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_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
int err;
while (pg_start < pg_end) {
struct dnode_of_data dn;
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
if (err == -ENOENT) {
pg_start++;
continue;
}
return err;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
pg_start += count;
}
return 0;
}
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int err;
f2fs_balance_fs(sbi);
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
/* block allocation */
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_reserve_block(&dn, page->index);
if (err) {
f2fs_unlock_op(sbi);
goto out;
}
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
file_update_time(vma->vm_file);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page))) {
unlock_page(page);
err = -EFAULT;
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
/* page is wholly or partially inside EOF */
if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
unsigned offset;
offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
}
set_page_dirty(page);
SetPageUptodate(page);
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
/* fill the page */
f2fs_wait_on_page_writeback(page, DATA);
/* if gced page is attached, don't write to cold segment */
clear_cold_data(page);
out:
return block_page_mkwrite_return(err);
}
int truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int blocksize = inode->i_sb->s_blocksize;
struct dnode_of_data dn;
pgoff_t free_from;
int count = 0, err = 0;
struct page *ipage;
trace_f2fs_truncate_blocks_enter(inode, from);
free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
if (lock)
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
if (f2fs_has_inline_data(inode)) {
f2fs_put_page(ipage, 1);
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
if (err) {
if (err == -ENOENT)
goto free_next;
goto out;
}
count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
count -= dn.ofs_in_node;
f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
truncate_data_blocks_range(&dn, count);
free_from += count;
}
f2fs_put_dnode(&dn);
free_next:
err = truncate_inode_blocks(inode, free_from);
out:
if (lock)
f2fs_unlock_op(sbi);
/* lastly zero out the first data page */
if (!err)
err = truncate_partial_data_page(inode, from);
trace_f2fs_truncate_blocks_exit(inode, err);
return err;
}
int do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
return err;
fio->blk_addr = dn.data_blkaddr;
/* This page is already truncated */
if (fio->blk_addr == NULL_ADDR) {
ClearPageUptodate(page);
goto out_writepage;
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
fio->encrypted_page = f2fs_encrypt(inode, fio->page);
if (IS_ERR(fio->encrypted_page)) {
err = PTR_ERR(fio->encrypted_page);
goto out_writepage;
}
}
set_page_writeback(page);
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
if (unlikely(fio->blk_addr != NEW_ADDR &&
!is_cold_data(page) &&
need_inplace_update(inode))) {
rewrite_data_page(fio);
set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
trace_f2fs_do_write_data_page(page, IPU);
} else {
write_data_page(&dn, fio);
set_data_blkaddr(&dn);
f2fs_update_extent_cache(&dn);
trace_f2fs_do_write_data_page(page, OPU);
set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
if (page->index == 0)
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
}
out_writepage:
f2fs_put_dnode(&dn);
return err;
}
/*
* Caller ensures that this data page is never allocated.
* A new zero-filled data page is allocated in the page cache.
*
* Also, caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
* Note that, ipage is set only by make_empty_dir, and if any error occur,
* ipage should be released by this function.
*/
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
int err;
repeat:
page = grab_cache_page(mapping, index);
if (!page) {
/*
* before exiting, we should make sure ipage will be released
* if any error occur.
*/
f2fs_put_page(ipage, 1);
return ERR_PTR(-ENOMEM);
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, index);
if (err) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
if (!ipage)
f2fs_put_dnode(&dn);
if (PageUptodate(page))
goto got_it;
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
} else {
f2fs_put_page(page, 1);
page = get_read_data_page(inode, index, READ_SYNC);
if (IS_ERR(page))
goto repeat;
/* wait for read completion */
lock_page(page);
}
got_it:
if (new_i_size &&
i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
/* Only the directory inode sets new_i_size */
set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
}
return page;
}
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
int err;
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
err = reserve_new_block(dn);
if (err || need_put)
f2fs_put_dnode(dn);
return err;
}
int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
