static void __allocate_data_blocks(struct inode *inode, loff_t offset,
size_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
u64 start = F2FS_BYTES_TO_BLK(offset);
u64 len = F2FS_BYTES_TO_BLK(count);
bool allocated;
u64 end_offset;
while (len) {
f2fs_balance_fs(sbi);
f2fs_lock_op(sbi);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (get_dnode_of_data(&dn, start, ALLOC_NODE))
goto out;
allocated = false;
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
while (dn.ofs_in_node < end_offset && len) {
block_t blkaddr;
if (unlikely(f2fs_cp_error(sbi)))
goto sync_out;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
if (__allocate_data_block(&dn))
goto sync_out;
allocated = true;
}
len--;
start++;
dn.ofs_in_node++;
}
if (allocated)
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
}
return;
sync_out:
if (allocated)
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
out:
f2fs_unlock_op(sbi);
return;
}
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
int nr_free = 0, ofs = dn->ofs_in_node;
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
__le32 *addr;
raw_node = F2FS_NODE(dn->node_page);
addr = blkaddr_in_node(raw_node) + ofs;
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(F2FS_I(dn->inode),
FI_FIRST_BLOCK_WRITTEN);
nr_free++;
}
if (nr_free) {
dec_valid_block_count(sbi, dn->inode, nr_free);
set_page_dirty(dn->node_page);
sync_inode_page(dn);
}
dn->ofs_in_node = ofs;
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
return nr_free;
}
/*
* NOTE: ipage is grabbed by caller, but if any error occurs, we should
* release ipage in this function.
*/
static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
struct dnode_of_data dn;
struct f2fs_dentry_block *dentry_blk;
int err;
page = grab_cache_page(dir->i_mapping, 0);
if (!page) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
}
set_new_dnode(&dn, dir, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err)
goto out;
f2fs_wait_on_page_writeback(page, DATA);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
dentry_blk = kmap_atomic(page);
/* copy data from inline dentry block to new dentry block */
memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
INLINE_DENTRY_BITMAP_SIZE);
memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
/*
* we do not need to zero out remainder part of dentry and filename
* field, since we have used bitmap for marking the usage status of
* them, besides, we can also ignore copying/zeroing reserved space
* of dentry block, because them haven't been used so far.
*/
memcpy(dentry_blk->dentry, inline_dentry->dentry,
sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
memcpy(dentry_blk->filename, inline_dentry->filename,
NR_INLINE_DENTRY * F2FS_SLOT_LEN);
kunmap_atomic(dentry_blk);
SetPageUptodate(page);
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
truncate_inline_inode(ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
if (i_size_read(dir) < PAGE_CACHE_SIZE) {
i_size_write(dir, PAGE_CACHE_SIZE);
set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
sync_inode_page(&dn);
out:
f2fs_put_page(page, 1);
return err;
}
static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
struct dnode_of_data dn;
struct f2fs_dentry_block *dentry_blk;
int err;
page = grab_cache_page(dir->i_mapping, 0);
if (!page)
return -ENOMEM;
set_new_dnode(&dn, dir, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err)
goto out;
f2fs_wait_on_page_writeback(page, DATA);
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
dentry_blk = kmap_atomic(page);
/* copy data from inline dentry block to new dentry block */
memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
INLINE_DENTRY_BITMAP_SIZE);
memcpy(dentry_blk->dentry, inline_dentry->dentry,
sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
memcpy(dentry_blk->filename, inline_dentry->filename,
NR_INLINE_DENTRY * F2FS_SLOT_LEN);
kunmap_atomic(dentry_blk);
SetPageUptodate(page);
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
truncate_inline_inode(ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
if (i_size_read(dir) < PAGE_CACHE_SIZE) {
i_size_write(dir, PAGE_CACHE_SIZE);
set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
sync_inode_page(&dn);
out:
f2fs_put_page(page, 1);
return err;
}
int reserve_new_block(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
return -ENOSPC;
trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
dn->data_blkaddr = NEW_ADDR;
set_data_blkaddr(dn);
mark_inode_dirty(dn->inode);
sync_inode_page(dn);
return 0;
}
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
raw_node = F2FS_NODE(dn->node_page);
addr = blkaddr_in_node(raw_node) + ofs;
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
set_data_blkaddr(dn);
invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(F2FS_I(dn->inode),
FI_FIRST_BLOCK_WRITTEN);
nr_free++;
}
if (nr_free) {
pgoff_t fofs;
/*
* once we invalidate valid blkaddr in range [ofs, ofs + count],
* we will invalidate all blkaddr in the whole range.
