static struct page *init_inode_metadata(struct inode *inode,
struct inode *dir, const struct qstr *name)
{
struct page *page;
int err;
if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
page = new_inode_page(inode, name);
if (IS_ERR(page))
return page;
if (S_ISDIR(inode->i_mode)) {
err = make_empty_dir(inode, dir, page);
if (err)
goto error;
}
err = f2fs_init_acl(inode, dir, page);
if (err)
goto put_error;
err = f2fs_init_security(inode, dir, name, page);
if (err)
goto put_error;
wait_on_page_writeback(page);
} else {
page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
if (IS_ERR(page))
return page;
wait_on_page_writeback(page);
set_cold_node(inode, page);
}
init_dent_inode(name, page);
/*
* This file should be checkpointed during fsync.
* We lost i_pino from now on.
*/
if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
file_lost_pino(inode);
inc_nlink(inode);
}
return page;
put_error:
f2fs_put_page(page, 1);
error:
remove_inode_page(inode);
return ERR_PTR(err);
}
/*
* 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;
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);
update_inode_page(dir);
} 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);
}
update_inode_page(inode);
if (inode->i_nlink == 0)
add_orphan_inode(sbi, inode->i_ino);
else
release_orphan_inode(sbi);
}
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);
}
/**
* invalidate_inode_pages2 - remove all unmapped pages from an address_space
* @mapping - the address_space
*
* invalidate_inode_pages2() is like truncate_inode_pages(), except for the case
* where the page is seen to be mapped into process pagetables. In that case,
* the page is marked clean but is left attached to its address_space.
*
* The page is also marked not uptodate so that a subsequent pagefault will
* perform I/O to bringthe page's contents back into sync with its backing
* store.
*
* FIXME: invalidate_inode_pages2() is probably trivially livelockable.
*/
void invalidate_inode_pages2(struct address_space *mapping)
{
struct pagevec pvec;
pgoff_t next = 0;
int i;
pagevec_init(&pvec, 0);
while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
lock_page(page);
if (page->mapping == mapping) { /* truncate race? */
wait_on_page_writeback(page);
next = page->index + 1;
if (page_mapped(page)) {
clear_page_dirty(page);
ClearPageUptodate(page);
} else {
if (!invalidate_complete_page(mapping,
page)) {
clear_page_dirty(page);
ClearPageUptodate(page);
}
}
}
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
}
}
/*
* Attempt to steal a page from a pipe buffer. This should perhaps go into
* a vm helper function, it's already simplified quite a bit by the
* addition of remove_mapping(). If success is returned, the caller may
* attempt to reuse this page for another destination.
*/
static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
struct address_space *mapping = page_mapping(page);
lock_page(page);
WARN_ON(!PageUptodate(page));
/*
* At least for ext2 with nobh option, we need to wait on writeback
* completing on this page, since we'll remove it from the pagecache.
* Otherwise truncate wont wait on the page, allowing the disk
* blocks to be reused by someone else before we actually wrote our
* data to them. fs corruption ensues.
*/
wait_on_page_writeback(page);
if (PagePrivate(page))
try_to_release_page(page, mapping_gfp_mask(mapping));
if (!remove_mapping(mapping, page)) {
unlock_page(page);
return 1;
}
buf->flags |= PIPE_BUF_FLAG_LRU;
return 0;
}
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);
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,
PAGE_CACHE_SIZE);
unlock_page(page);
continue;
}
ret = __gfs2_jdata_writepage(page, wbc);
if (ret || (--(wbc->nr_to_write) <= 0))
ret = 1;
}
gfs2_trans_end(sdp);
return ret;
}
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_dentry->d_inode;
struct nilfs_transaction_info ti;
int ret;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS;
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
return VM_FAULT_NOPAGE;
}
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
if (unlikely(ret))
