khugepaged: allow to collapse a page shared across fork (9445689f) · Commits · 戴 / test

mm/khugepaged.c

+37 −9

Original line number	Diff line number	Diff line
		@@ -526,6 +526,17 @@ static void release_pte_pages(pte_t pte, pte_t _pte)
		}
		}

		static bool is_refcount_suitable(struct page *page)
		{
		int expected_refcount;

		expected_refcount = total_mapcount(page);
		if (PageSwapCache(page))
		expected_refcount += compound_nr(page);

		return page_count(page) == expected_refcount;
		}

		static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
		unsigned long address,
		pte_t *pte)
		@@ -578,11 +589,17 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
		}

		/*
		* cannot use mapcount: can't collapse if there's a gup pin.
		* The page must only be referenced by the scanned process
		* and page swap cache.
		* Check if the page has any GUP (or other external) pins.
		*
		* The page table that maps the page has been already unlinked
		* from the page table tree and this process cannot get
		* an additinal pin on the page.
		*
		* New pins can come later if the page is shared across fork,
		* but not from this process. The other process cannot write to
		* the page, only trigger CoW.
		*/
		if (page_count(page) != 1 + PageSwapCache(page)) {
		if (!is_refcount_suitable(page)) {
		unlock_page(page);
		result = SCAN_PAGE_COUNT;
		goto out;
		@@ -669,7 +686,6 @@ static void __collapse_huge_page_copy(pte_t pte, struct page page,
		} else {
		src_page = pte_page(pteval);
		copy_user_highpage(page, src_page, address, vma);
		VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page);
		release_pte_page(src_page);
		/*
		* ptl mostly unnecessary, but preempt has to
		@@ -1221,11 +1237,23 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
		}

		/*
		* cannot use mapcount: can't collapse if there's a gup pin.
		* The page must only be referenced by the scanned process
		* and page swap cache.
		* Check if the page has any GUP (or other external) pins.
		*
		* Here the check is racy it may see totmal_mapcount > refcount
		* in some cases.
		* For example, one process with one forked child process.
		* The parent has the PMD split due to MADV_DONTNEED, then
		* the child is trying unmap the whole PMD, but khugepaged
		* may be scanning the parent between the child has
		* PageDoubleMap flag cleared and dec the mapcount. So
		* khugepaged may see total_mapcount > refcount.
		*
		* But such case is ephemeral we could always retry collapse
		* later. However it may report false positive if the page
		* has excessive GUP pins (i.e. 512). Anyway the same check
		* will be done again later the risk seems low.
		*/
		if (page_count(page) != 1 + PageSwapCache(page)) {
		if (!is_refcount_suitable(page)) {
		result = SCAN_PAGE_COUNT;
		goto out_unmap;
		}

Admin message