/*
* 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.
*/
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;
spin_lock_irq(&mapping->tree_lock);
if (PageDirty(page)) {
spin_unlock_irq(&mapping->tree_lock);
return 0;
}
BUG_ON(PagePrivate(page));
if (page_count(page) != 2) {
spin_unlock_irq(&mapping->tree_lock);
return 0;
}
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
ClearPageUptodate(page);
page_cache_release(page); /* pagecache ref */
return 1;
}
static void gfs2_invalidatepage(struct page *page, unsigned long offset)
{
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
struct buffer_head *head, *bh, *next;
unsigned int curr_off = 0;
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
return;
bh = head = page_buffers(page);
do {
unsigned int next_off = curr_off + bh->b_size;
next = bh->b_this_page;
if (offset <= curr_off)
discard_buffer(sdp, bh);
curr_off = next_off;
bh = next;
} while (bh != head);
if (!offset)
try_to_release_page(page, 0);
return;
}
/*
* 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_page_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)
{
struct mem_cgroup *memcg;
unsigned long flags;
if (page->mapping != mapping)
return 0;
if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
return 0;
memcg = mem_cgroup_begin_page_stat(page);
spin_lock_irqsave(&mapping->tree_lock, flags);
if (PageDirty(page))
goto failed;
BUG_ON(page_has_private(page));
__delete_from_page_cache(page, NULL, memcg);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_end_page_stat(memcg);
if (mapping->a_ops->freepage)
mapping->a_ops->freepage(page);
page_cache_release(page); /* pagecache ref */
return 1;
failed:
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_end_page_stat(memcg);
return 0;
}
/*
* 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_page_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 (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
return 0;
spin_lock_irq(&mapping->tree_lock);
if (PageDirty(page))
goto failed;
BUG_ON(page_has_private(page));
__delete_from_page_cache(page, NULL);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
if (mapping->a_ops->freepage)
mapping->a_ops->freepage(page);
page_cache_release(page); /* pagecache ref */
return 1;
failed:
spin_unlock_irq(&mapping->tree_lock);
return 0;
}
static void gfs2_invalidatepage(struct page *page, unsigned int offset,
unsigned int length)
{
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
unsigned int stop = offset + length;
int partial_page = (offset || length < PAGE_CACHE_SIZE);
struct buffer_head *bh, *head;
unsigned long pos = 0;
BUG_ON(!PageLocked(page));
if (!partial_page)
ClearPageChecked(page);
if (!page_has_buffers(page))
goto out;
bh = head = page_buffers(page);
do {
if (pos + bh->b_size > stop)
return;
if (offset <= pos)
gfs2_discard(sdp, bh);
pos += bh->b_size;
bh = bh->b_this_page;
} while (bh != head);
out:
if (!partial_page)
try_to_release_page(page, 0);
}
/*
* 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;
}
/*
* Try to drop buffers from the pages in a pagevec
*/
void pagevec_strip(struct pagevec *pvec)
{
int i;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
if (PagePrivate(page) && !TestSetPageLocked(page)) {
try_to_release_page(page, 0);
unlock_page(page);
}
}
}
/*
* Try to drop buffers from the pages in a pagevec
*/
void pagevec_strip(struct pagevec *pvec)
{
int i;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
if (page_has_private(page) && trylock_page(page)) {
if (page_has_private(page))
try_to_release_page(page, 0);
unlock_page(page);
}
}
}
/*
* This is for invalidate_mapping_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 use remove_mapping which safely
* discards clean, unused pages.
*
* Returns non-zero if the page was successfully invalidated.