*/
fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
F2FS_I(dn->inode)) + ofs;
f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
set_page_dirty(dn->node_page);
sync_inode_page(dn);
}
dn->ofs_in_node = ofs;
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
return nr_free;
}
static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
{
int err;
struct page *ipage;
struct dnode_of_data dn;
void *src_addr, *dst_addr;
block_t new_blk_addr;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct f2fs_io_info fio = {
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
};
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
/*
* i_addr[0] is not used for inline data,
* so reserving new block will not destroy inline data
*/
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err) {
f2fs_unlock_op(sbi);
return err;
}
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
dst_addr = kmap(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap(page);
SetPageUptodate(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
write_data_page(page, &dn, &new_blk_addr, &fio);
update_extent_cache(new_blk_addr, &dn);
f2fs_wait_on_page_writeback(page, DATA);
/* clear inline data and flag after data writeback */
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
stat_dec_inline_inode(inode);
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
return err;
}
int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size)
{
struct page *page;
int err;
if (!f2fs_has_inline_data(inode))
return 0;
else if (to_size <= MAX_INLINE_DATA)
return 0;
page = grab_cache_page_write_begin(inode->i_mapping, 0, AOP_FLAG_NOFS);
if (!page)
return -ENOMEM;
err = __f2fs_convert_inline_data(inode, page);
f2fs_put_page(page, 1);
return err;
}
int f2fs_write_inline_data(struct inode *inode,
struct page *page, unsigned size)
{
void *src_addr, *dst_addr;
struct page *ipage;
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
ipage = dn.inode_page;
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
src_addr = kmap(page);
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, size);
kunmap(page);
/* Release the first data block if it is allocated */
if (!f2fs_has_inline_data(inode)) {
truncate_data_blocks_range(&dn, 1);
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
stat_inc_inline_inode(inode);
}
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
return 0;
}
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
void *src_addr, *dst_addr;
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_wait_on_page_writeback(page, DATA);
if (PageUptodate(page))
goto no_update;
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(dn->inode_page);
dst_addr = kmap_atomic(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
flush_dcache_page(page);
kunmap_atomic(dst_addr);
SetPageUptodate(page);
no_update:
set_page_dirty(page);
/* clear dirty state */
dirty = clear_page_dirty_for_io(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
fio.blk_addr = dn->data_blkaddr;
write_data_page(dn, &fio);
set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
f2fs_wait_on_page_writeback(page, DATA);
if (dirty)
inode_dec_dirty_pages(dn->inode);
/* this converted inline_data should be recovered. */
set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode_page, 0);
clear_out:
stat_dec_inline_inode(dn->inode);
f2fs_clear_inline_inode(dn->inode);
sync_inode_page(dn);
f2fs_put_dnode(dn);
return 0;
}
int f2fs_convert_inline_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct page *ipage, *page;
int err = 0;
page = grab_cache_page(inode->i_mapping, 0);
if (!page)
return -ENOMEM;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode))
err = f2fs_convert_inline_page(&dn, page);
f2fs_put_dnode(&dn);
out:
f2fs_unlock_op(sbi);
f2fs_put_page(page, 1);
return err;
}
int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
if (!f2fs_has_inline_data(inode)) {
f2fs_put_dnode(&dn);
return -EAGAIN;
}
f2fs_bug_on(F2FS_I_SB(inode), page->index);
f2fs_wait_on_page_writeback(dn.inode_page, NODE);
src_addr = kmap_atomic(page);
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap_atomic(src_addr);
set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
return 0;
}
/*
* f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
* f2fs_map_blocks structure.
* If original data blocks are allocated, then give them to blockdev.
* Otherwise,
* a. preallocate requested block addresses
* b. do not use extent cache for better performance
* c. give the block addresses to blockdev
*/
static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag)
{
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
pgoff_t pgofs, end_offset;
int err = 0, ofs = 1;
struct extent_info ei;
bool allocated = false;
map->m_len = 0;
map->m_flags = 0;
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
map->m_pblk = ei.blk + pgofs - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
map->m_flags = F2FS_MAP_MAPPED;
goto out;
}
if (create)
f2fs_lock_op(F2FS_I_SB(inode));
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (err == -ENOENT)
err = 0;
goto unlock_out;
}
if (dn.data_blkaddr == NEW_ADDR) {
if (flag == F2FS_GET_BLOCK_BMAP) {
err = -ENOENT;
goto put_out;
} else if (flag == F2FS_GET_BLOCK_READ ||
flag == F2FS_GET_BLOCK_DIO) {
goto put_out;
}
/*
* if it is in fiemap call path (flag = F2FS_GET_BLOCK_FIEMAP),
* mark it as mapped and unwritten block.
