linux-kernel - [PATCH 53/75] mm/rmap: Convert make_device_exclusive

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri,  4 Feb 2022 19:58:30 +0000
From:   "Matthew Wilcox (Oracle)" <willy@...radead.org>
To:     linux-mm@...ck.org
Cc:     "Matthew Wilcox (Oracle)" <willy@...radead.org>,
        linux-kernel@...r.kernel.org
Subject: [PATCH 53/75] mm/rmap: Convert make_device_exclusive_range() to use folios

Move the PageTail check earlier so we can avoid even taking the page
lock on tail pages.  Otherwise, this is a straightforward use of
folios throughout.

Signed-off-by: Matthew Wilcox (Oracle) <willy@...radead.org>
---
 mm/rmap.c | 39 +++++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 4cfac67e328c..ffc1b2f0cf24 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2088,6 +2088,7 @@ struct make_exclusive_args {
 static bool page_make_device_exclusive_one(struct page *page,
 		struct vm_area_struct *vma, unsigned long address, void *priv)
 {
+	struct folio *folio = page_folio(page);
 	struct mm_struct *mm = vma->vm_mm;
 	struct page_vma_mapped_walk pvmw = {
 		.vma = vma,
@@ -2104,12 +2105,13 @@ static bool page_make_device_exclusive_one(struct page *page,
 	pvmw_set_page(&pvmw, page);
 	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
 				      vma->vm_mm, address, min(vma->vm_end,
-				      address + page_size(page)), args->owner);
+				      address + folio_size(folio)),
+				      args->owner);
 	mmu_notifier_invalidate_range_start(&range);
 
 	while (page_vma_mapped_walk(&pvmw)) {
 		/* Unexpected PMD-mapped THP? */
-		VM_BUG_ON_PAGE(!pvmw.pte, page);
+		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
 
 		if (!pte_present(*pvmw.pte)) {
 			ret = false;
@@ -2117,16 +2119,17 @@ static bool page_make_device_exclusive_one(struct page *page,
 			break;
 		}
 
-		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		subpage = folio_page(folio,
+				pte_pfn(*pvmw.pte) - folio_pfn(folio));
 		address = pvmw.address;
 
 		/* Nuke the page table entry. */
 		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
 		pteval = ptep_clear_flush(vma, address, pvmw.pte);
 
-		/* Move the dirty bit to the page. Now the pte is gone. */
+		/* Set the dirty flag on the folio now the pte is gone. */
 		if (pte_dirty(pteval))
-			set_page_dirty(page);
+			folio_mark_dirty(folio);
 
 		/*
 		 * Check that our target page is still mapped at the expected
@@ -2181,8 +2184,8 @@ static bool page_make_device_exclusive_one(struct page *page,
  * Returns false if the page is still mapped, or if it could not be unmapped
  * from the expected address. Otherwise returns true (success).
  */
-static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm,
-				unsigned long address, void *owner)
+static bool folio_make_device_exclusive(struct folio *folio,
+		struct mm_struct *mm, unsigned long address, void *owner)
 {
 	struct make_exclusive_args args = {
 		.mm = mm,
@@ -2198,16 +2201,15 @@ static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm,
 	};
 
 	/*
-	 * Restrict to anonymous pages for now to avoid potential writeback
-	 * issues. Also tail pages shouldn't be passed to rmap_walk so skip
-	 * those.
+	 * Restrict to anonymous folios for now to avoid potential writeback
+	 * issues.
 	 */
-	if (!PageAnon(page) || PageTail(page))
+	if (!folio_test_anon(folio))
 		return false;
 
-	rmap_walk(page, &rwc);
+	rmap_walk(&folio->page, &rwc);
 
-	return args.valid && !page_mapcount(page);
+	return args.valid && !folio_mapcount(folio);
 }
 
 /**
@@ -2245,15 +2247,16 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
 		return npages;
 
 	for (i = 0; i < npages; i++, start += PAGE_SIZE) {
-		if (!trylock_page(pages[i])) {
-			put_page(pages[i]);
+		struct folio *folio = page_folio(pages[i]);
+		if (PageTail(pages[i]) || !folio_trylock(folio)) {
+			folio_put(folio);
 			pages[i] = NULL;
 			continue;
 		}
 
-		if (!page_make_device_exclusive(pages[i], mm, start, owner)) {
-			unlock_page(pages[i]);
-			put_page(pages[i]);
+		if (!folio_make_device_exclusive(folio, mm, start, owner)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			pages[i] = NULL;
 		}
 	}
-- 
2.34.1