return VM_FAULT_SIGBUS;
ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret != VM_FAULT_LOCKED) {
nilfs_transaction_abort(inode->i_sb);
return ret;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
wait_on_page_writeback(page);
return VM_FAULT_LOCKED;
}
/* added: begin address space operations definitions */
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;
BUG_ON(!PageUptodate(page));
inode = page->mapping->host;
if (!inode || !WRAPFS_I(inode)){
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
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_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
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;
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
fsstack_copy_attr_times(inode, lower_inode);
out_release:
page_cache_release(lower_page);
out:
unlock_page(page);
return err;
}
void reiser4_wait_page_writeback(struct page *page)
{
assert("zam-783", PageLocked(page));
do {
unlock_page(page);
wait_on_page_writeback(page);
lock_page(page);
} while (PageWriteback(page));
}
int btrfs_wait_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages, int mark)
{
int ret;
int err = 0;
int werr = 0;
struct page *page;
struct inode *btree_inode = root->fs_info->btree_inode;
u64 start = 0;
u64 end;
unsigned long index;
while (1) {
ret = find_first_extent_bit(dirty_pages, start, &start, &end,
mark);
if (ret)
break;
clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
while (start <= end) {
index = start >> PAGE_CACHE_SHIFT;
start = (u64)(index + 1) << PAGE_CACHE_SHIFT;
page = find_get_page(btree_inode->i_mapping, index);
if (!page)
continue;
if (PageDirty(page)) {
btree_lock_page_hook(page);
wait_on_page_writeback(page);
err = write_one_page(page, 0);
if (err)
werr = err;
}
wait_on_page_writeback(page);
page_cache_release(page);
cond_resched();
}
}
if (err)
werr = err;
return werr;
}
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode)
{
lock_page(page);
wait_on_page_writeback(page);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
kunmap(page);
set_page_dirty(page);
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
mark_inode_dirty(dir);
f2fs_put_page(page, 1);
}
void init_dent_inode(const struct qstr *name, struct page *ipage)
{
struct f2fs_node *rn;
if (IS_ERR(ipage))
return;
wait_on_page_writeback(ipage);
/* copy name info. to this inode page */
rn = (struct f2fs_node *)page_address(ipage);
rn->i.i_namelen = cpu_to_le32(name->len);
memcpy(rn->i.i_name, name->name, name->len);
set_page_dirty(ipage);
}
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode)
{
lock_page(page);
wait_on_page_writeback(page);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
kunmap(page);
set_page_dirty(page);
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
mark_inode_dirty(dir);
/* update parent inode number before releasing dentry page */
F2FS_I(inode)->i_pino = dir->i_ino;
f2fs_put_page(page, 1);
}
/*
* Attempt to steal a page from a pipe buffer. This should perhaps go into
* a vm helper function, it's already simplified quite a bit by the
* addition of remove_mapping(). If success is returned, the caller may
* attempt to reuse this page for another destination.
*/
static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
struct address_space *mapping;
lock_page(page);
mapping = page_mapping(page);
if (mapping) {
WARN_ON(!PageUptodate(page));
/*
* At least for ext2 with nobh option, we need to wait on
* writeback completing on this page, since we'll remove it
* from the pagecache. Otherwise truncate wont wait on the
* page, allowing the disk blocks to be reused by someone else
* before we actually wrote our data to them. fs corruption
* ensues.
*/
wait_on_page_writeback(page);
if (PagePrivate(page)
&& try_to_release_page(page, GFP_KERNEL))
goto out_unlock;
/*
* If we succeeded in removing the mapping, set LRU flag
* and return good.
*/
if (remove_mapping(mapping, page)) {
buf->flags |= PIPE_BUF_FLAG_LRU;
return 0;
}
}
/*
* Raced with truncate or failed to remove page from current
* address space, unlock and return failure.
