static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
block_t total_count, user_block_count, start_count, ovp_count;
total_count = le64_to_cpu(sbi->raw_super->block_count);
user_block_count = sbi->user_block_count;
start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
buf->f_type = F2FS_SUPER_MAGIC;
buf->f_bsize = sbi->blocksize;
buf->f_blocks = total_count - start_count;
buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
buf->f_bavail = user_block_count - valid_user_blocks(sbi);
buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
buf->f_ffree = buf->f_files - valid_inode_count(sbi);
buf->f_namelen = F2FS_NAME_LEN;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
return 0;
}
static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
{
if (struct_type == GC_THREAD)
return (unsigned char *)sbi->gc_thread;
else if (struct_type == SM_INFO)
return (unsigned char *)SM_I(sbi);
return NULL;
}
static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
{
if (struct_type == GC_THREAD)
return (unsigned char *)sbi->gc_thread;
else if (struct_type == SM_INFO)
return (unsigned char *)SM_I(sbi);
else if (struct_type == DCC_INFO)
return (unsigned char *)SM_I(sbi)->dcc_info;
else if (struct_type == NM_INFO)
return (unsigned char *)NM_I(sbi);
else if (struct_type == F2FS_SBI || struct_type == RESERVED_BLOCKS)
return (unsigned char *)sbi;
#ifdef CONFIG_F2FS_FAULT_INJECTION
else if (struct_type == FAULT_INFO_RATE ||
struct_type == FAULT_INFO_TYPE)
return (unsigned char *)&sbi->fault_info;
#endif
return NULL;
}
void sit_dump(struct f2fs_sb_info *sbi, int start_sit, int end_sit)
{
struct seg_entry *se;
int segno;
char buf[BUF_SZ];
u32 free_segs = 0;;
u64 valid_blocks = 0;
int ret;
int fd;
fd = open("dump_sit", O_CREAT|O_WRONLY|O_TRUNC, 0666);
ASSERT(fd >= 0);
for (segno = start_sit; segno < end_sit; segno++) {
se = get_seg_entry(sbi, segno);
memset(buf, 0, BUF_SZ);
snprintf(buf, BUF_SZ, "%5d %8d\n", segno, se->valid_blocks);
ret = write(fd, buf, strlen(buf));
ASSERT(ret >= 0);
DBG(4, "SIT[0x%3x] : 0x%x\n", segno, se->valid_blocks);
if (se->valid_blocks == 0x0) {
free_segs++;
} else {
ASSERT(se->valid_blocks <= 512);
valid_blocks += se->valid_blocks;
}
}
memset(buf, 0, BUF_SZ);
snprintf(buf, BUF_SZ, "valid_segs:%d\t free_segs:%d\n",
SM_I(sbi)->main_segments - free_segs, free_segs);
ret = write(fd, buf, strlen(buf));
ASSERT(ret >= 0);
close(fd);
DBG(1, "Blocks [0x%lx] Free Segs [0x%x]\n", valid_blocks, free_segs);
}
int fsck_init(struct f2fs_sb_info *sbi)
{
struct f2fs_fsck *fsck = F2FS_FSCK(sbi);
struct f2fs_sm_info *sm_i = SM_I(sbi);
/*
* We build three bitmap for main/sit/nat so that may check consistency of filesystem.
* 1. main_area_bitmap will be used to check whether all blocks of main area is used or not.
* 2. nat_area_bitmap has bitmap information of used nid in NAT.
* 3. sit_area_bitmap has bitmap information of used main block.
* At Last sequence, we compare main_area_bitmap with sit_area_bitmap.
