/**ltl
功能:遍历给定地址空间的"脏"页面，写这些页面
参数:
返回值:
说明:
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;/*要冲刷页面的索引*/
pgoff_t end; /* Inclusive *//*冲刷最后一个页面的索引，-1表示要循环冲刷*/
pgoff_t done_index;
int cycled;/*主要用在回绕需要分成两段进行冲刷的情况下，为1表示前一段冲刷已经完成。*/
int range_whole = 0;
int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic)
{//是否要循环进行冲刷
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
}
else
{
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end))
{
int i;
/*在地址空间中查找设备了PAGECACHE_TAG_DIRTY标志的页面，将结果保存在pagevec中*/
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
//对找到的页面进行处理。
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
//页面加锁
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
/*由于在加锁过程中可能其它进程对页面做过改动，因此要做以下判断*/
if (unlikely(page->mapping != mapping)) {//页面无效
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {//页面回写完成，I_DIRTY标志已经清除。
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {//页面正在回写中，那要根据sync_mode采取策略
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);//要等待正在回写完成后才继续
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
trace_wbc_writepage(wbc, mapping->backing_dev_info);
//开始回写"脏"页面
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
/*页面写成功后，递减计数器*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
/*printk(KERN_ALERT "in writepage() \n");*/
BUG_ON(!PageUptodate(page));
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
/* all is well */
/* lower mtimes have changed: update ours */
/* fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
*/
out_release:
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
return 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;
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
return !TestSetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_DIRTIED);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
EXPORT_SYMBOL(account_page_dirtied);
/*
* Helper function for set_page_writeback family.
* NOTE: Unlike account_page_dirtied this does not rely on being atomic
* wrt interrupts.
*/
void account_page_writeback(struct page *page)
{
inc_zone_page_state(page, NR_WRITEBACK);
inc_zone_page_state(page, NR_WRITTEN);
}
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
spin_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
static int gfs2_write_jdata_pagevec(struct address_space *mapping,
struct writeback_control *wbc,
struct pagevec *pvec,
int nr_pages, pgoff_t end,
pgoff_t *done_index)
{
struct inode *inode = mapping->host;
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
int i;
int ret;
ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
if (ret < 0)
return ret;
for(i = 0; i < nr_pages; i++) {
struct page *page = pvec->pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
ret = 1;
break;
}
*done_index = page->index;
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
trace_wbc_writepage(wbc, inode_to_bdi(inode));
ret = __gfs2_jdata_writepage(page, wbc);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
*done_index = page->index + 1;
ret = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) {
ret = 1;
break;
}
}
gfs2_trans_end(sdp);
return ret;
}
static int gfs2_write_jdata_pagevec(struct address_space *mapping,
struct writeback_control *wbc,
struct pagevec *pvec,
int nr_pages, pgoff_t end)
{
struct inode *inode = mapping->host;
struct gfs2_sbd *sdp = GFS2_SB(inode);
loff_t i_size = i_size_read(inode);
pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
struct backing_dev_info *bdi = mapping->backing_dev_info;
int i;
int ret;
ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
if (ret < 0)
return ret;
for(i = 0; i < nr_pages; i++) {
struct page *page = pvec->pages[i];
lock_page(page);
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
if (!wbc->range_cyclic && page->index > end) {
ret = 1;
unlock_page(page);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
if (PageWriteback(page) ||
!clear_page_dirty_for_io(page)) {
unlock_page(page);
continue;
}
/* Is the page fully outside i_size? (truncate in progress) */
if (page->index > end_index || (page->index == end_index && !offset)) {
page->mapping->a_ops->invalidatepage(page, 0);
unlock_page(page);
continue;
}
ret = __gfs2_jdata_writepage(page, wbc);
if (ret || (--(wbc->nr_to_write) <= 0))
ret = 1;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
ret = 1;
}
}
gfs2_trans_end(sdp);
return ret;
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
* This is also used when a single buffer is being dirtied: we want to set the
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
* Most callers have locked the page, which pins the address_space in memory.
* But zap_pte_range() does not lock the page, however in that case the
* mapping is pinned by the vma's ->vm_file reference.
*
* We take care to handle the case where the page was truncated from the
* mapping by re-checking page_mapping() inside tree_lock.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
spin_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
*/
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
/*
* It only removes the dentry from the dentry page,corresponding name
* entry in name page does not need to be touched during deletion.