*/
out_unlock:
unlock_page(page);
return 1;
}
void nilfs_btnode_delete(struct buffer_head *bh)
{
struct address_space *mapping;
struct page *page = bh->b_page;
pgoff_t index = page_index(page);
int still_dirty;
page_cache_get(page);
lock_page(page);
wait_on_page_writeback(page);
nilfs_forget_buffer(bh);
still_dirty = PageDirty(page);
mapping = page->mapping;
unlock_page(page);
page_cache_release(page);
if (!still_dirty && mapping)
invalidate_inode_pages2_range(mapping, index, index);
}
/*
* Notification that a PTE pointing to an NFS page is about to be made
* writable, implying that someone is about to modify the page through a
* shared-writable mapping
*/
static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct file *filp = vma->vm_file;
struct inode *inode = file_inode(filp);
unsigned pagelen;
int ret = VM_FAULT_NOPAGE;
struct address_space *mapping;
dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n",
filp, filp->f_mapping->host->i_ino,
(long long)page_offset(page));
/* make sure the cache has finished storing the page */
nfs_fscache_wait_on_page_write(NFS_I(inode), page);
wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
nfs_wait_bit_killable, TASK_KILLABLE);
lock_page(page);
mapping = page_file_mapping(page);
if (mapping != inode->i_mapping)
goto out_unlock;
wait_on_page_writeback(page);
pagelen = nfs_page_length(page);
if (pagelen == 0)
goto out_unlock;
ret = VM_FAULT_LOCKED;
if (nfs_flush_incompatible(filp, page) == 0 &&
nfs_updatepage(filp, page, 0, pagelen) == 0)
goto out;
ret = VM_FAULT_SIGBUS;
out_unlock:
unlock_page(page);
out:
return ret;
}
/*
* Notification that a PTE pointing to an NFS page is about to be made
* writable, implying that someone is about to modify the page through a
* shared-writable mapping
*/
static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct file *filp = vma->vm_file;
struct dentry *dentry = filp->f_path.dentry;
unsigned pagelen;
int ret = VM_FAULT_NOPAGE;
struct address_space *mapping;
dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
filp->f_mapping->host->i_ino,
(long long)page_offset(page));
/* make sure the cache has finished storing the page */
nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
lock_page(page);
mapping = page_file_mapping(page);
if (mapping != dentry->d_inode->i_mapping)
goto out_unlock;
wait_on_page_writeback(page);
pagelen = nfs_page_length(page);
if (pagelen == 0)
goto out_unlock;
ret = VM_FAULT_LOCKED;
if (nfs_flush_incompatible(filp, page) == 0 &&
nfs_updatepage(filp, page, 0, pagelen) == 0)
goto out;
ret = VM_FAULT_SIGBUS;
out_unlock:
unlock_page(page);
out:
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;
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 (wbc->nr_to_write > 0) {
wbc->nr_to_write--;
if (wbc->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->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
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;
}
/*
* 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));
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info,
BDI_RECLAIMABLE);
task_io_account_write(PAGE_CACHE_SIZE);
}
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);
}
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, mapping->backing_dev_info);
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;
}
/**
* 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);
}
/**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;
}
/*
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode)
{
unsigned int bit_pos;
unsigned int level;
unsigned int current_depth;
unsigned long bidx, block;
f2fs_hash_t dentry_hash;
struct f2fs_dir_entry *de;
unsigned int nbucket, nblock;
size_t namelen = name->len;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
int slots = GET_DENTRY_SLOTS(namelen);
struct page *page;
int err = 0;
int i;
dentry_hash = f2fs_dentry_hash(name->name, name->len);
level = 0;
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
level = F2FS_I(dir)->clevel;
F2FS_I(dir)->chash = 0;
}
start:
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
return -ENOSPC;
/* Increase the depth, if required */
if (level == current_depth)
++current_depth;
nbucket = dir_buckets(level);
nblock = bucket_blocks(level);
bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(dentry_blk, slots);
if (bit_pos < NR_DENTRY_IN_BLOCK)
goto add_dentry;
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
/* Move to next level to find the empty slot for new dentry */
++level;
goto start;
add_dentry:
wait_on_page_writeback(dentry_page);
page = init_inode_metadata(inode, dir, name);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
de = &dentry_blk->dentry[bit_pos];
de->hash_code = dentry_hash;
de->name_len = cpu_to_le16(namelen);
memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
for (i = 0; i < slots; i++)
test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
set_page_dirty(dentry_page);
/* we don't need to mark_inode_dirty now */
F2FS_I(inode)->i_pino = dir->i_ino;
update_inode(inode, page);
f2fs_put_page(page, 1);
update_parent_metadata(dir, inode, current_depth);
fail:
clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
return err;
}
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;
}
struct inode *f2fs_iget_nowait(struct super_block *sb, unsigned long ino)