*/
static int
invalidate_complete_page(struct address_space *mapping, struct page *page)
{
int ret;
if (page->mapping != mapping)
return 0;
if (page_has_private(page) && !try_to_release_page(page, 0))
return 0;
ret = remove_mapping(mapping, page);
return ret;
}
/*
* 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;
}
static void gfs2_invalidatepage(struct page *page, unsigned long offset)
{
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
struct buffer_head *bh, *head;
unsigned long pos = 0;
BUG_ON(!PageLocked(page));
if (offset == 0)
ClearPageChecked(page);
if (!page_has_buffers(page))
goto out;
bh = head = page_buffers(page);
do {
if (offset <= pos)
gfs2_discard(sdp, bh);
pos += bh->b_size;
bh = bh->b_this_page;
} while (bh != head);
out:
if (offset == 0)
try_to_release_page(page, 0);
}
static int shrink_cache(int nr_pages, zone_t * classzone, unsigned int gfp_mask, int priority)
{
struct list_head * entry;
int max_scan = nr_inactive_pages / priority;
int max_mapped = min((nr_pages << (10 - priority)), max_scan / 10);
spin_lock(&pagemap_lru_lock);
while (--max_scan >= 0 && (entry = inactive_list.prev) != &inactive_list) {
struct page * page;
/* lock depth is 1 or 2 */
if (unlikely(current->need_resched)) {
spin_unlock(&pagemap_lru_lock);
__set_current_state(TASK_RUNNING);
schedule();
spin_lock(&pagemap_lru_lock);
continue;
}
page = list_entry(entry, struct page, lru);
if (unlikely(!PageLRU(page)))
BUG();
if (unlikely(PageActive(page)))
BUG();
list_del(entry);
list_add(entry, &inactive_list);
/*
* Zero page counts can happen because we unlink the pages
* _after_ decrementing the usage count..
*/
if (unlikely(!page_count(page)))
continue;
if (!memclass(page->zone, classzone))
continue;
/* Racy check to avoid trylocking when not worthwhile */
if (!page->buffers && (page_count(page) != 1 || !page->mapping))
goto page_mapped;
/*
* The page is locked. IO in progress?
* Move it to the back of the list.
*/
if (unlikely(TryLockPage(page))) {
if (PageLaunder(page) && (gfp_mask & __GFP_FS)) {
page_cache_get(page);
spin_unlock(&pagemap_lru_lock);
wait_on_page(page);
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
}
continue;
}
if ((PageDirty(page) || DelallocPage(page)) && is_page_cache_freeable(page) && page->mapping) {
/*
* It is not critical here to write it only if
* the page is unmapped beause any direct writer
* like O_DIRECT would set the PG_dirty bitflag
* on the phisical page after having successfully
* pinned it and after the I/O to the page is finished,
* so the direct writes to the page cannot get lost.
*/
int (*writepage)(struct page *);
writepage = page->mapping->a_ops->writepage;
if ((gfp_mask & __GFP_FS) && writepage) {
ClearPageDirty(page);
SetPageLaunder(page);
page_cache_get(page);
spin_unlock(&pagemap_lru_lock);
writepage(page);
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
continue;
}
}
/*
* If the page has buffers, try to free the buffer mappings
* associated with this page. If we succeed we try to free
* the page as well.
*/
if (page->buffers) {
spin_unlock(&pagemap_lru_lock);
/* avoid to free a locked page */
page_cache_get(page);
if (try_to_release_page(page, gfp_mask)) {
if (!page->mapping) {
/*
* We must not allow an anon page
* with no buffers to be visible on
* the LRU, so we unlock the page after
* taking the lru lock
*/
spin_lock(&pagemap_lru_lock);
UnlockPage(page);
__lru_cache_del(page);
/* effectively free the page here */
page_cache_release(page);
if (--nr_pages)
continue;
break;
} else {
/*
* The page is still in pagecache so undo the stuff
* before the try_to_release_page since we've not
* finished and we can now try the next step.
*/
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
}
} else {
/* failed to drop the buffers so stop here */
UnlockPage(page);
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
continue;
}
}
spin_lock(&pagecache_lock);
/*
* this is the non-racy check for busy page.
*/
if (!page->mapping || !is_page_cache_freeable(page)) {
spin_unlock(&pagecache_lock);
UnlockPage(page);
page_mapped:
if (--max_mapped >= 0)
continue;
/*
* Alert! We've found too many mapped pages on the
* inactive list, so we start swapping out now!
