2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* mm/truncate.c - code for taking down pages from address_spaces
|
|
|
|
*
|
|
|
|
* Copyright (C) 2002, Linus Torvalds
|
|
|
|
*
|
|
|
|
* 10Sep2002 akpm@zip.com.au
|
|
|
|
* Initial version.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/pagevec.h>
|
|
|
|
#include <linux/buffer_head.h> /* grr. try_to_release_page,
|
2005-10-31 07:00:16 +08:00
|
|
|
do_invalidatepage */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
static inline void truncate_partial_page(struct page *page, unsigned partial)
|
|
|
|
{
|
|
|
|
memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
|
|
|
|
if (PagePrivate(page))
|
|
|
|
do_invalidatepage(page, partial);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If truncate cannot remove the fs-private metadata from the page, the page
|
|
|
|
* becomes anonymous. It will be left on the LRU and may even be mapped into
|
|
|
|
* user pagetables if we're racing with filemap_nopage().
|
|
|
|
*
|
|
|
|
* We need to bale out if page->mapping is no longer equal to the original
|
|
|
|
* mapping. This happens a) when the VM reclaimed the page while we waited on
|
|
|
|
* its lock, b) when a concurrent invalidate_inode_pages got there first and
|
|
|
|
* c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
truncate_complete_page(struct address_space *mapping, struct page *page)
|
|
|
|
{
|
|
|
|
if (page->mapping != mapping)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (PagePrivate(page))
|
|
|
|
do_invalidatepage(page, 0);
|
|
|
|
|
|
|
|
clear_page_dirty(page);
|
|
|
|
ClearPageUptodate(page);
|
|
|
|
ClearPageMappedToDisk(page);
|
|
|
|
remove_from_page_cache(page);
|
|
|
|
page_cache_release(page); /* pagecache ref */
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is for invalidate_inode_pages(). That function can be called at
|
|
|
|
* any time, and is not supposed to throw away dirty pages. But pages can
|
|
|
|
* be marked dirty at any time too. So we re-check the dirtiness inside
|
|
|
|
* ->tree_lock. That provides exclusion against the __set_page_dirty
|
|
|
|
* functions.
|
|
|
|
*
|
|
|
|
* Returns non-zero if the page was successfully invalidated.
|
|
|
|
*/
|
|
|
|
static int
|
|
|
|
invalidate_complete_page(struct address_space *mapping, struct page *page)
|
|
|
|
{
|
|
|
|
if (page->mapping != mapping)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (PagePrivate(page) && !try_to_release_page(page, 0))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
write_lock_irq(&mapping->tree_lock);
|
|
|
|
if (PageDirty(page)) {
|
|
|
|
write_unlock_irq(&mapping->tree_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
BUG_ON(PagePrivate(page));
|
|
|
|
__remove_from_page_cache(page);
|
|
|
|
write_unlock_irq(&mapping->tree_lock);
|
|
|
|
ClearPageUptodate(page);
|
|
|
|
page_cache_release(page); /* pagecache ref */
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2006-01-06 16:10:36 +08:00
|
|
|
* truncate_inode_pages - truncate range of pages specified by start and
|
|
|
|
* end byte offsets
|
2005-04-17 06:20:36 +08:00
|
|
|
* @mapping: mapping to truncate
|
|
|
|
* @lstart: offset from which to truncate
|
2006-01-06 16:10:36 +08:00
|
|
|
* @lend: offset to which to truncate
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2006-01-06 16:10:36 +08:00
|
|
|
* Truncate the page cache, removing the pages that are between
|
|
|
|
* specified offsets (and zeroing out partial page
|
|
|
|
* (if lstart is not page aligned)).