*/
fsck->nr_main_blks = sm_i->main_segments << sbi->log_blocks_per_seg;
fsck->main_area_bitmap_sz = (fsck->nr_main_blks + 7) / 8;
fsck->main_area_bitmap = calloc(fsck->main_area_bitmap_sz, 1);
ASSERT(fsck->main_area_bitmap != NULL);
build_nat_area_bitmap(sbi);
build_sit_area_bitmap(sbi);
tree_mark = calloc(tree_mark_size, 1);
return 0;
}
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct f2fs_mount_info org_mount_opt;
int err, active_logs;
bool need_restart_gc = false;
bool need_stop_gc = false;
sync_filesystem(sb);
/*
* Save the old mount options in case we
* need to restore them.
*/
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
sbi->mount_opt.opt = 0;
default_options(sbi);
/* parse mount options */
err = parse_options(sb, data);
if (err)
goto restore_opts;
/*
* Previous and new state of filesystem is RO,
* so skip checking GC and FLUSH_MERGE conditions.
*/
if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
goto skip;
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
* option. Also sync the filesystem.
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
f2fs_sync_fs(sb, 1);
need_restart_gc = true;
}
} else if (!sbi->gc_thread) {
err = start_gc_thread(sbi);
if (err)
goto restore_opts;
need_stop_gc = true;
}
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
destroy_flush_cmd_control(sbi);
} else if (!SM_I(sbi)->cmd_control_info) {
err = create_flush_cmd_control(sbi);
if (err)
goto restore_gc;
}
skip:
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
return 0;
restore_gc:
if (need_restart_gc) {
if (start_gc_thread(sbi))
f2fs_msg(sbi->sb, KERN_WARNING,
"background gc thread has stopped");
} else if (need_stop_gc) {
stop_gc_thread(sbi);
}
restore_opts:
sbi->mount_opt = org_mount_opt;
sbi->active_logs = active_logs;
return err;
}
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
bool need_cp = false;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
if (unlikely(f2fs_readonly(inode->i_sb)))
return 0;
trace_f2fs_sync_file_enter(inode);
/* if fdatasync is triggered, let's do in-place-update */
if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(fi, FI_NEED_IPU);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
clear_inode_flag(fi, FI_NEED_IPU);
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
return ret;
}
/* if the inode is dirty, let's recover all the time */
if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) {
update_inode_page(inode);
goto go_write;
}
/*
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
!exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
go_write:
/* guarantee free sections for fsync */
f2fs_balance_fs(sbi);
/*
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
down_read(&fi->i_sem);
need_cp = need_do_checkpoint(inode);
up_read(&fi->i_sem);
if (need_cp) {
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
/*
* We've secured consistency through sync_fs. Following pino
* will be used only for fsynced inodes after checkpoint.
*/
try_to_fix_pino(inode);
clear_inode_flag(fi, FI_APPEND_WRITE);
clear_inode_flag(fi, FI_UPDATE_WRITE);
goto out;
}
sync_nodes:
sync_node_pages(sbi, ino, &wbc);
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi)))
goto out;
if (need_inode_block_update(sbi, ino)) {
mark_inode_dirty_sync(inode);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
ret = wait_on_node_pages_writeback(sbi, ino);
if (ret)
goto out;
/* once recovery info is written, don't need to tack this */
remove_dirty_inode(sbi, ino, APPEND_INO);
