_list_blocks = per_list_blocks;
for (i = 0; i < sbi->cpus; i++) {
free_list = nova_get_free_list(sb, i);
tree = &(free_list->block_free_tree);
free_list->block_start = per_list_blocks * i;
free_list->block_end = free_list->block_start +
per_list_blocks - 1;
/* For recovery, update these fields later */
if (recovery == 0) {
free_list->num_free_blocks = per_list_blocks;
if (i == 0) {
free_list->block_start += num_used_block;
free_list->num_free_blocks -= num_used_block;
}
blknode = nova_alloc_blocknode(sb);
if (blknode == NULL)
NOVA_ASSERT(0);
blknode->range_low = free_list->block_start;
blknode->range_high = free_list->block_end;
ret = nova_insert_blocktree(sbi, tree, blknode);
if (ret) {
nova_err(sb, "%s failed\n", __func__);
nova_free_blocknode(sb, blknode);
return;
}
free_list->first_node = blknode;
free_list->num_blocknode = 1;
}
}
free_list = nova_get_free_list(sb, (sbi->cpus - 1));
if (free_list->block_end + 1 < sbi->num_blocks) {
/* Shared free list gets any remaining blocks */
sbi->shared_free_list.block_start = free_list->block_end + 1;
sbi->shared_free_list.block_end = sbi->num_blocks - 1;
}
}
/* 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;
}
void nova_delete_dir_tree(struct super_block *sb,
struct nova_inode_info_header *sih)
{
struct nova_dentry *direntry;
unsigned long pos = 0;
struct nova_dentry *entries[FREE_BATCH];
timing_t delete_time;
int nr_entries;
int i;
void *ret;
NOVA_START_TIMING(delete_dir_tree_t, delete_time);
do {
nr_entries = radix_tree_gang_lookup(&sih->tree,
(void **)entries, pos, FREE_BATCH);
for (i = 0; i < nr_entries; i++) {
direntry = entries[i];
BUG_ON(!direntry);
pos = BKDRHash(direntry->name, direntry->name_len);
ret = radix_tree_delete(&sih->tree, pos);
if (!ret || ret != direntry) {
nova_err(sb, "dentry: type %d, inode %llu, "
"name %s, namelen %u, rec len %u\n",
direntry->entry_type,
le64_to_cpu(direntry->ino),
direntry->name, direntry->name_len,
le16_to_cpu(direntry->de_len));
if (!ret)
nova_dbg("ret is NULL\n");
}
}
pos++;
} while (nr_entries == FREE_BATCH);
NOVA_END_TIMING(delete_dir_tree_t, delete_time);
return;
}
static int nova_failure_insert_inodetree(struct super_block *sb,
unsigned long ino_low, unsigned long ino_high)
{
struct nova_sb_info *sbi = NOVA_SB(sb);
struct inode_map *inode_map;
struct nova_range_node *prev = NULL, *next = NULL;
struct nova_range_node *new_node;
unsigned long internal_low, internal_high;
int cpu;
struct rb_root *tree;
int ret;
if (ino_low > ino_high) {
nova_err(sb, "%s: ino low %lu, ino high %lu\n",
__func__, ino_low, ino_high);
BUG();
}
cpu = ino_low % sbi->cpus;
if (ino_high % sbi->cpus != cpu) {
nova_err(sb, "%s: ino low %lu, ino high %lu\n",
__func__, ino_low, ino_high);
BUG();
}
internal_low = ino_low / sbi->cpus;
internal_high = ino_high / sbi->cpus;
inode_map = &sbi->inode_maps[cpu];
tree = &inode_map->inode_inuse_tree;
mutex_lock(&inode_map->inode_table_mutex);
ret = nova_find_free_slot(sbi, tree, internal_low, internal_high,
&prev, &next);
if (ret) {
nova_dbg("%s: ino %lu - %lu already exists!: %d\n",
__func__, ino_low, ino_high, ret);
mutex_unlock(&inode_map->inode_table_mutex);
return ret;
}
if (prev && next && (internal_low == prev->range_high + 1) &&
(internal_high + 1 == next->range_low)) {
/* fits the hole */
rb_erase(&next->node, tree);
inode_map->num_range_node_inode--;
prev->range_high = next->range_high;
nova_free_inode_node(sb, next);
goto finish;
}
if (prev && (internal_low == prev->range_high + 1)) {
/* Aligns left */
prev->range_high += internal_high - internal_low + 1;
goto finish;
}
if (next && (internal_high + 1 == next->range_low)) {
/* Aligns right */
next->range_low -= internal_high - internal_low + 1;
goto finish;
}
/* Aligns somewhere in the middle */
new_node = nova_alloc_inode_node(sb);
NOVA_ASSERT(new_node);
new_node->range_low = internal_low;
new_node->range_high = internal_high;
ret = nova_insert_inodetree(sbi, new_node, cpu);
if (ret) {
nova_err(sb, "%s failed\n", __func__);
nova_free_inode_node(sb, new_node);
goto finish;
}
inode_map->num_range_node_inode++;
finish:
mutex_unlock(&inode_map->inode_table_mutex);
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;
}
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;
}