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
2006-01-06 16:10:36 +08:00
|
|
|
void truncate_inode_pages_range(struct address_space *mapping,
|
|
|
|
loff_t lstart, loff_t lend)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
|
2006-01-06 16:10:36 +08:00
|
|
|
pgoff_t end;
|
2005-04-17 06:20:36 +08:00
|
|
|
const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
|
|
|
|
struct pagevec pvec;
|
|
|
|
pgoff_t next;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (mapping->nrpages == 0)
|
|
|
|
return;
|
|
|
|
|
2006-01-06 16:10:36 +08:00
|
|
|
BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
|
|
|
|
end = (lend >> PAGE_CACHE_SHIFT);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
pagevec_init(&pvec, 0);
|
|
|
|
next = start;
|
2006-01-06 16:10:36 +08:00
|
|
|
while (next <= end &&
|
|
|
|
pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
for (i = 0; i < pagevec_count(&pvec); i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
|
|
|
pgoff_t page_index = page->index;
|
|
|
|
|
2006-01-06 16:10:36 +08:00
|
|
|
if (page_index > end) {
|
|
|
|
next = page_index;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
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;
|
|
|
|
}
|
2006-01-06 16:10:36 +08:00
|
|
|
if (pvec.pages[0]->index > end) {
|
|
|
|
pagevec_release(&pvec);
|
|
|
|
break;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
for (i = 0; i < pagevec_count(&pvec); i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
|
|
|
|
2006-01-06 16:10:36 +08:00
|
|
|
if (page->index > end)
|
|
|
|
break;
|
2005-04-17 06:20:36 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
}
|
2006-01-06 16:10:36 +08:00
|
|
|
EXPORT_SYMBOL(truncate_inode_pages_range);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-01-06 16:10:36 +08:00
|
|
|
/**
|
|
|
|
* truncate_inode_pages - truncate *all* the pages from an offset
|
|
|
|
* @mapping: mapping to truncate
|
|
|
|
* @lstart: offset from which to truncate
|
|
|
|
*
|
2006-01-10 07:59:24 +08:00
|
|
|
* Called under (and serialised by) inode->i_mutex.
|
2006-01-06 16:10:36 +08:00
|
|
|
*/
|
|
|
|
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
|
|
|
|
{
|
|
|
|
truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
EXPORT_SYMBOL(truncate_inode_pages);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
|
|
|
|
* @mapping: the address_space which holds the pages to invalidate
|
|
|
|
* @start: the offset 'from' which to invalidate
|
|
|
|
* @end: the offset 'to' which to invalidate (inclusive)
|
|
|
|
*
|
|
|
|
* This function only removes the unlocked pages, if you want to
|
|
|
|
* remove all the pages of one inode, you must call truncate_inode_pages.
|
|
|
|
*
|
|
|
|
* invalidate_mapping_pages() will not block on IO activity. It will not
|
|
|
|
* invalidate pages which are dirty, locked, under writeback or mapped into
|
|
|
|
* pagetables.
|
|
|
|
*/
|
|
|
|
unsigned long invalidate_mapping_pages(struct address_space *mapping,
|
|
|
|
pgoff_t start, pgoff_t end)
|
|
|
|
{
|
|
|
|
struct pagevec pvec;
|
|
|
|
pgoff_t next = start;
|
|
|
|
unsigned long ret = 0;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
pagevec_init(&pvec, 0);
|
|
|
|
while (next <= end &&
|
|
|
|
pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
|
|
|
|
for (i = 0; i < pagevec_count(&pvec); i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
2006-06-23 17:05:48 +08:00
|
|
|
pgoff_t index;
|
|
|
|
int lock_failed;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-06-23 17:05:48 +08:00
|
|
|
lock_failed = TestSetPageLocked(page);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We really shouldn't be looking at the ->index of an
|
|
|
|
* unlocked page. But we're not allowed to lock these
|
|
|
|
* pages. So we rely upon nobody altering the ->index
|
|
|
|
* of this (pinned-by-us) page.