clear_inode_flag(fi, FI_APPEND_WRITE);
flush_out:
remove_dirty_inode(sbi, ino, UPDATE_INO);
clear_inode_flag(fi, FI_UPDATE_WRITE);
ret = f2fs_issue_flush(sbi);
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
f2fs_trace_ios(NULL, 1);
return ret;
}
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
struct pagevec pvec;
int nr_pages;
if (whence != SEEK_DATA)
return 0;
/* find first dirty page index */
pagevec_init(&pvec, 0);
nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
PAGECACHE_TAG_DIRTY, 1);
pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
pagevec_release(&pvec);
return pgofs;
}
static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
int whence)
{
switch (whence) {
case SEEK_DATA:
if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
return true;
break;
case SEEK_HOLE:
if (blkaddr == NULL_ADDR)
return true;
break;
}
return false;
}
static inline int unsigned_offsets(struct file *file)
{
return file->f_mode & FMODE_UNSIGNED_OFFSET;
}
static loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
{
if (offset < 0 && !unsigned_offsets(file))
return -EINVAL;
if (offset > maxsize)
return -EINVAL;
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
return offset;
}
static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
struct dnode_of_data dn;
pgoff_t pgofs, end_offset, dirty;
loff_t data_ofs = offset;
loff_t isize;
int err = 0;
mutex_lock(&inode->i_mutex);
isize = i_size_read(inode);
if (offset >= isize)
goto fail;
/* handle inline data case */
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
if (whence == SEEK_HOLE)
data_ofs = isize;
goto found;
}
pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
F2FS_I(inode));
continue;
} else {
goto found;
}
}
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
if (__found_offset(blkaddr, dirty, pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
}
}
f2fs_put_dnode(&dn);
}
if (whence == SEEK_DATA)
goto fail;
found:
if (whence == SEEK_HOLE && data_ofs > isize)
data_ofs = isize;
mutex_unlock(&inode->i_mutex);
return vfs_setpos(file, data_ofs, maxbytes);
fail:
mutex_unlock(&inode->i_mutex);
return -ENXIO;
}
static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
switch (whence) {
case SEEK_SET:
case SEEK_CUR:
case SEEK_END:
return generic_file_llseek_size(file, offset, whence,
maxbytes);
case SEEK_DATA:
case SEEK_HOLE:
if (offset < 0)
return -ENXIO;
return f2fs_seek_block(file, offset, whence);
}
return -EINVAL;
}
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
if (f2fs_encrypted_inode(inode)) {
int err = f2fs_get_encryption_info(inode);
if (err)
return 0;
}
/* we don't need to use inline_data strictly */
if (f2fs_has_inline_data(inode)) {
int err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
return 0;
}
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int ret = generic_file_open(inode, filp);
if (!ret && f2fs_encrypted_inode(inode)) {
ret = f2fs_get_encryption_info(inode);
if (ret)
ret = -EACCES;
}
return ret;
}
static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
struct f2fs_sb_info *sbi,
const char *buf, size_t count)
{
unsigned char *ptr;
unsigned long t;
unsigned int *ui;
ssize_t ret;
ptr = __struct_ptr(sbi, a->struct_type);
if (!ptr)
return -EINVAL;
ui = (unsigned int *)(ptr + a->offset);
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret < 0)
return ret;
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
return -EINVAL;
#endif
if (a->struct_type == RESERVED_BLOCKS) {
spin_lock(&sbi->stat_lock);
if ((unsigned long)sbi->total_valid_block_count + t >