*/
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *inode)
{
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
struct address_space *mapping = page->mapping;
struct inode *dir = mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
void *kaddr = page_address(page);
int i;
mutex_lock_op(sbi, DENTRY_OPS);
lock_page(page);
wait_on_page_writeback(page);
dentry_blk = (struct f2fs_dentry_block *)kaddr;
bit_pos = dentry - (struct f2fs_dir_entry *)dentry_blk->dentry;
for (i = 0; i < slots; i++)
test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
/* Let's check and deallocate this dentry page */
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
0);
kunmap(page); /* kunmap - pair of f2fs_find_entry */
set_page_dirty(page);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode && S_ISDIR(inode->i_mode)) {
drop_nlink(dir);
f2fs_write_inode(dir, NULL);
} else {
mark_inode_dirty(dir);
}
if (inode) {
inode->i_ctime = CURRENT_TIME;
drop_nlink(inode);
if (S_ISDIR(inode->i_mode)) {
drop_nlink(inode);
i_size_write(inode, 0);
}
f2fs_write_inode(inode, NULL);
if (inode->i_nlink == 0)
add_orphan_inode(sbi, inode->i_ino);
}
if (bit_pos == NR_DENTRY_IN_BLOCK) {
truncate_hole(dir, page->index, page->index + 1);
clear_page_dirty_for_io(page);
ClearPageUptodate(page);
dec_page_count(sbi, F2FS_DIRTY_DENTS);
inode_dec_dirty_dents(dir);
}
f2fs_put_page(page, 1);
mutex_unlock_op(sbi, DENTRY_OPS);
}
/*
* Inspired by write_cache_pages from /mm/page-writeback.c
*/
static int ecryptfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
struct page **pgs;
int pgidx;
/* printk("[g-ecryptfs] Info: call writepages\n"); */
pgs = kmalloc(sizeof(struct page*)*PAGEVEC_SIZE, GFP_KERNEL);
if (!pgs) {
printk("[g-ecryptfs] Error: pgs alloc failed!\n");
return -EFAULT;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
struct page *page;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
pgidx = 0;
for (i = 0; i < nr_pages; i++) {
page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
pgs[pgidx++] = page;
}
/*trace_wbc_writepage(wbc, mapping->backing_dev_info);*/
ret = ecryptfs_encrypt_pages(pgs, pgidx);
//printk("[g-ecryptfs] Info: enc %d pages in writepages\n", pgidx);
mapping_set_error(mapping, ret);
for (i = 0; i < nr_pages; i++) {
page = pvec.pages[i];
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
if (PageLocked(page))
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
kfree(pgs);
return ret;
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*
* To avoid livelocks (when other process dirties new pages), we first tag
* pages which should be written back with TOWRITE tag and only then start
* writing them. For data-integrity sync we have to be careful so that we do
* not miss some pages (e.g., because some other process has cleared TOWRITE
* tag we set). The rule we follow is that TOWRITE tag can be cleared only
* by the process clearing the DIRTY tag (and submitting the page for IO).
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int range_whole = 0;
int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0) {
done_index = 0;
break;
}
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
trace_wbc_writepage(wbc, mapping->backing_dev_info);
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
/*
* write a region of pages back to the server
*/
static int afs_writepages_region(struct address_space *mapping,
struct writeback_control *wbc,
pgoff_t index, pgoff_t end, pgoff_t *_next)
{
struct page *page;
int ret, n;
_enter(",,%lx,%lx,", index, end);
do {
n = find_get_pages_range_tag(mapping, &index, end,
PAGECACHE_TAG_DIRTY, 1, &page);
if (!n)
break;
_debug("wback %lx", page->index);
/*
* at this point we hold neither the i_pages lock nor the
* page lock: the page may be truncated or invalidated
* (changing page->mapping to NULL), or even swizzled
* back from swapper_space to tmpfs file mapping
*/
ret = lock_page_killable(page);
if (ret < 0) {
put_page(page);
_leave(" = %d", ret);
return ret;
}
if (page->mapping != mapping || !PageDirty(page)) {
unlock_page(page);
put_page(page);
continue;
}
if (PageWriteback(page)) {
unlock_page(page);
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
put_page(page);
continue;
}
if (!clear_page_dirty_for_io(page))
BUG();
ret = afs_write_back_from_locked_page(mapping, wbc, page, end);
put_page(page);
if (ret < 0) {
_leave(" = %d", ret);
return ret;
}
wbc->nr_to_write -= ret;
cond_resched();
} while (index < end && wbc->nr_to_write > 0);
*_next = index;
_leave(" = 0 [%lx]", *_next);
return 0;
}
/*
* Synchronously write back the locked page and any subsequent non-locked dirty
* pages.