{
struct f2fs_iget_args args = {
.ino = ino,
.on_free = 0
};
struct inode *inode = ilookup5(sb, ino, f2fs_iget_test, &args);
if (inode)
return inode;
if (!args.on_free)
return f2fs_iget(sb, ino);
return ERR_PTR(-ENOENT);
}
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_node *rn;
struct f2fs_inode *ri;
/* Check if ino is within scope */
check_nid_range(sbi, inode->i_ino);
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
rn = page_address(node_page);
ri = &(rn->i);
inode->i_mode = le16_to_cpu(ri->i_mode);
i_uid_write(inode, le32_to_cpu(ri->i_uid));
i_gid_write(inode, le32_to_cpu(ri->i_gid));
set_nlink(inode, le32_to_cpu(ri->i_links));
inode->i_size = le64_to_cpu(ri->i_size);
inode->i_blocks = le64_to_cpu(ri->i_blocks);
inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime);
inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
fi->flags = 0;
fi->data_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver) - 1;
fi->i_advise = ri->i_advise;
fi->i_pino = le32_to_cpu(ri->i_pino);
get_extent_info(&fi->ext, ri->i_ext);
f2fs_put_page(node_page, 1);
return 0;
}
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
int ret;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
goto make_now;
ret = do_read_inode(inode);
if (ret)
goto bad_inode;
if (!sbi->por_doing && inode->i_nlink == 0) {
ret = -ENOENT;
goto bad_inode;
}
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (S_ISREG(inode->i_mode)) {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE |
__GFP_ZERO);
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &f2fs_special_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
} else {
ret = -EIO;
goto bad_inode;
}
unlock_new_inode(inode);
return inode;
bad_inode:
iget_failed(inode);
return ERR_PTR(ret);
}
void update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_node *rn;
struct f2fs_inode *ri;
wait_on_page_writeback(node_page);
rn = page_address(node_page);
ri = &(rn->i);
ri->i_mode = cpu_to_le16(inode->i_mode);
ri->i_advise = F2FS_I(inode)->i_advise;
ri->i_uid = cpu_to_le32(i_uid_read(inode));
ri->i_gid = cpu_to_le32(i_gid_read(inode));
ri->i_links = cpu_to_le32(inode->i_nlink);
ri->i_size = cpu_to_le64(i_size_read(inode));
ri->i_blocks = cpu_to_le64(inode->i_blocks);
set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
set_cold_node(inode, node_page);
set_page_dirty(node_page);
}
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *node_page;
bool need_lock = false;
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
return 0;
if (wbc)
f2fs_balance_fs(sbi);
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
if (!PageDirty(node_page)) {
need_lock = true;
f2fs_put_page(node_page, 1);
mutex_lock(&sbi->write_inode);
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
mutex_unlock(&sbi->write_inode);
return PTR_ERR(node_page);
}
}
update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
if (need_lock)
mutex_unlock(&sbi->write_inode);
return 0;
}
/*
* Called at the last iput() if i_nlink is zero
*/
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
goto no_delete;
BUG_ON(atomic_read(&F2FS_I(inode)->dirty_dents));
remove_dirty_dir_inode(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
f2fs_truncate(inode);
remove_inode_page(inode);
no_delete:
clear_inode(inode);
}
/**
* truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
* @lend: offset to which to truncate (inclusive)
*
* Truncate the page cache, removing the pages that are between
* specified offsets (and zeroing out partial pages
* if lstart or lend + 1 is not page aligned).
*
* Truncate takes two passes - the first pass is nonblocking. It will not
* block on page locks and it will not block on writeback. The second pass
* will wait. This is to prevent as much IO as possible in the affected region.
* The first pass will remove most pages, so the search cost of the second pass
* is low.
*
* We pass down the cache-hot hint to the page freeing code. Even if the
* mapping is large, it is probably the case that the final pages are the most
* recently touched, and freeing happens in ascending file offset order.
*
* Note that since ->invalidatepage() accepts range to invalidate
* truncate_inode_pages_range is able to handle cases where lend + 1 is not
* page aligned properly.
*/
void truncate_inode_pages_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
pgoff_t start; /* inclusive */
pgoff_t end; /* exclusive */
unsigned int partial_start; /* inclusive */
unsigned int partial_end; /* exclusive */
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
pgoff_t index;
int i;
cleancache_invalidate_inode(mapping);
if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
return;
/* Offsets within partial pages */
partial_start = lstart & (PAGE_CACHE_SIZE - 1);
partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
/*
* 'start' and 'end' always covers the range of pages to be fully
* truncated. Partial pages are covered with 'partial_start' at the
* start of the range and 'partial_end' at the end of the range.
* Note that 'end' is exclusive while 'lend' is inclusive.
*/
start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (lend == -1)
/*
* lend == -1 indicates end-of-file so we have to set 'end'
* to the highest possible pgoff_t and since the type is
* unsigned we're using -1.
