Merge tag 'mm-hotfixes-stable-2022-07-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull hotfixes from Andrew Morton:
 "Mainly MM fixes. About half for issues which were introduced after
  5.18 and the remainder for longer-term issues"

* tag 'mm-hotfixes-stable-2022-07-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm: split huge PUD on wp_huge_pud fallback
  nilfs2: fix incorrect masking of permission flags for symlinks
  mm/rmap: fix dereferencing invalid subpage pointer in try_to_migrate_one()
  riscv/mm: fix build error while PAGE_TABLE_CHECK enabled without MMU
  Documentation: highmem: use literal block for code example in highmem.h comment
  mm: sparsemem: fix missing higher order allocation splitting
  mm/damon: use set_huge_pte_at() to make huge pte old
  sh: convert nommu io{re,un}map() to static inline functions
  mm: userfaultfd: fix UFFDIO_CONTINUE on fallocated shmem pages

Author: torvalds

arch/riscv/Kconfig

@@ -38,7 +38,7 @@ config RISCV
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
-	select ARCH_SUPPORTS_PAGE_TABLE_CHECK
+	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU

arch/sh/include/asm/io.h

@@ -271,8 +271,12 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 #endif /* CONFIG_HAVE_IOREMAP_PROT */
 
 #else /* CONFIG_MMU */
-#define iounmap(addr)		do { } while (0)
-#define ioremap(offset, size)	((void __iomem *)(unsigned long)(offset))
+static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
+{
+	return (void __iomem *)(unsigned long)offset;
+}
+
+static inline void iounmap(volatile void __iomem *addr) { }
 #endif /* CONFIG_MMU */
 
 #define ioremap_uc	ioremap

fs/nilfs2/nilfs.h

@@ -198,6 +198,9 @@ static inline int nilfs_acl_chmod(struct inode *inode)
 
 static inline int nilfs_init_acl(struct inode *inode, struct inode *dir)
 {
+	if (S_ISLNK(inode->i_mode))
+		return 0;
+
 	inode->i_mode &= ~current_umask();
 	return 0;
 }

include/linux/highmem.h

@@ -149,19 +149,19 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset);
  * It is used in atomic context when code wants to access the contents of a
  * page that might be allocated from high memory (see __GFP_HIGHMEM), for
  * example a page in the pagecache.  The API has two functions, and they
- * can be used in a manner similar to the following:
+ * can be used in a manner similar to the following::
  *
- * -- Find the page of interest. --
- * struct page *page = find_get_page(mapping, offset);
+ *   // Find the page of interest.
+ *   struct page *page = find_get_page(mapping, offset);
  *
- * -- Gain access to the contents of that page. --
- * void *vaddr = kmap_atomic(page);
+ *   // Gain access to the contents of that page.
+ *   void *vaddr = kmap_atomic(page);
  *
- * -- Do something to the contents of that page. --
- * memset(vaddr, 0, PAGE_SIZE);
+ *   // Do something to the contents of that page.
+ *   memset(vaddr, 0, PAGE_SIZE);
  *
- * -- Unmap that page. --
- * kunmap_atomic(vaddr);
+ *   // Unmap that page.
+ *   kunmap_atomic(vaddr);
  *
  * Note that the kunmap_atomic() call takes the result of the kmap_atomic()
  * call, not the argument.

mm/damon/vaddr.c

@@ -336,8 +336,7 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm,
 	if (pte_young(entry)) {
 		referenced = true;
 		entry = pte_mkold(entry);
-		huge_ptep_set_access_flags(vma, addr, pte, entry,
-					   vma->vm_flags & VM_WRITE);
+		set_huge_pte_at(mm, addr, pte, entry);
 	}
 
 #ifdef CONFIG_MMU_NOTIFIER

mm/memory.c

@@ -4798,6 +4798,19 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
 
 static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 {
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+	/* No support for anonymous transparent PUD pages yet */
+	if (vma_is_anonymous(vmf->vma))
+		return VM_FAULT_FALLBACK;
+	if (vmf->vma->vm_ops->huge_fault)
+		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+	return VM_FAULT_FALLBACK;
+}
+
+static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
+{
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	/* No support for anonymous transparent PUD pages yet */
@@ -4812,19 +4825,7 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 split:
 	/* COW or write-notify not handled on PUD level: split pud.*/
 	__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-	return VM_FAULT_FALLBACK;
-}
-
-static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	/* No support for anonymous transparent PUD pages yet */
-	if (vma_is_anonymous(vmf->vma))
-		return VM_FAULT_FALLBACK;
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 	return VM_FAULT_FALLBACK;
 }
 

mm/rmap.c

@@ -1899,8 +1899,23 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		/* Unexpected PMD-mapped THP? */
 		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
 
-		subpage = folio_page(folio,
-				pte_pfn(*pvmw.pte) - folio_pfn(folio));
+		if (folio_is_zone_device(folio)) {
+			/*
+			 * Our PTE is a non-present device exclusive entry and
+			 * calculating the subpage as for the common case would
+			 * result in an invalid pointer.
+			 *
+			 * Since only PAGE_SIZE pages can currently be
+			 * migrated, just set it to page. This will need to be
+			 * changed when hugepage migrations to device private
+			 * memory are supported.
+			 */
+			VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio);
+			subpage = &folio->page;
+		} else {
+			subpage = folio_page(folio,
+					pte_pfn(*pvmw.pte) - folio_pfn(folio));
+		}
 		address = pvmw.address;
 		anon_exclusive = folio_test_anon(folio) &&
 				 PageAnonExclusive(subpage);
@@ -1993,15 +2008,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			/*
 			 * No need to invalidate here it will synchronize on
 			 * against the special swap migration pte.
-			 *
-			 * The assignment to subpage above was computed from a
-			 * swap PTE which results in an invalid pointer.
-			 * Since only PAGE_SIZE pages can currently be
-			 * migrated, just set it to page. This will need to be
-			 * changed when hugepage migrations to device private
-			 * memory are supported.
 			 */
-			subpage = &folio->page;
 		} else if (PageHWPoison(subpage)) {
 			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
 			if (folio_test_hugetlb(folio)) {

mm/sparse-vmemmap.c

@@ -78,6 +78,14 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 
 	spin_lock(&init_mm.page_table_lock);
 	if (likely(pmd_leaf(*pmd))) {
+		/*
+		 * Higher order allocations from buddy allocator must be able to
+		 * be treated as indepdenent small pages (as they can be freed
+		 * individually).
+		 */
+		if (!PageReserved(page))
+			split_page(page, get_order(PMD_SIZE));
+
 		/* Make pte visible before pmd. See comment in pmd_install(). */
 		smp_wmb();
 		pmd_populate_kernel(&init_mm, pmd, pgtable);

mm/userfaultfd.c

@@ -246,7 +246,10 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
 	struct page *page;
 	int ret;
 
-	ret = shmem_getpage(inode, pgoff, &page, SGP_READ);
+	ret = shmem_getpage(inode, pgoff, &page, SGP_NOALLOC);
+	/* Our caller expects us to return -EFAULT if we failed to find page. */
+	if (ret == -ENOENT)
+		ret = -EFAULT;
 	if (ret)
 		goto out;
 	if (!page) {