*/
static int afs_write_back_from_locked_page(struct address_space *mapping,
struct writeback_control *wbc,
struct page *primary_page,
pgoff_t final_page)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct page *pages[8], *page;
unsigned long count, priv;
unsigned n, offset, to, f, t;
pgoff_t start, first, last;
int loop, ret;
_enter(",%lx", primary_page->index);
count = 1;
if (test_set_page_writeback(primary_page))
BUG();
/* Find all consecutive lockable dirty pages that have contiguous
* written regions, stopping when we find a page that is not
* immediately lockable, is not dirty or is missing, or we reach the
* end of the range.
*/
start = primary_page->index;
priv = page_private(primary_page);
offset = priv & AFS_PRIV_MAX;
to = priv >> AFS_PRIV_SHIFT;
trace_afs_page_dirty(vnode, tracepoint_string("store"),
primary_page->index, priv);
WARN_ON(offset == to);
if (offset == to)
trace_afs_page_dirty(vnode, tracepoint_string("WARN"),
primary_page->index, priv);
if (start >= final_page ||
(to < PAGE_SIZE && !test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)))
goto no_more;
start++;
do {
_debug("more %lx [%lx]", start, count);
n = final_page - start + 1;
if (n > ARRAY_SIZE(pages))
n = ARRAY_SIZE(pages);
n = find_get_pages_contig(mapping, start, ARRAY_SIZE(pages), pages);
_debug("fgpc %u", n);
if (n == 0)
goto no_more;
if (pages[0]->index != start) {
do {
put_page(pages[--n]);
} while (n > 0);
goto no_more;
}
for (loop = 0; loop < n; loop++) {
page = pages[loop];
if (to != PAGE_SIZE &&
!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags))
break;
if (page->index > final_page)
break;
if (!trylock_page(page))
break;
if (!PageDirty(page) || PageWriteback(page)) {
unlock_page(page);
break;
}
priv = page_private(page);
f = priv & AFS_PRIV_MAX;
t = priv >> AFS_PRIV_SHIFT;
if (f != 0 &&
!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)) {
unlock_page(page);
break;
}
to = t;
trace_afs_page_dirty(vnode, tracepoint_string("store+"),
page->index, priv);
if (!clear_page_dirty_for_io(page))
BUG();
if (test_set_page_writeback(page))
BUG();
unlock_page(page);
put_page(page);
}
count += loop;
if (loop < n) {
for (; loop < n; loop++)
put_page(pages[loop]);
goto no_more;
}
start += loop;
} while (start <= final_page && count < 65536);
no_more:
/* We now have a contiguous set of dirty pages, each with writeback
* set; the first page is still locked at this point, but all the rest
* have been unlocked.
*/
unlock_page(primary_page);
first = primary_page->index;
last = first + count - 1;
_debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
ret = afs_store_data(mapping, first, last, offset, to);
switch (ret) {
case 0:
ret = count;
break;
default:
pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
/* Fall through */
case -EACCES:
case -EPERM:
case -ENOKEY:
case -EKEYEXPIRED:
case -EKEYREJECTED:
case -EKEYREVOKED:
afs_redirty_pages(wbc, mapping, first, last);
mapping_set_error(mapping, ret);
break;
case -EDQUOT:
case -ENOSPC:
afs_redirty_pages(wbc, mapping, first, last);
mapping_set_error(mapping, -ENOSPC);
break;
case -EROFS:
case -EIO:
case -EREMOTEIO:
case -EFBIG:
case -ENOENT:
case -ENOMEDIUM:
case -ENXIO:
afs_kill_pages(mapping, first, last);
mapping_set_error(mapping, ret);
break;
}
_leave(" = %d", ret);
return ret;
}
/* Two pass sync: first using WB_SYNC_NONE, then WB_SYNC_ALL */
static int nfs_write_mapping(struct address_space *mapping, int how)
{
struct writeback_control wbc = {
.bdi = mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
};
return __nfs_write_mapping(mapping, &wbc, how);
}
/*
* flush the inode to disk.