*/
end = -1;
else
end = (lend + 1) >> PAGE_CACHE_SHIFT;
pagevec_init(&pvec, 0);
index = start;
while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
index = indices[i];
if (index >= end)
break;
if (radix_tree_exceptional_entry(page)) {
clear_exceptional_entry(mapping, index, page);
continue;
}
if (!trylock_page(page))
continue;
WARN_ON(page->index != index);
if (PageWriteback(page)) {
unlock_page(page);
continue;
}
truncate_inode_page(mapping, page);
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
cond_resched();
index++;
}
if (partial_start) {
struct page *page = find_lock_page(mapping, start - 1);
if (page) {
unsigned int top = PAGE_CACHE_SIZE;
if (start > end) {
/* Truncation within a single page */
top = partial_end;
partial_end = 0;
}
wait_on_page_writeback(page);
zero_user_segment(page, partial_start, top);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, partial_start,
top - partial_start);
unlock_page(page);
page_cache_release(page);
}
}
if (partial_end) {
struct page *page = find_lock_page(mapping, end);
if (page) {
wait_on_page_writeback(page);
zero_user_segment(page, 0, partial_end);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, 0,
partial_end);
unlock_page(page);
page_cache_release(page);
}
}
/*
* If the truncation happened within a single page no pages
* will be released, just zeroed, so we can bail out now.
*/
if (start >= end)
return;
index = start;
for ( ; ; ) {
cond_resched();
if (!pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) {
/* If all gone from start onwards, we're done */
if (index == start)
break;
/* Otherwise restart to make sure all gone */
index = start;
continue;
}
if (index == start && indices[0] >= end) {
/* All gone out of hole to be punched, we're done */
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
break;
}
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
index = indices[i];
if (index >= end) {
/* Restart punch to make sure all gone */
index = start - 1;
break;
}
if (radix_tree_exceptional_entry(page)) {
clear_exceptional_entry(mapping, index, page);
continue;
}
lock_page(page);
WARN_ON(page->index != index);
wait_on_page_writeback(page);
truncate_inode_page(mapping, page);
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
index++;
}
cleancache_invalidate_inode(mapping);
}
/**
* invalidate_inode_pages2_range - remove range of pages from an address_space
* @mapping: the address_space
* @start: the page offset 'from' which to invalidate
* @end: the page offset 'to' which to invalidate (inclusive)
*
* Any pages which are found to be mapped into pagetables are unmapped prior to
* invalidation.
*
* Returns -EBUSY if any pages could not be invalidated.
*/
int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
pgoff_t index;
int i;
int ret = 0;
int ret2 = 0;
int did_range_unmap = 0;
cleancache_invalidate_inode(mapping);
pagevec_init(&pvec, 0);
index = start;
while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
index = indices[i];
if (index > end)
break;
if (radix_tree_exceptional_entry(page)) {
clear_exceptional_entry(mapping, index, page);
continue;
}
lock_page(page);
WARN_ON(page->index != index);
if (page->mapping != mapping) {
unlock_page(page);
continue;
}
wait_on_page_writeback(page);
if (page_mapped(page)) {
if (!did_range_unmap) {
/*
* Zap the rest of the file in one hit.
*/
unmap_mapping_range(mapping,
(loff_t)index << PAGE_CACHE_SHIFT,
(loff_t)(1 + end - index)
<< PAGE_CACHE_SHIFT,
0);
did_range_unmap = 1;
} else {
/*
* Just zap this page
*/
unmap_mapping_range(mapping,
(loff_t)index << PAGE_CACHE_SHIFT,
PAGE_CACHE_SIZE, 0);
}
}
BUG_ON(page_mapped(page));
ret2 = do_launder_page(mapping, page);
if (ret2 == 0) {
if (!invalidate_complete_page2(mapping, page))
ret2 = -EBUSY;
}
if (ret2 < 0)
ret = ret2;
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
cond_resched();
index++;
}
cleancache_invalidate_inode(mapping);
return ret;
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
struct gfs2_qadata *qa;
loff_t size;
int ret;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = -ENOMEM;
qa = gfs2_qadata_get(ip);
if (qa == NULL)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_alloc_put;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ret = gfs2_inplace_reserve(ip, data_blocks + ind_blocks);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_alloc_put:
gfs2_qadata_put(ip);
out_unlock:
gfs2_glock_dq(&gh);
out:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
if (inode->i_sb->s_frozen == SB_UNFROZEN) {
wait_on_page_writeback(page);
} else {
ret = -EAGAIN;
unlock_page(page);
}
}
return block_page_mkwrite_return(ret);
}
/*
* We completely avoid races by reading each swap page in advance,
* and then search for the process using it. All the necessary
* page table adjustments can then be made atomically.
