Merge tag 'mm-hotfixes-stable-2024-04-18-14-41' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "15 hotfixes. 9 are cc:stable and the remainder address post-6.8 issues
  or aren't considered suitable for backporting.

  There are a significant number of fixups for this cycle's page_owner
  changes (series "page_owner: print stacks and their outstanding
  allocations"). Apart from that, singleton changes all over, mainly in
  MM"

* tag 'mm-hotfixes-stable-2024-04-18-14-41' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  nilfs2: fix OOB in nilfs_set_de_type
  MAINTAINERS: update Naoya Horiguchi's email address
  fork: defer linking file vma until vma is fully initialized
  mm/shmem: inline shmem_is_huge() for disabled transparent hugepages
  mm,page_owner: defer enablement of static branch
  Squashfs: check the inode number is not the invalid value of zero
  mm,swapops: update check in is_pfn_swap_entry for hwpoison entries
  mm/memory-failure: fix deadlock when hugetlb_optimize_vmemmap is enabled
  mm/userfaultfd: allow hugetlb change protection upon poison entry
  mm,page_owner: fix printing of stack records
  mm,page_owner: fix accounting of pages when migrating
  mm,page_owner: fix refcount imbalance
  mm,page_owner: update metadata for tail pages
  userfaultfd: change src_folio after ensuring it's unpinned in UFFDIO_MOVE
  mm/madvise: make MADV_POPULATE_(READ|WRITE) handle VM_FAULT_RETRY properly

.mailmap

@@ -446,7 +446,8 @@ Mythri P K <[email protected]>
 Nadav Amit <[email protected]> <[email protected]>
 Nadav Amit <[email protected]> <[email protected]>
 Nadia Yvette Chambers <[email protected]> William Lee Irwin III <[email protected]>
-Naoya Horiguchi <[email protected]> <[email protected]>
+Naoya Horiguchi <[email protected]> <[email protected]>
+Naoya Horiguchi <[email protected]> <[email protected]>
 Nathan Chancellor <[email protected]> <[email protected]>
 Neeraj Upadhyay <[email protected]> <[email protected]>
 Neil Armstrong <[email protected]> <[email protected]>

Documentation/mm/page_owner.rst

@@ -24,10 +24,10 @@ fragmentation statistics can be obtained through gfp flag information of
 each page. It is already implemented and activated if page owner is
 enabled. Other usages are more than welcome.
 
-It can also be used to show all the stacks and their outstanding
-allocations, which gives us a quick overview of where the memory is going
-without the need to screen through all the pages and match the allocation
-and free operation.
+It can also be used to show all the stacks and their current number of
+allocated base pages, which gives us a quick overview of where the memory
+is going without the need to screen through all the pages and match the
+allocation and free operation.
 
 page owner is disabled by default. So, if you'd like to use it, you need
 to add "page_owner=on" to your boot cmdline. If the kernel is built
@@ -75,42 +75,45 @@ Usage
 