*/
spin_unlock(&pagemap_lru_lock);
swap_out(priority, gfp_mask, classzone);
return nr_pages;
}
/*
* It is critical to check PageDirty _after_ we made sure
* the page is freeable* so not in use by anybody.
*/
if (PageDirty(page)) {
spin_unlock(&pagecache_lock);
UnlockPage(page);
continue;
}
/* point of no return */
if (likely(!PageSwapCache(page))) {
__remove_inode_page(page);
spin_unlock(&pagecache_lock);
} else {
swp_entry_t swap;
swap.val = page->index;
__delete_from_swap_cache(page);
spin_unlock(&pagecache_lock);
swap_free(swap);
}
__lru_cache_del(page);
UnlockPage(page);
/* effectively free the page here */
page_cache_release(page);
if (--nr_pages)
continue;
break;
}
spin_unlock(&pagemap_lru_lock);
return nr_pages;
}
/*
* Try to free buffers if "page" has them.
*/
static int
remap_preparepage(struct page *page, int fastmode)
{
struct address_space *mapping;
int waitcnt = fastmode ? 0 : 10;
BUG_ON(!PageLocked(page));
mapping = page_mapping(page);
if (PageWriteback(page) && !PagePrivate(page) && !PageSwapCache(page)) {
printk("remap: mapping %p page %p\n", page->mapping, page);
return -REMAPPREP_WB;
}
if (PageWriteback(page))
wait_on_page_writeback(page);
if (PagePrivate(page)) {
#ifdef DEBUG_MSG
printk("rmap: process page with buffers...\n");
#endif
/* XXX copied from shrink_list() */
if (PageDirty(page) &&
is_page_cache_freeable(page) &&
mapping != NULL &&
mapping->a_ops->writepage != NULL) {
spin_lock_irq(&mapping->tree_lock);
if (clear_page_dirty_for_io(page)) {
int res;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
.nonblocking = 1,
.for_reclaim = 1,
};
spin_unlock_irq(&mapping->tree_lock);
SetPageReclaim(page);
res = mapping->a_ops->writepage(page, &wbc);
if (res < 0)
/* not implemented. help */
BUG();
if (res == WRITEPAGE_ACTIVATE) {
ClearPageReclaim(page);
return -REMAPPREP_WB;
}
if (!PageWriteback(page)) {
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
lock_page(page);
if (!PagePrivate(page))
return 0;
} else
spin_unlock_irq(&mapping->tree_lock);
}
while (1) {
if (try_to_release_page(page, GFP_KERNEL))
break;
if (!waitcnt)
return -REMAPPREP_BUFFER;
msleep(10);
waitcnt--;
if (!waitcnt)
print_buffer(page);
}
}
static int shrink_cache(int nr_pages, zone_t * classzone, unsigned int gfp_mask, int * failed_swapout)
{
struct list_head * entry;
int max_scan = (classzone->nr_inactive_pages + classzone->nr_active_pages) / vm_cache_scan_ratio;
int max_mapped = vm_mapped_ratio * nr_pages;
while (max_scan && classzone->nr_inactive_pages && (entry = inactive_list.prev) != &inactive_list) {
struct page * page;
if (unlikely(current->need_resched)) {
spin_unlock(&pagemap_lru_lock);
__set_current_state(TASK_RUNNING);
schedule();
spin_lock(&pagemap_lru_lock);
continue;
}
page = list_entry(entry, struct page, lru);
BUG_ON(!PageLRU(page));
BUG_ON(PageActive(page));
list_del(entry);
list_add(entry, &inactive_list);
/*
* Zero page counts can happen because we unlink the pages
* _after_ decrementing the usage count..
*/
if (unlikely(!page_count(page)))
continue;
if (!memclass(page_zone(page), classzone))
continue;
max_scan--;
/* Racy check to avoid trylocking when not worthwhile */
if (!page->buffers && (page_count(page) != 1 || !page->mapping))
goto page_mapped;
/*
* The page is locked. IO in progress?