*/
static int try_to_unuse(unsigned int type)
{
struct swap_info_struct * si = &swap_info[type];
struct mm_struct *start_mm;
unsigned short *swap_map;
unsigned short swcount;
struct page *page;
swp_entry_t entry;
unsigned int i = 0;
int retval = 0;
int reset_overflow = 0;
int shmem;
/*
* When searching mms for an entry, a good strategy is to
* start at the first mm we freed the previous entry from
* (though actually we don't notice whether we or coincidence
* freed the entry). Initialize this start_mm with a hold.
*
* A simpler strategy would be to start at the last mm we
* freed the previous entry from; but that would take less
* advantage of mmlist ordering, which clusters forked mms
* together, child after parent. If we race with dup_mmap(), we
* prefer to resolve parent before child, lest we miss entries
* duplicated after we scanned child: using last mm would invert
* that. Though it's only a serious concern when an overflowed
* swap count is reset from SWAP_MAP_MAX, preventing a rescan.
*/
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
/*
* Keep on scanning until all entries have gone. Usually,
* one pass through swap_map is enough, but not necessarily:
* there are races when an instance of an entry might be missed.
*/
while ((i = find_next_to_unuse(si, i)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
}
/*
* Get a page for the entry, using the existing swap
* cache page if there is one. Otherwise, get a clean
* page and read the swap into it.
*/
swap_map = &si->swap_map[i];
entry = swp_entry(type, i);
page = read_swap_cache_async(entry, NULL, 0);
if (!page) {
/*
* Either swap_duplicate() failed because entry
* has been freed independently, and will not be
* reused since sys_swapoff() already disabled
* allocation from here, or alloc_page() failed.
*/
if (!*swap_map)
continue;
retval = -ENOMEM;
break;
}
/*
* Don't hold on to start_mm if it looks like exiting.
*/
if (atomic_read(&start_mm->mm_users) == 1) {
mmput(start_mm);
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
}
/*
* Wait for and lock page. When do_swap_page races with
* try_to_unuse, do_swap_page can handle the fault much
* faster than try_to_unuse can locate the entry. This
* apparently redundant "wait_on_page_locked" lets try_to_unuse
* defer to do_swap_page in such a case - in some tests,
* do_swap_page and try_to_unuse repeatedly compete.
*/
wait_on_page_locked(page);
wait_on_page_writeback(page);
lock_page(page);
wait_on_page_writeback(page);
/*
* Remove all references to entry.
* Whenever we reach init_mm, there's no address space
* to search, but use it as a reminder to search shmem.
*/
shmem = 0;
swcount = *swap_map;
if (swcount > 1) {
if (start_mm == &init_mm)
shmem = shmem_unuse(entry, page);
else
retval = unuse_mm(start_mm, entry, page);
}
if (*swap_map > 1) {
int set_start_mm = (*swap_map >= swcount);
struct list_head *p = &start_mm->mmlist;
struct mm_struct *new_start_mm = start_mm;
struct mm_struct *prev_mm = start_mm;
struct mm_struct *mm;
atomic_inc(&new_start_mm->mm_users);
atomic_inc(&prev_mm->mm_users);
spin_lock(&mmlist_lock);
while (*swap_map > 1 && !retval &&
(p = p->next) != &start_mm->mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!atomic_inc_not_zero(&mm->mm_users))
continue;
spin_unlock(&mmlist_lock);
mmput(prev_mm);
prev_mm = mm;
cond_resched();
swcount = *swap_map;
if (swcount <= 1)
;
else if (mm == &init_mm) {
set_start_mm = 1;
shmem = shmem_unuse(entry, page);
} else
retval = unuse_mm(mm, entry, page);
if (set_start_mm && *swap_map < swcount) {
mmput(new_start_mm);
atomic_inc(&mm->mm_users);
new_start_mm = mm;
set_start_mm = 0;
}
spin_lock(&mmlist_lock);
}
spin_unlock(&mmlist_lock);
mmput(prev_mm);
mmput(start_mm);
start_mm = new_start_mm;
}
if (retval) {
unlock_page(page);
page_cache_release(page);
break;
}
/*
* How could swap count reach 0x7fff when the maximum
* pid is 0x7fff, and there's no way to repeat a swap
* page within an mm (except in shmem, where it's the
* shared object which takes the reference count)?
