参照元

説明

引数

返り値

参考

実装

static void __split_huge_page_refcount(struct page *page,
				       struct list_head *list)
{
	int i;
	struct zone *zone = page_zone(page);
	struct lruvec *lruvec;
	int tail_count = 0;
	/* prevent PageLRU to go away from under us, and freeze lru stats */
	spin_lock_irq(&zone->lru_lock);
	lruvec = mem_cgroup_page_lruvec(page, zone);
	compound_lock(page);
	/* complete memcg works before add pages to LRU */
	mem_cgroup_split_huge_fixup(page);
	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
		struct page *page_tail = page + i;

		/* tail_page->_mapcount cannot change */
		BUG_ON(page_mapcount(page_tail) < 0);
		tail_count += page_mapcount(page_tail);
		/* check for overflow */
		BUG_ON(tail_count < 0);
		BUG_ON(atomic_read(&page_tail->_count) != 0);
		/*
		 * tail_page->_count is zero and not changing from
		 * under us. But get_page_unless_zero() may be running
		 * from under us on the tail_page. If we used
		 * atomic_set() below instead of atomic_add(), we
		 * would then run atomic_set() concurrently with
		 * get_page_unless_zero(), and atomic_set() is
		 * implemented in C not using locked ops. spin_unlock
		 * on x86 sometime uses locked ops because of PPro
		 * errata 66, 92, so unless somebody can guarantee
		 * atomic_set() here would be safe on all archs (and
		 * not only on x86), it's safer to use atomic_add().
		 */
		atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
			   &page_tail->_count);
		/* after clearing PageTail the gup refcount can be released */
		smp_mb__after_atomic();

		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
		page_tail->flags |= (page->flags &
				     ((1L << PG_referenced) |
				      (1L << PG_swapbacked) |
				      (1L << PG_mlocked) |
				      (1L << PG_uptodate) |
				      (1L << PG_active) |
				      (1L << PG_unevictable)));
		page_tail->flags |= (1L << PG_dirty);

		clear_compound_head(page_tail);
		if (page_is_young(page))
			set_page_young(page_tail);
		if (page_is_idle(page))
			set_page_idle(page_tail);
		/*
		 * __split_huge_page_splitting() already set the
		 * splitting bit in all pmd that could map this
		 * hugepage, that will ensure no CPU can alter the
		 * mapcount on the head page. The mapcount is only
		 * accounted in the head page and it has to be
		 * transferred to all tail pages in the below code. So
		 * for this code to be safe, the split the mapcount
		 * can't change. But that doesn't mean userland can't
		 * keep changing and reading the page contents while
		 * we transfer the mapcount, so the pmd splitting
		 * status is achieved setting a reserved bit in the
		 * pmd, not by clearing the present bit.
		*/
		page_tail->_mapcount = page->_mapcount;

		BUG_ON(page_tail->mapping);
		page_tail->mapping = page->mapping;

		page_tail->index = page->index + i;
		page_cpupid_xchg_last(page_tail, page_cpupid_last(page));
		BUG_ON(!PageAnon(page_tail));
		BUG_ON(!PageUptodate(page_tail));
		BUG_ON(!PageDirty(page_tail));
		BUG_ON(!PageSwapBacked(page_tail));

		lru_add_page_tail(page, page_tail, lruvec, list);
	}
	atomic_sub(tail_count, &page->_count);
	BUG_ON(atomic_read(&page->_count) <= 0);
	__mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);
	ClearPageCompound(page);
	compound_unlock(page);
	spin_unlock_irq(&zone->lru_lock);
	for (i = 1; i < HPAGE_PMD_NR; i++) {
		struct page *page_tail = page + i;
		BUG_ON(page_count(page_tail) <= 0);
		/*
		 * Tail pages may be freed if there wasn't any mapping
		 * like if add_to_swap() is running on a lru page that
		 * had its mapping zapped. And freeing these pages
		 * requires taking the lru_lock so we do the put_page
		 * of the tail pages after the split is complete.
		 */
		put_page(page_tail);
	}
	/*
	 * Only the head page (now become a regular page) is required
	 * to be pinned by the caller.
	 */
	BUG_ON(page_count(page) <= 0);
}

コメント


トップ   新規 一覧 検索 最終更新   ヘルプ   最終更新のRSS