* Move it to the back of the list.
*/
if (unlikely(TryLockPage(page))) {
if (PageLaunder(page) && (gfp_mask & __GFP_FS)) {
page_cache_get(page);
spin_unlock(&pagemap_lru_lock);
wait_on_page(page);
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
}
continue;
}
if (PageDirty(page) && is_page_cache_freeable(page) && page->mapping) {
/*
* It is not critical here to write it only if
* the page is unmapped beause any direct writer
* like O_DIRECT would set the PG_dirty bitflag
* on the phisical page after having successfully
* pinned it and after the I/O to the page is finished,
* so the direct writes to the page cannot get lost.
*/
int (*writepage)(struct page *);
writepage = page->mapping->a_ops->writepage;
if ((gfp_mask & __GFP_FS) && writepage) {
ClearPageDirty(page);
SetPageLaunder(page);
page_cache_get(page);
spin_unlock(&pagemap_lru_lock);
writepage(page);
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
continue;
}
}
/*
* If the page has buffers, try to free the buffer mappings
* associated with this page. If we succeed we try to free
* the page as well.
*/
if (page->buffers) {
spin_unlock(&pagemap_lru_lock);
/* avoid to free a locked page */
page_cache_get(page);
if (try_to_release_page(page, gfp_mask)) {
if (!page->mapping) {
/*
* We must not allow an anon page
* with no buffers to be visible on
* the LRU, so we unlock the page after
* taking the lru lock
*/
spin_lock(&pagemap_lru_lock);
UnlockPage(page);
__lru_cache_del(page);
/* effectively free the page here */
page_cache_release(page);
if (--nr_pages)
continue;
break;
} else {
/*
* The page is still in pagecache so undo the stuff
* before the try_to_release_page since we've not
* finished and we can now try the next step.
*/
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
}
} else {
/* failed to drop the buffers so stop here */
UnlockPage(page);
page_cache_release(page);
spin_lock(&pagemap_lru_lock);
continue;
}
}
spin_lock(&pagecache_lock);
/*
* This is the non-racy check for busy page.
* It is critical to check PageDirty _after_ we made sure
* the page is freeable so not in use by anybody.
* At this point we're guaranteed that page->buffers is NULL,
* nobody can refill page->buffers under us because we still
* hold the page lock.
*/
if (!page->mapping || page_count(page) > 1) {
spin_unlock(&pagecache_lock);
UnlockPage(page);
page_mapped:
if (--max_mapped < 0) {
spin_unlock(&pagemap_lru_lock);
nr_pages -= kmem_cache_reap(gfp_mask);
if (nr_pages <= 0)
goto out;
shrink_dcache_memory(vm_vfs_scan_ratio, gfp_mask);
shrink_icache_memory(vm_vfs_scan_ratio, gfp_mask);
#ifdef CONFIG_QUOTA
shrink_dqcache_memory(vm_vfs_scan_ratio, gfp_mask);
#endif
if (!*failed_swapout)
*failed_swapout = !swap_out(classzone);
max_mapped = nr_pages * vm_mapped_ratio;
spin_lock(&pagemap_lru_lock);
refill_inactive(nr_pages, classzone);
}
continue;
}
if (PageDirty(page)) {
spin_unlock(&pagecache_lock);
UnlockPage(page);
continue;
}
__lru_cache_del(page);
/* point of no return */
if (likely(!PageSwapCache(page))) {
__remove_inode_page(page);
spin_unlock(&pagecache_lock);
} else {
swp_entry_t swap;
swap.val = page->index;
__delete_from_swap_cache(page);
spin_unlock(&pagecache_lock);
swap_free(swap);
}
UnlockPage(page);
/* effectively free the page here */
page_cache_release(page);
if (--nr_pages)
continue;
break;
}
spin_unlock(&pagemap_lru_lock);
out:
return nr_pages;
}