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.

Link: https://lkml.kernel.org/r/c4d831-13c3-9dfd-70c2-64514ad951fd@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zack Rusin <zackr@vmware.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/swapfile.c

@@ -1757,7 +1757,7 @@ 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;
 	}
@@ -1810,7 +1810,8 @@ setpte:
 	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);
@@ -1822,17 +1823,22 @@ 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;
@@ -1843,6 +1849,8 @@ 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;
@@ -1861,8 +1869,7 @@ 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;
 		}
 
@@ -1872,20 +1879,17 @@ 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,
@@ -1900,8 +1904,6 @@ 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;