*/
}
if (dn.data_blkaddr != NULL_ADDR) {
map->m_flags = F2FS_MAP_MAPPED;
map->m_pblk = dn.data_blkaddr;
if (dn.data_blkaddr == NEW_ADDR)
map->m_flags |= F2FS_MAP_UNWRITTEN;
} else if (create) {
err = __allocate_data_block(&dn);
if (err)
goto put_out;
allocated = true;
map->m_flags = F2FS_MAP_NEW | F2FS_MAP_MAPPED;
map->m_pblk = dn.data_blkaddr;
} else {
if (flag == F2FS_GET_BLOCK_BMAP)
err = -ENOENT;
goto put_out;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
map->m_len = 1;
dn.ofs_in_node++;
pgofs++;
get_next:
if (dn.ofs_in_node >= end_offset) {
if (allocated)
sync_inode_page(&dn);
allocated = false;
f2fs_put_dnode(&dn);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (err == -ENOENT)
err = 0;
goto unlock_out;
}
if (dn.data_blkaddr == NEW_ADDR &&
flag != F2FS_GET_BLOCK_FIEMAP)
goto put_out;
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
}
if (maxblocks > map->m_len) {
block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
if (blkaddr == NULL_ADDR && create) {
err = __allocate_data_block(&dn);
if (err)
goto sync_out;
allocated = true;
map->m_flags |= F2FS_MAP_NEW;
blkaddr = dn.data_blkaddr;
}
/* Give more consecutive addresses for the readahead */
if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
(map->m_pblk == NEW_ADDR &&
blkaddr == NEW_ADDR)) {
ofs++;
dn.ofs_in_node++;
pgofs++;
map->m_len++;
goto get_next;
}
}
sync_out:
if (allocated)
sync_inode_page(&dn);
put_out:
f2fs_put_dnode(&dn);
unlock_out:
if (create)
f2fs_unlock_op(F2FS_I_SB(inode));
out:
trace_f2fs_map_blocks(inode, map, err);
return err;
}
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
struct page *ipage;
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
int err = 0;
trace_f2fs_write_begin(inode, pos, len, flags);
f2fs_balance_fs(sbi);
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
* lock_page(page #0) -> lock_page(inode_page)
*/
if (index != 0) {
err = f2fs_convert_inline_inode(inode);
if (err)
goto fail;
}
repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
err = -ENOMEM;
goto fail;
}
*pagep = page;
f2fs_lock_op(sbi);
/* check inline_data */
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_fail;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA) {
read_inline_data(page, ipage);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
goto put_next;
}
err = f2fs_convert_inline_page(&dn, page);
if (err)
goto put_fail;
}
err = f2fs_get_block(&dn, index);
if (err)
goto put_fail;
put_next:
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
f2fs_wait_on_page_writeback(page, DATA);
if (len == PAGE_CACHE_SIZE)
goto out_update;
if (PageUptodate(page))
goto out_clear;
if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
unsigned start = pos & (PAGE_CACHE_SIZE - 1);
unsigned end = start + len;
/* Reading beyond i_size is simple: memset to zero */
zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
goto out_update;
}
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
struct f2fs_io_info fio = {
.sbi = sbi,
.type = DATA,
.rw = READ_SYNC,
.blk_addr = dn.data_blkaddr,
.page = page,
.encrypted_page = NULL,
};
err = f2fs_submit_page_bio(&fio);
if (err)
goto fail;
lock_page(page);
if (unlikely(!PageUptodate(page))) {
err = -EIO;
goto fail;
}
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
/* avoid symlink page */
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
err = f2fs_decrypt_one(inode, page);
if (err)
goto fail;
}
}
out_update:
SetPageUptodate(page);
out_clear:
clear_cold_data(page);
return 0;
put_fail:
f2fs_put_dnode(&dn);
unlock_fail:
f2fs_unlock_op(sbi);
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
return err;
}
static int f2fs_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
trace_f2fs_write_end(inode, pos, len, copied);
set_page_dirty(page);
if (pos + copied > i_size_read(inode)) {
i_size_write(inode, pos + copied);
mark_inode_dirty(inode);
update_inode_page(inode);
}
f2fs_put_page(page, 1);
return copied;
}
static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
loff_t offset)
{
unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
if (offset & blocksize_mask)
return -EINVAL;
if (iov_iter_alignment(iter) & blocksize_mask)
return -EINVAL;
return 0;