|
|
|
|
*/
|
|
|
|
index = page->index;
|
|
|
|
if (index > next)
|
|
|
|
next = index;
|
2005-04-17 06:20:36 +08:00
|
|
|
next++;
|
2006-06-23 17:05:48 +08:00
|
|
|
if (lock_failed)
|
|
|
|
continue;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (PageDirty(page) || PageWriteback(page))
|
|
|
|
goto unlock;
|
|
|
|
if (page_mapped(page))
|
|
|
|
goto unlock;
|
|
|
|
ret += invalidate_complete_page(mapping, page);
|
|
|
|
unlock:
|
|
|
|
unlock_page(page);
|
|
|
|
if (next > end)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
pagevec_release(&pvec);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long invalidate_inode_pages(struct address_space *mapping)
|
|
|
|
{
|
|
|
|
return invalidate_mapping_pages(mapping, 0, ~0UL);
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(invalidate_inode_pages);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* invalidate_inode_pages2_range - remove range of pages from an address_space
|
2005-05-01 23:59:26 +08:00
|
|
|
* @mapping: the address_space
|
2005-04-17 06:20:36 +08:00
|
|
|
* @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 -EIO if any pages could not be invalidated.
|
|
|
|
*/
|
|
|
|
int invalidate_inode_pages2_range(struct address_space *mapping,
|
|
|
|
pgoff_t start, pgoff_t end)
|
|
|
|
{
|
|
|
|
struct pagevec pvec;
|
|
|
|
pgoff_t next;
|
|
|
|
int i;
|
|
|
|
int ret = 0;
|
|
|
|
int did_range_unmap = 0;
|
|
|
|
int wrapped = 0;
|
|
|
|
|
|
|
|
pagevec_init(&pvec, 0);
|
|
|
|
next = start;
|
|
|
|
while (next <= end && !ret && !wrapped &&
|
|
|
|
pagevec_lookup(&pvec, mapping, next,
|
|
|
|
min(end - next, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
|
|
|
|
for (i = 0; !ret && i < pagevec_count(&pvec); i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
|
|
|
pgoff_t page_index;
|
|
|
|
int was_dirty;
|
|
|
|
|
|
|
|
lock_page(page);
|
|
|
|
if (page->mapping != mapping) {
|
|
|
|
unlock_page(page);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
page_index = page->index;
|
|
|
|
next = page_index + 1;
|
|
|
|
if (next == 0)
|
|
|
|
wrapped = 1;
|
|
|
|
if (page_index > end) {
|
|
|
|
unlock_page(page);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
wait_on_page_writeback(page);
|
|
|
|
while (page_mapped(page)) {
|
|
|
|
if (!did_range_unmap) {
|
|
|
|
/*
|
|
|
|
* Zap the rest of the file in one hit.
|
|
|
|
*/
|
|
|
|
unmap_mapping_range(mapping,
|
2005-11-24 05:37:47 +08:00
|
|
|
(loff_t)page_index<<PAGE_CACHE_SHIFT,
|
|
|
|
(loff_t)(end - page_index + 1)
|
2005-04-17 06:20:36 +08:00
|
|
|
<< PAGE_CACHE_SHIFT,
|
|
|
|
0);
|
|
|
|
did_range_unmap = 1;
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* Just zap this page
|
|
|
|
*/
|
|
|
|
unmap_mapping_range(mapping,
|
2005-11-24 05:37:47 +08:00
|
|
|
(loff_t)page_index<<PAGE_CACHE_SHIFT,
|
2005-04-17 06:20:36 +08:00
|
|
|
PAGE_CACHE_SIZE, 0);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
was_dirty = test_clear_page_dirty(page);
|
|
|
|
if (!invalidate_complete_page(mapping, page)) {
|
|
|
|
if (was_dirty)
|
|
|
|
set_page_dirty(page);
|
|
|
|
ret = -EIO;
|
|
|
|
}
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
|
|
|
pagevec_release(&pvec);
|
|
|
|
cond_resched();
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* invalidate_inode_pages2 - remove all pages from an address_space
|
2005-05-01 23:59:26 +08:00
|
|
|
* @mapping: the address_space
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Any pages which are found to be mapped into pagetables are unmapped prior to
|
|
|
|
* invalidation.
|
|
|
|
*
|
|
|
|
* Returns -EIO if any pages could not be invalidated.
|
|
|
|
*/
|
|
|
|
int invalidate_inode_pages2(struct address_space *mapping)
|
|
|
|
{
|
|
|
|
return invalidate_inode_pages2_range(mapping, 0, -1);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
|