Commit 40d707f3 authored by Alex Shi (tencent)'s avatar Alex Shi (tencent) Committed by Andrew Morton
Browse files

mm/ksm: use folio in write_protect_page 

Compound page is checked and skipped before write_protect_page() called,
use folio to save a few compound_head checks.

Link: https://lkml.kernel.org/r/20240411061713.1847574-8-alexs@kernel.org


Signed-off-by: default avatarAlex Shi (tencent) <alexs@kernel.org>
Reviewed-by: default avatarDavid Hildenbrand <david@redhat.com>
Cc: Izik Eidus <izik.eidus@ravellosystems.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 72556a4c

mm/ksm.c

+13 −12
Original line number Diff line number Diff line
@@ -1289,23 +1289,24 @@ static u32 calc_checksum(struct page *page) 
	return checksum;

}



static int write_protect_page(struct vm_area_struct *vma, struct page *page,

static int write_protect_page(struct vm_area_struct *vma, struct folio *folio,

			      pte_t *orig_pte)

{

	struct mm_struct *mm = vma->vm_mm;

	DEFINE_PAGE_VMA_WALK(pvmw, page, vma, 0, 0);

	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0);

	int swapped;

	int err = -EFAULT;

	struct mmu_notifier_range range;

	bool anon_exclusive;

	pte_t entry;



	pvmw.address = page_address_in_vma(page, vma);

	if (WARN_ON_ONCE(folio_test_large(folio)))

		return err;



	pvmw.address = page_address_in_vma(&folio->page, vma);

	if (pvmw.address == -EFAULT)

		goto out;



	BUG_ON(PageTransCompound(page));



	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address,

				pvmw.address + PAGE_SIZE);

	mmu_notifier_invalidate_range_start(&range);
@@ -1315,12 +1316,12 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, 
	if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?"))

		goto out_unlock;



	anon_exclusive = PageAnonExclusive(page);

	anon_exclusive = PageAnonExclusive(&folio->page);

	entry = ptep_get(pvmw.pte);

	if (pte_write(entry) || pte_dirty(entry) ||

	    anon_exclusive || mm_tlb_flush_pending(mm)) {

		swapped = PageSwapCache(page);

		flush_cache_page(vma, pvmw.address, page_to_pfn(page));

		swapped = folio_test_swapcache(folio);

		flush_cache_page(vma, pvmw.address, folio_pfn(folio));

		/*

		 * Ok this is tricky, when get_user_pages_fast() run it doesn't

		 * take any lock, therefore the check that we are going to make
@@ -1340,20 +1341,20 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, 
		 * Check that no O_DIRECT or similar I/O is in progress on the

		 * page

		 */

		if (page_mapcount(page) + 1 + swapped != page_count(page)) {

		if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) {

			set_pte_at(mm, pvmw.address, pvmw.pte, entry);

			goto out_unlock;

		}



		/* See folio_try_share_anon_rmap_pte(): clear PTE first. */

		if (anon_exclusive &&

		    folio_try_share_anon_rmap_pte(page_folio(page), page)) {

		    folio_try_share_anon_rmap_pte(folio, &folio->page)) {

			set_pte_at(mm, pvmw.address, pvmw.pte, entry);

			goto out_unlock;

		}



		if (pte_dirty(entry))

			set_page_dirty(page);

			folio_mark_dirty(folio);

		entry = pte_mkclean(entry);



		if (pte_write(entry))
@@ -1519,7 +1520,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, 
	 * ptes are necessarily already write-protected.  But in either

	 * case, we need to lock and check page_count is not raised.

	 */

	if (write_protect_page(vma, page, &orig_pte) == 0) {

	if (write_protect_page(vma, page_folio(page), &orig_pte) == 0) {

		if (!kpage) {

			/*

			 * While we hold page lock, upgrade page from