}
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);
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, 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, i_size_read(inode));
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);
/* 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;
}
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
int nr_free = 0, ofs = dn->ofs_in_node;
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
__le32 *addr;
raw_node = F2FS_NODE(dn->node_page);
addr = blkaddr_in_node(raw_node) + ofs;
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
update_extent_cache(dn);
invalidate_blocks(sbi, blkaddr);
nr_free++;
}
if (nr_free) {
dec_valid_block_count(sbi, dn->inode, nr_free);
set_page_dirty(dn->node_page);
sync_inode_page(dn);
}
dn->ofs_in_node = ofs;
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
return nr_free;
}
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
struct page *ipage;
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
int err = 0;
trace_f2fs_write_begin(inode, pos, len, flags);
f2fs_balance_fs(sbi);
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
* lock_page(page #0) -> lock_page(inode_page)
*/
if (index != 0) {
err = f2fs_convert_inline_inode(inode);
if (err)
goto fail;
}
repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
err = -ENOMEM;
goto fail;
}
*pagep = page;
f2fs_lock_op(sbi);
/* check inline_data */
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_fail;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA) {
read_inline_data(page, ipage);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
goto put_next;
}
err = f2fs_convert_inline_page(&dn, page);
if (err)
goto put_fail;
}
err = f2fs_get_block(&dn, index);
if (err)
goto put_fail;
put_next:
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
f2fs_wait_on_page_writeback(page, DATA);
if (len == PAGE_CACHE_SIZE)
goto out_update;
if (PageUptodate(page))
goto out_clear;
if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
unsigned start = pos & (PAGE_CACHE_SIZE - 1);
unsigned end = start + len;
/* Reading beyond i_size is simple: memset to zero */
zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
goto out_update;
}
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
struct f2fs_io_info fio = {
.sbi = sbi,
.type = DATA,
.rw = READ_SYNC,
.blk_addr = dn.data_blkaddr,
.page = page,
.encrypted_page = NULL,
};
err = f2fs_submit_page_bio(&fio);
if (err)
goto fail;
lock_page(page);
if (unlikely(!PageUptodate(page))) {
err = -EIO;
goto fail;
}
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
/* avoid symlink page */
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
err = f2fs_decrypt_one(inode, page);
if (err)
goto fail;
}
}
out_update:
SetPageUptodate(page);
out_clear:
clear_cold_data(page);
return 0;
put_fail:
f2fs_put_dnode(&dn);
unlock_fail:
f2fs_unlock_op(sbi);
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
return err;
}
static int f2fs_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
trace_f2fs_write_end(inode, pos, len, copied);
set_page_dirty(page);
if (pos + copied > i_size_read(inode)) {
i_size_write(inode, pos + copied);
mark_inode_dirty(inode);
update_inode_page(inode);
}
f2fs_put_page(page, 1);
return copied;
}
static ssize_t check_direct_IO(struct inode *inode, int rw,
const struct iovec *iov, loff_t offset, unsigned long nr_segs)
{
unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
int seg, i;
size_t size;
unsigned long addr;
ssize_t retval = -EINVAL;
loff_t end = offset;
if (offset & blocksize_mask)
return -EINVAL;
/* Check the memory alignment. Blocks cannot straddle pages */
for (seg = 0; seg < nr_segs; seg++) {
addr = (unsigned long)iov[seg].iov_base;
size = iov[seg].iov_len;
end += size;
if ((addr & blocksize_mask) || (size & blocksize_mask))
goto out;
/* If this is a write we don't need to check anymore */
if (rw & WRITE)
continue;
/*
* Check to make sure we don't have duplicate iov_base's in this
* iovec, if so return EINVAL, otherwise we'll get csum errors
* when reading back.
*/
for (i = seg + 1; i < nr_segs; i++) {
if (iov[seg].iov_base == iov[i].iov_base)
goto out;
}
}
retval = 0;
out:
return retval;
}