(unsigned long)sbi->user_block_count) {
spin_unlock(&sbi->stat_lock);
return -EINVAL;
}
*ui = t;
spin_unlock(&sbi->stat_lock);
return count;
}
if (!strcmp(a->attr.name, "discard_granularity")) {
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
int i;
if (t == 0 || t > MAX_PLIST_NUM)
return -EINVAL;
if (t == *ui)
return count;
mutex_lock(&dcc->cmd_lock);
for (i = 0; i < MAX_PLIST_NUM; i++) {
if (i >= t - 1)
dcc->pend_list_tag[i] |= P_ACTIVE;
else
dcc->pend_list_tag[i] &= (~P_ACTIVE);
}
mutex_unlock(&dcc->cmd_lock);
*ui = t;
return count;
}
*ui = t;
if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0)
f2fs_reset_iostat(sbi);
if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && sbi->gc_thread) {
sbi->gc_thread->gc_wake = 1;
wake_up_interruptible_all(&sbi->gc_thread->gc_wait_queue_head);
wake_up_discard_thread(sbi, true);
}
return count;
}
int dump_info_from_blkaddr(struct f2fs_sb_info *sbi, u32 blk_addr)
{
nid_t nid;
int type;
struct f2fs_summary sum_entry;
struct node_info ni, ino_ni;
int ret = 0;
MSG(0, "\n== Dump data from block address ==\n\n");
if (blk_addr < SM_I(sbi)->seg0_blkaddr) {
MSG(0, "\nFS Reserved Area for SEG #0: ");
ret = -EINVAL;
} else if (blk_addr < SIT_I(sbi)->sit_base_addr) {
MSG(0, "\nFS Metadata Area: ");
ret = -EINVAL;
} else if (blk_addr < NM_I(sbi)->nat_blkaddr) {
MSG(0, "\nFS SIT Area: ");
ret = -EINVAL;
} else if (blk_addr < SM_I(sbi)->ssa_blkaddr) {
MSG(0, "\nFS NAT Area: ");
ret = -EINVAL;
} else if (blk_addr < SM_I(sbi)->main_blkaddr) {
MSG(0, "\nFS SSA Area: ");
ret = -EINVAL;
} else if (blk_addr > __end_block_addr(sbi)) {
MSG(0, "\nOut of address space: ");
ret = -EINVAL;
}
if (ret) {
MSG(0, "User data is from 0x%x to 0x%x\n\n",
SM_I(sbi)->main_blkaddr,
__end_block_addr(sbi));
return ret;
}
type = get_sum_entry(sbi, blk_addr, &sum_entry);
nid = le32_to_cpu(sum_entry.nid);
get_node_info(sbi, nid, &ni);
DBG(1, "Note: blkaddr = main_blkaddr + segno * 512 + offset\n");
DBG(1, "Block_addr [0x%x]\n", blk_addr);
DBG(1, " - Segno [0x%x]\n", GET_SEGNO(sbi, blk_addr));
DBG(1, " - Offset [0x%x]\n", OFFSET_IN_SEG(sbi, blk_addr));
DBG(1, "SUM.nid [0x%x]\n", nid);
DBG(1, "SUM.type [%s]\n", seg_type_name[type]);
DBG(1, "SUM.version [%d]\n", sum_entry.version);
DBG(1, "SUM.ofs_in_node [0x%x]\n", sum_entry.ofs_in_node);
DBG(1, "NAT.blkaddr [0x%x]\n", ni.blk_addr);
DBG(1, "NAT.ino [0x%x]\n", ni.ino);
get_node_info(sbi, ni.ino, &ino_ni);
/* inode block address */
if (ni.blk_addr == NULL_ADDR || ino_ni.blk_addr == NULL_ADDR) {
MSG(0, "FS Userdata Area: Obsolete block from 0x%x\n",
blk_addr);
return -EINVAL;
}
/* print inode */
if (config.dbg_lv > 0)
dump_node_from_blkaddr(ino_ni.blk_addr);
if (type == SEG_TYPE_CUR_DATA || type == SEG_TYPE_DATA) {
MSG(0, "FS Userdata Area: Data block from 0x%x\n", blk_addr);
MSG(0, " - Direct node block : id = 0x%x from 0x%x\n",
nid, ni.blk_addr);
MSG(0, " - Inode block : id = 0x%x from 0x%x\n",
ni.ino, ino_ni.blk_addr);
dump_node_from_blkaddr(ino_ni.blk_addr);
dump_data_offset(ni.blk_addr,
le16_to_cpu(sum_entry.ofs_in_node));
} else {
MSG(0, "FS Userdata Area: Node block from 0x%x\n", blk_addr);
if (ni.ino == ni.nid) {
MSG(0, " - Inode block : id = 0x%x from 0x%x\n",
ni.ino, ino_ni.blk_addr);
dump_node_from_blkaddr(ino_ni.blk_addr);
} else {
MSG(0, " - Node block : id = 0x%x from 0x%x\n",
nid, ni.blk_addr);
MSG(0, " - Inode block : id = 0x%x from 0x%x\n",
ni.ino, ino_ni.blk_addr);
dump_node_from_blkaddr(ino_ni.blk_addr);
dump_node_offset(ni.blk_addr);
}
}
return 0;
}