*/
int nfs_wb_all(struct inode *inode)
{
return nfs_write_mapping(inode->i_mapping, 0);
}
int nfs_wb_nocommit(struct inode *inode)
{
return nfs_write_mapping(inode->i_mapping, FLUSH_NOCOMMIT);
}
int nfs_wb_page_cancel(struct inode *inode, struct page *page)
{
struct nfs_page *req;
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.bdi = page->mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
.range_end = range_end,
};
int ret = 0;
BUG_ON(!PageLocked(page));
for (;;) {
req = nfs_page_find_request(page);
if (req == NULL)
goto out;
if (test_bit(PG_CLEAN, &req->wb_flags)) {
nfs_release_request(req);
break;
}
if (nfs_lock_request_dontget(req)) {
nfs_inode_remove_request(req);
/*
* In case nfs_inode_remove_request has marked the
* page as being dirty
*/
cancel_dirty_page(page, PAGE_CACHE_SIZE);
nfs_unlock_request(req);
break;
}
ret = nfs_wait_on_request(req);
if (ret < 0)
goto out;
}
if (!PagePrivate(page))
return 0;
ret = nfs_sync_mapping_wait(page->mapping, &wbc, FLUSH_INVALIDATE);
out:
return ret;
}
static int nfs_wb_page_priority(struct inode *inode, struct page *page,
int how)
{
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.bdi = page->mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
.range_end = range_end,
};
int ret;
do {
if (clear_page_dirty_for_io(page)) {
ret = nfs_writepage_locked(page, &wbc);
if (ret < 0)
goto out_error;
} else if (!PagePrivate(page))
break;
ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
if (ret < 0)
goto out_error;
} while (PagePrivate(page));
return 0;
out_error:
__mark_inode_dirty(inode, I_DIRTY_PAGES);
return ret;
}
/*
* Write back all requests on one page - we do this before reading it.
*/
int nfs_wb_page(struct inode *inode, struct page* page)
{
return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
}
#ifdef CONFIG_MIGRATION
int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
struct page *page)
{
struct nfs_page *req;
int ret;
if (PageFsCache(page))
nfs_fscache_release_page(page, GFP_KERNEL);
req = nfs_find_and_lock_request(page);
ret = PTR_ERR(req);
if (IS_ERR(req))
goto out;
ret = migrate_page(mapping, newpage, page);
if (!req)
goto out;
if (ret)
goto out_unlock;
page_cache_get(newpage);
req->wb_page = newpage;
SetPagePrivate(newpage);
set_page_private(newpage, page_private(page));
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
out_unlock:
nfs_clear_page_tag_locked(req);
nfs_release_request(req);
out:
return ret;
}
#endif
int __init nfs_init_writepagecache(void)
{
nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
sizeof(struct nfs_write_data),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_wdata_cachep == NULL)
return -ENOMEM;
nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
nfs_wdata_cachep);
if (nfs_wdata_mempool == NULL)
return -ENOMEM;
nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
nfs_wdata_cachep);
if (nfs_commit_mempool == NULL)
return -ENOMEM;
/*
* NFS congestion size, scale with available memory.
*
* 64MB: 8192k
* 128MB: 11585k
* 256MB: 16384k
* 512MB: 23170k
* 1GB: 32768k
* 2GB: 46340k
* 4GB: 65536k
* 8GB: 92681k
* 16GB: 131072k
*
* This allows larger machines to have larger/more transfers.
