linux-kernel - [PATCH v2 22/32] mm/swapoff: allow pte_offset_map[

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]

Message-ID: <c4d831-13c3-9dfd-70c2-64514ad951fd@google.com>
Date:   Thu, 8 Jun 2023 18:36:11 -0700 (PDT)
From:   Hugh Dickins <hughd@...gle.com>
To:     Andrew Morton <akpm@...ux-foundation.org>
cc:     Mike Kravetz <mike.kravetz@...cle.com>,
        Mike Rapoport <rppt@...nel.org>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Matthew Wilcox <willy@...radead.org>,
        David Hildenbrand <david@...hat.com>,
        Suren Baghdasaryan <surenb@...gle.com>,
        Qi Zheng <zhengqi.arch@...edance.com>,
        Yang Shi <shy828301@...il.com>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Peter Xu <peterx@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Will Deacon <will@...nel.org>, Yu Zhao <yuzhao@...gle.com>,
        Alistair Popple <apopple@...dia.com>,
        Ralph Campbell <rcampbell@...dia.com>,
        Ira Weiny <ira.weiny@...el.com>,
        Steven Price <steven.price@....com>,
        SeongJae Park <sj@...nel.org>,
        Lorenzo Stoakes <lstoakes@...il.com>,
        Huang Ying <ying.huang@...el.com>,
        Naoya Horiguchi <naoya.horiguchi@....com>,
        Christophe Leroy <christophe.leroy@...roup.eu>,
        Zack Rusin <zackr@...are.com>, Jason Gunthorpe <jgg@...pe.ca>,
        Axel Rasmussen <axelrasmussen@...gle.com>,
        Anshuman Khandual <anshuman.khandual@....com>,
        Pasha Tatashin <pasha.tatashin@...een.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Minchan Kim <minchan@...nel.org>,
        Christoph Hellwig <hch@...radead.org>,
        Song Liu <song@...nel.org>,
        Thomas Hellstrom <thomas.hellstrom@...ux.intel.com>,
        Ryan Roberts <ryan.roberts@....com>,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: [PATCH v2 22/32] mm/swapoff: allow pte_offset_map[_lock]() to fail

Adjust unuse_pte() and unuse_pte_range() to allow pte_offset_map_lock()
and pte_offset_map() failure; remove pmd_none_or_trans_huge_or_clear_bad()
from unuse_pmd_range() now that pte_offset_map() does all that itself.

Signed-off-by: Hugh Dickins <hughd@...gle.com>
---
 mm/swapfile.c | 38 ++++++++++++++++++++------------------
 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 274bbf797480..12d204e6dae2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1774,7 +1774,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		hwposioned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
+	if (unlikely(!pte || !pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
 		ret = 0;
 		goto out;
 	}
@@ -1827,7 +1827,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	set_pte_at(vma->vm_mm, addr, pte, new_pte);
 	swap_free(entry);
 out:
-	pte_unmap_unlock(pte, ptl);
+	if (pte)
+		pte_unmap_unlock(pte, ptl);
 	if (page != swapcache) {
 		unlock_page(page);
 		put_page(page);
@@ -1839,17 +1840,22 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned int type)
 {
-	swp_entry_t entry;
-	pte_t *pte;
+	pte_t *pte = NULL;
 	struct swap_info_struct *si;
-	int ret = 0;
 
 	si = swap_info[type];
-	pte = pte_offset_map(pmd, addr);
 	do {
 		struct folio *folio;
 		unsigned long offset;
 		unsigned char swp_count;
+		swp_entry_t entry;
+		int ret;
+
+		if (!pte++) {
+			pte = pte_offset_map(pmd, addr);
+			if (!pte)
+				break;
+		}
 
 		if (!is_swap_pte(*pte))
 			continue;
@@ -1860,6 +1866,8 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 		offset = swp_offset(entry);
 		pte_unmap(pte);
+		pte = NULL;
+
 		folio = swap_cache_get_folio(entry, vma, addr);
 		if (!folio) {
 			struct page *page;
@@ -1878,8 +1886,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		if (!folio) {
 			swp_count = READ_ONCE(si->swap_map[offset]);
 			if (swp_count == 0 || swp_count == SWAP_MAP_BAD)
-				goto try_next;
-
+				continue;
 			return -ENOMEM;
 		}
 
@@ -1889,20 +1896,17 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		if (ret < 0) {
 			folio_unlock(folio);
 			folio_put(folio);
-			goto out;
+			return ret;
 		}
 
 		folio_free_swap(folio);
 		folio_unlock(folio);
 		folio_put(folio);
-try_next:
-		pte = pte_offset_map(pmd, addr);
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
+	} while (addr += PAGE_SIZE, addr != end);
 
-	ret = 0;
-out:
-	return ret;
+	if (pte)
+		pte_unmap(pte);
+	return 0;
 }
 
 static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -1917,8 +1921,6 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	do {
 		cond_resched();
 		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
-			continue;
 		ret = unuse_pte_range(vma, pmd, addr, next, type);
 		if (ret)
 			return ret;
-- 
2.35.3