pgoff_t index;
int err;
for (index = pg_start; index < pg_end; index++) {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err) {
if (err == -ENOENT)
continue;
return err;
}
if (dn.data_blkaddr != NULL_ADDR)
truncate_data_blocks_range(&dn, 1);
f2fs_put_dnode(&dn);
}
return 0;
}
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;
}
/*
* 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 __exchange_data_block(struct inode *inode, pgoff_t src,
pgoff_t dst, bool full)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
block_t new_addr;
bool do_replace = false;
int ret;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
return ret;
} else if (ret == -ENOENT) {
new_addr = NULL_ADDR;
} else {
new_addr = dn.data_blkaddr;
if (!is_checkpointed_data(sbi, new_addr)) {
dn.data_blkaddr = NULL_ADDR;
/* do not invalidate this block address */
set_data_blkaddr(&dn);
f2fs_update_extent_cache(&dn);
do_replace = true;
}
f2fs_put_dnode(&dn);
}
if (new_addr == NULL_ADDR)
return full ? truncate_hole(inode, dst, dst + 1) : 0;
if (do_replace) {
struct page *ipage = get_node_page(sbi, inode->i_ino);
struct node_info ni;
if (IS_ERR(ipage)) {
ret = PTR_ERR(ipage);
goto err_out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
ret = f2fs_reserve_block(&dn, dst);
if (ret)
goto err_out;
truncate_data_blocks_range(&dn, 1);
get_node_info(sbi, dn.nid, &ni);
f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
ni.version, true);
f2fs_put_dnode(&dn);
} else {
struct page *psrc, *pdst;
psrc = get_lock_data_page(inode, src, true);
if (IS_ERR(psrc))
return PTR_ERR(psrc);
pdst = get_new_data_page(inode, NULL, dst, false);
if (IS_ERR(pdst)) {
f2fs_put_page(psrc, 1);
return PTR_ERR(pdst);
}
f2fs_copy_page(psrc, pdst);
set_page_dirty(pdst);
f2fs_put_page(pdst, 1);
f2fs_put_page(psrc, 1);
return truncate_hole(inode, src, src + 1);
}
return 0;
err_out:
if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
dn.data_blkaddr = new_addr;
set_data_blkaddr(&dn);
f2fs_update_extent_cache(&dn);
f2fs_put_dnode(&dn);
}
return ret;
}
struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
struct extent_info ei;
int err;
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.type = DATA,
.rw = rw,
.encrypted_page = NULL,
};
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return read_mapping_page(mapping, index, NULL);
page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
goto got_it;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
goto put_err;
f2fs_put_dnode(&dn);
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
err = -ENOENT;
goto put_err;
}
got_it:
if (PageUptodate(page)) {
unlock_page(page);
return page;
}
/*
* A new dentry page is allocated but not able to be written, since its
* new inode page couldn't be allocated due to -ENOSPC.
* In such the case, its blkaddr can be remained as NEW_ADDR.
* see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
unlock_page(page);
return page;
}
fio.blk_addr = dn.data_blkaddr;
fio.page = page;
err = f2fs_submit_page_bio(&fio);
if (err)
goto put_err;
return page;
put_err:
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = REQ_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
read_inline_data(page, dn->inode_page);
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.old_blkaddr = dn->data_blkaddr;
set_inode_flag(dn->inode, FI_HOT_DATA);
write_data_page(dn, &fio);
f2fs_wait_on_page_writeback(page, DATA, true);
if (dirty) {
inode_dec_dirty_pages(dn->inode);
remove_dirty_inode(dn->inode);
}
/* this converted inline_data should be recovered. */
set_inode_flag(dn->inode, FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode, dn->inode_page, 0);
clear_inline_node(dn->inode_page);
clear_out:
stat_dec_inline_inode(dn->inode);
clear_inode_flag(dn->inode, FI_INLINE_DATA);
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;
if (!f2fs_has_inline_data(inode))
return 0;
page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
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);
f2fs_balance_fs(sbi, dn.node_changed);
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, true);
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_page_dirty(dn.inode_page);
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
clear_inline_node(dn.inode_page);
f2fs_put_dnode(&dn);
return 0;
}
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;
}
static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
int ret = 0;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
f2fs_balance_fs(sbi);
if (f2fs_has_inline_data(inode)) {
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
}
ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
if (ret)
return ret;
truncate_pagecache_range(inode, offset, offset + len - 1);
pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
off_start = offset & (PAGE_CACHE_SIZE - 1);
off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
