#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/buffer_head.h> /* grr. try_to_release_page,
- block_invalidatepage */
+ do_invalidatepage */
-static int do_invalidatepage(struct page *page, unsigned long offset)
-{
- int (*invalidatepage)(struct page *, unsigned long);
- invalidatepage = page->mapping->a_ops->invalidatepage;
- if (invalidatepage == NULL)
- invalidatepage = block_invalidatepage;
- return (*invalidatepage)(page, offset);
-}
-
static inline void truncate_partial_page(struct page *page, unsigned partial)
{
memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
* 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 (PagePrivate(page) && !try_to_release_page(page, 0))
return 0;
- spin_lock_irq(&mapping->tree_lock);
- if (PageDirty(page)) {
- spin_unlock_irq(&mapping->tree_lock);
- return 0;
- }
+ write_lock_irq(&mapping->tree_lock);
+ if (PageDirty(page))
+ goto failed;
+ if (page_count(page) != 2) /* caller's ref + pagecache ref */
+ goto failed;
+
+ BUG_ON(PagePrivate(page));
__remove_from_page_cache(page);
- spin_unlock_irq(&mapping->tree_lock);
+ write_unlock_irq(&mapping->tree_lock);
ClearPageUptodate(page);
page_cache_release(page); /* pagecache ref */
return 1;
+failed:
+ write_unlock_irq(&mapping->tree_lock);
+ return 0;
}
/**
- * truncate_inode_pages - truncate *all* the pages from an offset
+ * truncate_inode_pages - truncate range of pages specified by start and
+ * end byte offsets
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
+ * @lend: offset to 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 the page cache, removing the pages that are between
+ * specified offsets (and zeroing out partial page
+ * (if lstart 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
* 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)
+void truncate_inode_pages_range(struct address_space *mapping,
+ loff_t lstart, loff_t lend)
{
const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+ pgoff_t end;
const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
struct pagevec pvec;
pgoff_t next;
if (mapping->nrpages == 0)
return;
+ BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
+ end = (lend >> PAGE_CACHE_SHIFT);
+
pagevec_init(&pvec, 0);
next = start;
- while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+ while (next <= end &&
+ 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 > end) {
+ next = page_index;
+ break;
+ }
+
if (page_index > next)
next = page_index;
next++;
next = start;
for ( ; ; ) {
+ cond_resched();
if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
if (next == start)
break;
next = start;
continue;
}
+ if (pvec.pages[0]->index > end) {
+ pagevec_release(&pvec);
+ break;
+ }
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
+ if (page->index > end)
+ break;
lock_page(page);
wait_on_page_writeback(page);
if (page->index > next)
pagevec_release(&pvec);
}
}
+EXPORT_SYMBOL(truncate_inode_pages_range);
+/**
+ * truncate_inode_pages - truncate *all* the pages from an offset
+ * @mapping: mapping to truncate
+ * @lstart: offset from which to truncate
+ *
+ * Called under (and serialised by) inode->i_mutex.
+ */
+void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
+{
+ truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
+}
EXPORT_SYMBOL(truncate_inode_pages);
/**
pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
+ pgoff_t index;
+ int lock_failed;
- if (TestSetPageLocked(page)) {
- next++;
- continue;
- }
- if (page->index > next)
- next = page->index;
+ 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;
next++;
+ if (lock_failed)
+ continue;
+
if (PageDirty(page) || PageWriteback(page))
goto unlock;
if (page_mapped(page))
break;
}
pagevec_release(&pvec);
- cond_resched();
}
return ret;
}
+EXPORT_SYMBOL_GPL(invalidate_mapping_pages);
+
unsigned long invalidate_inode_pages(struct address_space *mapping)
{
return invalidate_mapping_pages(mapping, 0, ~0UL);
}
-
EXPORT_SYMBOL(invalidate_inode_pages);
+/*
+ * This is like invalidate_complete_page(), except it ignores the page's
+ * refcount. We do this because invalidate_inode_pages2() needs stronger
+ * invalidation guarantees, and cannot afford to leave pages behind because
+ * shrink_list() has a temp ref on them, or because they're transiently sitting
+ * in the lru_cache_add() pagevecs.
+ */
+static int
+invalidate_complete_page2(struct address_space *mapping, struct page *page)
+{
+ if (page->mapping != mapping)
+ return 0;
+
+ if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+ return 0;
+
+ write_lock_irq(&mapping->tree_lock);
+ if (PageDirty(page))
+ goto failed;
+
+ 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;
+failed:
+ write_unlock_irq(&mapping->tree_lock);
+ return 0;
+}
+
/**
- * invalidate_inode_pages2 - remove all unmapped pages from an address_space
- * @mapping - the address_space
+ * 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)
*
- * 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.
+ * Any pages which are found to be mapped into pagetables are unmapped prior to
+ * invalidation.
*
- * FIXME: invalidate_inode_pages2() is probably trivially livelockable.
+ * Returns -EIO if any pages could not be invalidated.
*/
-void invalidate_inode_pages2(struct address_space *mapping)
+int invalidate_inode_pages2_range(struct address_space *mapping,
+ pgoff_t start, pgoff_t end)
{
struct pagevec pvec;
- pgoff_t next = 0;
+ pgoff_t next;
int i;
+ int ret = 0;
+ int did_range_unmap = 0;
+ int wrapped = 0;
pagevec_init(&pvec, 0);
- while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
- for (i = 0; i < pagevec_count(&pvec); i++) {
+ 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) { /* truncate race? */
- wait_on_page_writeback(page);
- next = page->index + 1;
- if (page_mapped(page))
- clear_page_dirty(page);
- else
- invalidate_complete_page(mapping, 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,
+ (loff_t)page_index<<PAGE_CACHE_SHIFT,
+ (loff_t)(end - page_index + 1)
+ << PAGE_CACHE_SHIFT,
+ 0);
+ did_range_unmap = 1;
+ } else {
+ /*
+ * Just zap this page
+ */
+ unmap_mapping_range(mapping,
+ (loff_t)page_index<<PAGE_CACHE_SHIFT,
+ PAGE_CACHE_SIZE, 0);
+ }
+ }
+ was_dirty = test_clear_page_dirty(page);
+ if (!invalidate_complete_page2(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
+ * @mapping: the address_space
+ *
+ * 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);