* We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
*
* If that's wrong, then we should worry more about
* exit_mmap() and do_munmap() cases described above:
* we might be resetting SWAP_MAP_MAX too early here.
* We know "Undead"s can happen, they're okay, so don't
* report them; but do report if we reset SWAP_MAP_MAX.
*/
if (*swap_map == SWAP_MAP_MAX) {
spin_lock(&swap_lock);
*swap_map = 1;
spin_unlock(&swap_lock);
reset_overflow = 1;
}
/*
* If a reference remains (rare), we would like to leave
* the page in the swap cache; but try_to_unmap could
* then re-duplicate the entry once we drop page lock,
* so we might loop indefinitely; also, that page could
* not be swapped out to other storage meanwhile. So:
* delete from cache even if there's another reference,
* after ensuring that the data has been saved to disk -
* since if the reference remains (rarer), it will be
* read from disk into another page. Splitting into two
* pages would be incorrect if swap supported "shared
* private" pages, but they are handled by tmpfs files.
*
* Note shmem_unuse already deleted a swappage from
* the swap cache, unless the move to filepage failed:
* in which case it left swappage in cache, lowered its
* swap count to pass quickly through the loops above,
* and now we must reincrement count to try again later.
*/
if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
};
swap_writepage(page, &wbc);
lock_page(page);
wait_on_page_writeback(page);
}
if (PageSwapCache(page)) {
if (shmem)
swap_duplicate(entry);
else
delete_from_swap_cache(page);
}
/*
* So we could skip searching mms once swap count went
* to 1, we did not mark any present ptes as dirty: must
* mark page dirty so shrink_page_list will preserve it.
*/
SetPageDirty(page);
unlock_page(page);
page_cache_release(page);
/*
* Make sure that we aren't completely killing
* interactive performance.
*/
cond_resched();
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
/* Update file times before taking page lock */
file_update_time(vma->vm_file);
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = gfs2_rindex_update(sdp);
if (ret)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ret = gfs2_inplace_reserve(ip, data_blocks + ind_blocks, 0);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
/* Check page index against inode size */
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
/* Unstuff, if required, and allocate backing blocks for page */
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_on_page_writeback(page);
}
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
/**
* truncate_inode_pages - truncate *all* the pages from an offset
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
*
* Truncate the page cache at a set offset, removing the pages that are beyond
* that offset (and zeroing out partial pages).
*
* Truncate takes two passes - the first pass is nonblocking. It will not
* block on page locks and it will not block on writeback. The second pass
* will wait. This is to prevent as much IO as possible in the affected region.
* The first pass will remove most pages, so the search cost of the second pass
* is low.
*
* When looking at page->index outside the page lock we need to be careful to
* copy it into a local to avoid races (it could change at any time).
*
* We pass down the cache-hot hint to the page freeing code. Even if the
* mapping is large, it is probably the case that the final pages are the most
* recently touched, and freeing happens in ascending file offset order.
*
* Called under (and serialised by) inode->i_sem.
*/
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
{
const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
struct pagevec pvec;
pgoff_t next;
int i;
if (mapping->nrpages == 0)
return;
pagevec_init(&pvec, 0);
next = start;
while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
pgoff_t page_index = page->index;
if (page_index > next)
next = page_index;
next++;
if (TestSetPageLocked(page))
continue;
if (PageWriteback(page)) {
unlock_page(page);
continue;
}
truncate_complete_page(mapping, page);
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
}
if (partial) {
struct page *page = find_lock_page(mapping, start - 1);
if (page) {
wait_on_page_writeback(page);
truncate_partial_page(page, partial);
unlock_page(page);
page_cache_release(page);
}
}
next = start;
for ( ; ; ) {
cond_resched();
if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
if (next == start)
break;
next = start;
continue;
}
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
lock_page(page);
wait_on_page_writeback(page);
if (page->index > next)
next = page->index;
next++;
truncate_complete_page(mapping, page);
unlock_page(page);
}
pagevec_release(&pvec);
}
}