return ret;
if (offset + len > new_size)
new_size = offset + len;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_CACHE_SIZE - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size,
pg_start << PAGE_CACHE_SHIFT);
}
for (index = pg_start; index < pg_end; index++) {
struct dnode_of_data dn;
struct page *ipage;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
ret = PTR_ERR(ipage);
f2fs_unlock_op(sbi);
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
ret = f2fs_reserve_block(&dn, index);
if (ret) {
f2fs_unlock_op(sbi);
goto out;
}
if (dn.data_blkaddr != NEW_ADDR) {
invalidate_blocks(sbi, dn.data_blkaddr);
dn.data_blkaddr = NEW_ADDR;
set_data_blkaddr(&dn);
dn.data_blkaddr = NULL_ADDR;
f2fs_update_extent_cache(&dn);
}
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
new_size = max_t(loff_t, new_size,
(index + 1) << PAGE_CACHE_SHIFT);
}
if (off_end) {
ret = fill_zero(inode, pg_end, 0, off_end);
if (ret)
goto out;
new_size = max_t(loff_t, new_size, offset + len);
}
}
out:
if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
update_inode_page(inode);
}
return ret;
}
static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t pg_start, pg_end, delta, nrpages, idx;
loff_t new_size;
int ret;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
new_size = i_size_read(inode) + len;
if (new_size > inode->i_sb->s_maxbytes)
return -EFBIG;
if (offset >= i_size_read(inode))
return -EINVAL;
/* insert range should be aligned to block size of f2fs. */
if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
return -EINVAL;
f2fs_balance_fs(sbi);
if (f2fs_has_inline_data(inode)) {
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
}
ret = truncate_blocks(inode, i_size_read(inode), true);
if (ret)
return ret;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
return ret;
truncate_pagecache(inode, 0, offset);
pg_start = offset >> PAGE_CACHE_SHIFT;
pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
delta = pg_end - pg_start;
nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) {
struct dnode_of_data dn;
struct page *ipage;
block_t new_addr, old_addr;
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, idx, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
goto out;
} else if (ret == -ENOENT) {
goto next;
} else if (dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
goto next;
} else {
new_addr = dn.data_blkaddr;
truncate_data_blocks_range(&dn, 1);
f2fs_put_dnode(&dn);
}
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
ret = PTR_ERR(ipage);
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
ret = f2fs_reserve_block(&dn, idx + delta);
if (ret)
goto out;
old_addr = dn.data_blkaddr;
f2fs_bug_on(sbi, old_addr != NEW_ADDR);
if (new_addr != NEW_ADDR) {
struct node_info ni;
get_node_info(sbi, dn.nid, &ni);
f2fs_replace_block(sbi, &dn, old_addr, new_addr,
ni.version, true);
}
f2fs_put_dnode(&dn);
next:
f2fs_unlock_op(sbi);
}
i_size_write(inode, new_size);
return 0;
out:
f2fs_unlock_op(sbi);
return ret;
}
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;
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
block_t blkaddr, struct dnode_of_data *dn)
{
struct seg_entry *sentry;
unsigned int segno = GET_SEGNO(sbi, blkaddr);
unsigned short blkoff = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
struct f2fs_summary_block *sum_node;
struct f2fs_summary sum;
struct page *sum_page, *node_page;
struct dnode_of_data tdn = *dn;
nid_t ino, nid;
struct inode *inode;
unsigned int offset;
block_t bidx;
int i;
sentry = get_seg_entry(sbi, segno);
if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
return 0;
/* Get the previous summary */
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
if (curseg->segno == segno) {
sum = curseg->sum_blk->entries[blkoff];
goto got_it;
}
}
sum_page = f2fs_get_sum_page(sbi, segno);
if (IS_ERR(sum_page))
return PTR_ERR(sum_page);
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
sum = sum_node->entries[blkoff];
f2fs_put_page(sum_page, 1);
got_it:
/* Use the locked dnode page and inode */
nid = le32_to_cpu(sum.nid);
if (dn->inode->i_ino == nid) {
tdn.nid = nid;
if (!dn->inode_page_locked)
lock_page(dn->inode_page);
tdn.node_page = dn->inode_page;
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
} else if (dn->nid == nid) {
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
}
/* Get the node page */
node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
offset = ofs_of_node(node_page);
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
if (ino != dn->inode->i_ino) {
int ret;
/* Deallocate previous index in the node page */
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
ret = dquot_initialize(inode);
if (ret) {
iput(inode);
return ret;
}
} else {
inode = dn->inode;
}
bidx = f2fs_start_bidx_of_node(offset, inode) +
le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
* count keeps alive.