* Limit the default to 256M
*/
nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
if (nfs_congestion_kb > 256*1024)
nfs_congestion_kb = 256*1024;
return 0;
}
void nfs_destroy_writepagecache(void)
{
mempool_destroy(nfs_commit_mempool);
mempool_destroy(nfs_wdata_mempool);
kmem_cache_destroy(nfs_wdata_cachep);
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_CACHE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = DATA,
.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
.page = page,
.encrypted_page = NULL,
};
trace_f2fs_writepage(page, DATA);
if (page->index < end_index)
goto write;
/*
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
offset = i_size & (PAGE_CACHE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
goto out;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
write:
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (f2fs_is_drop_cache(inode))
goto out;
if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
available_free_memory(sbi, BASE_CHECK))
goto redirty_out;
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
err = do_write_data_page(&fio);
goto done;
}
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
SetPageError(page);
goto out;
}
if (!wbc->for_reclaim)
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0))
goto redirty_out;
err = -EAGAIN;
f2fs_lock_op(sbi);
if (f2fs_has_inline_data(inode))
err = f2fs_write_inline_data(inode, page);
if (err == -EAGAIN)
err = do_write_data_page(&fio);
f2fs_unlock_op(sbi);
done:
if (err && err != -ENOENT)
goto redirty_out;
clear_cold_data(page);
out:
inode_dec_dirty_pages(inode);
if (err)
ClearPageUptodate(page);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
if (wbc->for_reclaim)
f2fs_submit_merged_bio(sbi, DATA, WRITE);
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct address_space *mapping = data;
int ret = mapping->a_ops->writepage(page, wbc);
mapping_set_error(mapping, ret);
return ret;
}
/*
* This function was copied from write_cche_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
int step = 0;
pagevec_init(&pvec, 0);
next:
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page->index > end) {
done = 1;
break;
}
done_index = page->index;
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (step == is_cold_data(page))
goto continue_unlock;
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page, DATA);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
done_index = page->index + 1;
done = 1;
break;
}
}
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (step < 1) {
step++;
goto next;
}
if (!cycled && !done) {
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
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 = {
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
};
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:
/* 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(page, dn, &fio);
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_data(dn->inode_page);
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;
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
int scanned = 0;
int range_whole = 0;
long nr_to_write = wbc->nr_to_write;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
scanned = 1;
}
retry:
while (!done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
unsigned i;
scanned = 1;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point we hold neither mapping->tree_lock nor
* lock on the page itself: the page may be truncated or
* invalidated (changing page->mapping to NULL), or even
* swizzled back from swapper_space to tmpfs file
* mapping
*/
lock_page(page);
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
if (!wbc->range_cyclic && page->index > end) {
done = 1;
unlock_page(page);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
if (PageWriteback(page) ||
!clear_page_dirty_for_io(page)) {
unlock_page(page);
continue;
}
ret = (*writepage)(page, wbc, data);
if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
unlock_page(page);
ret = 0;
}
if (ret || (--nr_to_write <= 0))
done = 1;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
goto retry;
}
if (!wbc->no_nrwrite_index_update) {
if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
mapping->writeback_index = index;
wbc->nr_to_write = nr_to_write;
}
return ret;
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
long nr_to_write = wbc->nr_to_write;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
retry:
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
if (nr_to_write > 0) {
nr_to_write--;
if (nr_to_write == 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
/*
* We stop writing back only if we are
* not doing integrity sync. In case of
* integrity sync we have to keep going
* because someone may be concurrently
* dirtying pages, and we might have
* synced a lot of newly appeared dirty
* pages, but have not synced all of the
* old dirty pages.
*/
done = 1;
break;
}
}
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (!wbc->no_nrwrite_index_update) {
if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
mapping->writeback_index = done_index;
wbc->nr_to_write = nr_to_write;
}
return ret;
}
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
char *lower_page_data = NULL;
/*#ifdef WRAPFS_CRYPTO
char *enc_buf = NULL;
#endif*/
wrapfs_debug_aops(
WRAPFS_SB(page->mapping->host->i_sb)->wrapfs_debug_a_ops, "");
wrapfs_debug("");
BUG_ON(!PageUptodate(page));
wrapfs_debug("");
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
lower_page_data = (char *)kmap(lower_page);
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*#ifdef WRAPFS_CRYPTO
enc_buf = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
if (enc_buf == NULL) {
wrapfs_debug("No memory!!");
err = -ENOMEM;
goto out_release;
}
err = my_encrypt(lower_page_data, PAGE_CACHE_SIZE, enc_buf,
PAGE_CACHE_SIZE,
WRAPFS_SB(inode->i_sb)->key,
WRAPFS_CRYPTO_KEY_LEN);
if (err < 0) {
wrapfs_debug("encrypt error!!");
kfree(enc_buf);
err = -EINVAL;
goto out_release;
}
memcpy(lower_page_data, enc_buf, PAGE_CACHE_SIZE);
kfree(enc_buf);
#endif*/
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
/*if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}*/
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
out_release:
kunmap(lower_page);
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
wrapfs_debug_aops(WRAPFS_SB(inode->i_sb)->wrapfs_debug_a_ops,
"err : %d", err);
return err;
}
