/**
* pagecache_isize_extended - update pagecache after extension of i_size
* @inode: inode for which i_size was extended
* @from: original inode size
* @to: new inode size
*
* Handle extension of inode size either caused by extending truncate or by
* write starting after current i_size. We mark the page straddling current
* i_size RO so that page_mkwrite() is called on the nearest write access to
* the page. This way filesystem can be sure that page_mkwrite() is called on
* the page before user writes to the page via mmap after the i_size has been
* changed.
*
* The function must be called after i_size is updated so that page fault
* coming after we unlock the page will already see the new i_size.
* The function must be called while we still hold i_mutex - this not only
* makes sure i_size is stable but also that userspace cannot observe new
* i_size value before we are prepared to store mmap writes at new inode size.
*/
void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
{
int bsize = 1 << inode->i_blkbits;
loff_t rounded_from;
struct page *page;
pgoff_t index;
WARN_ON(to > inode->i_size);
if (from >= to || bsize == PAGE_CACHE_SIZE)
return;
/* Page straddling @from will not have any hole block created? */
rounded_from = round_up(from, bsize);
if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
return;
index = from >> PAGE_CACHE_SHIFT;
page = find_lock_page(inode->i_mapping, index);
/* Page not cached? Nothing to do */
if (!page)
return;
/*
* See clear_page_dirty_for_io() for details why set_page_dirty()
* is needed.
*/
if (page_mkclean(page))
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
}
/*
* Clear a page's dirty flag, while caring for dirty memory accounting.
* Returns true if the page was previously dirty.
*
* This is for preparing to put the page under writeout. We leave the page
* tagged as dirty in the radix tree so that a concurrent write-for-sync
* can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
* implementation will run either set_page_writeback() or set_page_dirty(),
* at which stage we bring the page's dirty flag and radix-tree dirty tag
* back into sync.
*
* This incoherency between the page's dirty flag and radix-tree tag is
* unfortunate, but it only exists while the page is locked.
*/
static int tux3_clear_page_dirty_for_io(struct page *page)
{
if(DEBUG_MODE_K==1)
{
printf("\t\t\t\t%25s[K] %25s %4d #in\n",__FILE__,__func__,__LINE__);
}
struct address_space *mapping = page->mapping;
BUG_ON(!PageLocked(page));
if (mapping && mapping_cap_account_dirty(mapping)) {
/*
* Yes, Virginia, this is indeed insane.
*
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
* mark the whole page dirty if it was
* dirty in a pagetable. Only to then
* (c) clean the page again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
* Note! Normally the "set_page_dirty(page)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
/* If PageForked(), don't touch PTE and don't dirty */
if (!PageForked(page) && page_mkclean(page))
set_page_dirty(page);
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the page dirty
* at this point. We do this by having them hold the
* page lock at some point after installing their
* pte, but before marking the page dirty.
* Pages are always locked coming in here, so we get
* the desired exclusion. See mm/memory.c:do_wp_page()
* for more comments.
*/
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_bdi_stat(mapping->backing_dev_info,
BDI_RECLAIMABLE);
return 1;
}
return 0;
}
return TestClearPageDirty(page);
}
/*
* Clear a page's dirty flag, while caring for dirty memory accounting.
* Returns true if the page was previously dirty.
*
* This is for preparing to put the page under writeout. We leave the page
* tagged as dirty in the radix tree so that a concurrent write-for-sync
* can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
* implementation will run either set_page_writeback() or set_page_dirty(),
* at which stage we bring the page's dirty flag and radix-tree dirty tag
* back into sync.
*
* This incoherency between the page's dirty flag and radix-tree tag is
* unfortunate, but it only exists while the page is locked.
*/
int clear_page_dirty_for_io(struct page *page)
{
struct address_space *mapping = page_mapping(page);
if (mapping && mapping_cap_account_dirty(mapping)) {
/*
* Yes, Virginia, this is indeed insane.
*
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
* mark the whole page dirty if it was
* dirty in a pagetable. Only to then
* (c) clean the page again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
* Note! Normally the "set_page_dirty(page)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*
* FIXME! We still have a race here: if somebody
* adds the page back to the page tables in
* between the "page_mkclean()" and the "TestClearPageDirty()",
* we might have it mapped without the dirty bit set.
*/
if (page_mkclean(page))
set_page_dirty(page);
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
return 1;
}
return 0;
}
return TestClearPageDirty(page);
}