*/
if (ino == dn->inode->i_ino && dn->inode_page_locked)
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
f2fs_truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
if (ino != dn->inode->i_ino)
iput(inode);
else if (dn->inode_page_locked)
lock_page(dn->inode_page);
return 0;
truncate_out:
if (datablock_addr(tdn.inode, tdn.node_page,
tdn.ofs_in_node) == blkaddr)
f2fs_truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
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);
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 int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page)
{
struct dnode_of_data dn;
struct node_info ni;
unsigned int start, end;
int err = 0, recovered = 0;
/* step 1: recover xattr */
if (IS_INODE(page)) {
f2fs_recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = f2fs_recover_xattr_data(inode, page);
if (!err)
recovered++;
goto out;
}
/* step 2: recover inline data */
if (f2fs_recover_inline_data(inode, page))
goto out;
/* step 3: recover data indices */
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
retry_dn:
err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_dn;
}
goto out;
}
f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
err = f2fs_get_node_info(sbi, dn.nid, &ni);
if (err)
goto err;
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
f2fs_msg(sbi->sb, KERN_WARNING,
"Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
inode->i_ino, ofs_of_node(dn.node_page),
ofs_of_node(page));
err = -EFAULT;
goto err;
}
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
if (__is_valid_data_blkaddr(src) &&
!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
err = -EFAULT;
goto err;
}
if (__is_valid_data_blkaddr(dest) &&
!f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
err = -EFAULT;
goto err;
}
/* skip recovering if dest is the same as src */
if (src == dest)
continue;
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
f2fs_truncate_data_blocks_range(&dn, 1);
continue;
}
if (!file_keep_isize(inode) &&
(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
f2fs_i_size_write(inode,
(loff_t)(start + 1) << PAGE_SHIFT);
/*
* dest is reserved block, invalidate src block
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
f2fs_truncate_data_blocks_range(&dn, 1);
f2fs_reserve_new_block(&dn);
continue;
}
/* dest is valid block, try to recover from src to dest */
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = f2fs_reserve_new_block(&dn);
while (err &&
IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION))
err = f2fs_reserve_new_block(&dn);
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
if (err)
goto err;
}
retry_prev:
/* Check the previous node page having this index */
err = check_index_in_prev_nodes(sbi, dest, &dn);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_prev;
}
goto err;
}
/* write dummy data page */
f2fs_replace_block(sbi, &dn, src, dest,
ni.version, false, false);
recovered++;
}
}
copy_node_footer(dn.node_page, page);
fill_node_footer(dn.node_page, dn.nid, ni.ino,
ofs_of_node(page), false);
set_page_dirty(dn.node_page);
err:
f2fs_put_dnode(&dn);
out:
f2fs_msg(sbi->sb, KERN_NOTICE,
"recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
inode->i_ino,
file_keep_isize(inode) ? "keep" : "recover",
recovered, err);
return err;
}
static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
int ret = 0;
for (; end < nrpages; start++, end++) {
block_t new_addr, old_addr;
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, end, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
goto out;
} else if (ret == -ENOENT) {
new_addr = NULL_ADDR;
} else {
new_addr = dn.data_blkaddr;
truncate_data_blocks_range(&dn, 1);
f2fs_put_dnode(&dn);
}
if (new_addr == NULL_ADDR) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = get_dnode_of_data(&dn, start, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
goto out;
} else if (ret == -ENOENT) {
f2fs_unlock_op(sbi);
continue;
}
if (dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
continue;
} else {
truncate_data_blocks_range(&dn, 1);
}
f2fs_put_dnode(&dn);
} else {
struct page *ipage;
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
ret = PTR_ERR(ipage);
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
ret = f2fs_reserve_block(&dn, start);
if (ret)
goto out;
old_addr = dn.data_blkaddr;
if (old_addr != NEW_ADDR && new_addr == NEW_ADDR) {
dn.data_blkaddr = NULL_ADDR;
f2fs_update_extent_cache(&dn);
invalidate_blocks(sbi, old_addr);
dn.data_blkaddr = new_addr;
set_data_blkaddr(&dn);
} else if (new_addr != NEW_ADDR) {
struct node_info ni;
get_node_info(sbi, dn.nid, &ni);
f2fs_replace_block(sbi, &dn, old_addr, new_addr,
ni.version, true);
}
f2fs_put_dnode(&dn);
}
f2fs_unlock_op(sbi);
}
return 0;
out:
f2fs_unlock_op(sbi);
return ret;
}
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;
}
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
block_t old_blk_addr;
struct dnode_of_data dn;
int err, ilock;
f2fs_balance_fs(sbi);
/* F2FS backport: We replace in old kernels sb_start_pagefault(inode->i_sb) with vfs_check_frozen()
* and remove the original sb_end_pagefault(inode->i_sb) after the out label
*
* The introduction of sb_{start,end}_pagefault() was made post-3.2 kernels by Jan Kara
* and merged in commit a0e881b7c189fa2bd76c024dbff91e79511c971d.
* Discussed at https://lkml.org/lkml/2012/3/5/278
*
* - Alex
*/
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* block allocation */
ilock = mutex_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, page->index, ALLOC_NODE);
if (err) {
mutex_unlock_op(sbi, ilock);
goto out;
}
old_blk_addr = dn.data_blkaddr;
if (old_blk_addr == NULL_ADDR) {
err = reserve_new_block(&dn);
if (err) {
f2fs_put_dnode(&dn);
mutex_unlock_op(sbi, ilock);
goto out;
}
}
f2fs_put_dnode(&dn);
mutex_unlock_op(sbi, ilock);
file_update_time(vma->vm_file);
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page)) {
unlock_page(page);
err = -EFAULT;
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
/* page is wholly or partially inside EOF */
if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
unsigned offset;
offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
}
set_page_dirty(page);
SetPageUptodate(page);
mapped:
/* fill the page */
wait_on_page_writeback(page);
out:
return block_page_mkwrite_return(err);
}