mm/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails

Simple walk_page_range() users should set ACTION_AGAIN to retry when
pte_offset_map_lock() fails.

No need to check pmd_trans_unstable(): that was precisely to avoid the
possiblity of calling pte_offset_map() on a racily removed or inserted THP
entry, but such cases are now safely handled inside it.  Likewise there is
no need to check pmd_none() or pmd_bad() before calling it.

Link: https://lkml.kernel.org/r/c77d9d10-3aad-e3ce-4896-99e91c7947f3@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: SeongJae Park <sj@kernel.org> for mm/damon part
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: 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>

Author: Hugh Dickins

fs/proc/task_mmu.c

@@ -631,14 +631,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		goto out;
 	}
 
-	if (pmd_trans_unstable(pmd))
-		goto out;
-	/*
-	 * The mmap_lock held all the way back in m_start() is what
-	 * keeps khugepaged out of here and from collapsing things
-	 * in here.
-	 */
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (; addr != end; pte++, addr += PAGE_SIZE)
 		smaps_pte_entry(pte, addr, walk);
 	pte_unmap_unlock(pte - 1, ptl);
@@ -1191,10 +1188,11 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		return 0;
 	}
 
-	if (pmd_trans_unstable(pmd))
-		return 0;
-
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
 
@@ -1538,16 +1536,17 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		spin_unlock(ptl);
 		return err;
 	}
-
-	if (pmd_trans_unstable(pmdp))
-		return 0;
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 	/*
 	 * We can assume that @vma always points to a valid one and @end never
 	 * goes beyond vma->vm_end.
 	 */
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return err;
+	}
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		pagemap_entry_t pme;
 
@@ -1887,11 +1886,12 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		spin_unlock(ptl);
 		return 0;
 	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
 #endif
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	do {
 		struct page *page = can_gather_numa_stats(*pte, vma, addr);
 		if (!page)

mm/damon/vaddr.c

@@ -318,9 +318,11 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
 		spin_unlock(ptl);
 	}
 
-	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		return 0;
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	if (!pte_present(*pte))
 		goto out;
 	damon_ptep_mkold(pte, walk->vma, addr);
@@ -464,9 +466,11 @@ static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr,
 regular_page:
 #endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
 
-	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		return -EINVAL;
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	if (!pte_present(*pte))
 		goto out;
 	folio = damon_get_folio(pte_pfn(*pte));

mm/mempolicy.c

@@ -514,10 +514,11 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
 	if (ptl)
 		return queue_folios_pmd(pmd, ptl, addr, end, walk);
 
-	if (pmd_trans_unstable(pmd))
-		return 0;
-
 	mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
 			continue;

mm/mincore.c

@@ -113,12 +113,11 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		goto out;
 	}
 
-	if (pmd_trans_unstable(pmd)) {
-		__mincore_unmapped_range(addr, end, vma, vec);
-		goto out;
-	}
-
 	ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!ptep) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (; addr != end; ptep++, addr += PAGE_SIZE) {
 		pte_t pte = *ptep;
 

mm/mlock.c

@@ -329,6 +329,10 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 	}
 
 	start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!start_pte) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 	for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
 			continue;