 	cat /sys/kernel/debug/page_owner_stacks/show_stacks > stacks.txt
 	cat stacks.txt
-	 prep_new_page+0xa9/0x120
-	 get_page_from_freelist+0x7e6/0x2140
-	 __alloc_pages+0x18a/0x370
-	 new_slab+0xc8/0x580
-	 ___slab_alloc+0x1f2/0xaf0
-	 __slab_alloc.isra.86+0x22/0x40
-	 kmem_cache_alloc+0x31b/0x350
-	 __khugepaged_enter+0x39/0x100
-	 dup_mmap+0x1c7/0x5ce
-	 copy_process+0x1afe/0x1c90
-	 kernel_clone+0x9a/0x3c0
-	 __do_sys_clone+0x66/0x90
-	 do_syscall_64+0x7f/0x160
-	 entry_SYSCALL_64_after_hwframe+0x6c/0x74
-	stack_count: 234
+	 post_alloc_hook+0x177/0x1a0
+	 get_page_from_freelist+0xd01/0xd80
+	 __alloc_pages+0x39e/0x7e0
+	 allocate_slab+0xbc/0x3f0
+	 ___slab_alloc+0x528/0x8a0
+	 kmem_cache_alloc+0x224/0x3b0
+	 sk_prot_alloc+0x58/0x1a0
+	 sk_alloc+0x32/0x4f0
+	 inet_create+0x427/0xb50
+	 __sock_create+0x2e4/0x650
+	 inet_ctl_sock_create+0x30/0x180
+	 igmp_net_init+0xc1/0x130
+	 ops_init+0x167/0x410
+	 setup_net+0x304/0xa60
+	 copy_net_ns+0x29b/0x4a0
+	 create_new_namespaces+0x4a1/0x820
+	nr_base_pages: 16
 	...
 	...
 	echo 7000 > /sys/kernel/debug/page_owner_stacks/count_threshold
 	cat /sys/kernel/debug/page_owner_stacks/show_stacks> stacks_7000.txt
 	cat stacks_7000.txt
-	 prep_new_page+0xa9/0x120
-	 get_page_from_freelist+0x7e6/0x2140
-	 __alloc_pages+0x18a/0x370
-	 alloc_pages_mpol+0xdf/0x1e0
-	 folio_alloc+0x14/0x50
-	 filemap_alloc_folio+0xb0/0x100
-	 page_cache_ra_unbounded+0x97/0x180
-	 filemap_fault+0x4b4/0x1200
-	 __do_fault+0x2d/0x110
-	 do_pte_missing+0x4b0/0xa30
-	 __handle_mm_fault+0x7fa/0xb70
-	 handle_mm_fault+0x125/0x300
-	 do_user_addr_fault+0x3c9/0x840
-	 exc_page_fault+0x68/0x150
-	 asm_exc_page_fault+0x22/0x30
-	stack_count: 8248
+	 post_alloc_hook+0x177/0x1a0
+	 get_page_from_freelist+0xd01/0xd80
+	 __alloc_pages+0x39e/0x7e0
+	 alloc_pages_mpol+0x22e/0x490
+	 folio_alloc+0xd5/0x110
+	 filemap_alloc_folio+0x78/0x230
+	 page_cache_ra_order+0x287/0x6f0
+	 filemap_get_pages+0x517/0x1160
+	 filemap_read+0x304/0x9f0
+	 xfs_file_buffered_read+0xe6/0x1d0 [xfs]
+	 xfs_file_read_iter+0x1f0/0x380 [xfs]
+	 __kernel_read+0x3b9/0x730
+	 kernel_read_file+0x309/0x4d0
+	 __do_sys_finit_module+0x381/0x730
+	 do_syscall_64+0x8d/0x150
+	 entry_SYSCALL_64_after_hwframe+0x62/0x6a
+	nr_base_pages: 20824
 	...
 
 	cat /sys/kernel/debug/page_owner > page_owner_full.txt

MAINTAINERS

@@ -10024,7 +10024,7 @@ F:	drivers/media/platform/st/sti/hva
 
 HWPOISON MEMORY FAILURE HANDLING
 M:	Miaohe Lin <[email protected]>
-R:	Naoya Horiguchi <naoya.horiguchi@nec.com>
+R:	Naoya Horiguchi <nao.horiguchi@gmail.com>
 L:	[email protected]
 S:	Maintained
 F:	mm/hwpoison-inject.c

fs/nilfs2/dir.c

@@ -240,7 +240,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = {
 
 #define S_SHIFT 12
 static unsigned char
-nilfs_type_by_mode[S_IFMT >> S_SHIFT] = {
+nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
 	[S_IFREG >> S_SHIFT]	= NILFS_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= NILFS_FT_DIR,
 	[S_IFCHR >> S_SHIFT]	= NILFS_FT_CHRDEV,

fs/squashfs/inode.c

@@ -48,6 +48,10 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode,
 	gid_t i_gid;
 	int err;
 
+	inode->i_ino = le32_to_cpu(sqsh_ino->inode_number);
+	if (inode->i_ino == 0)
+		return -EINVAL;
+
 	err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid);
 	if (err)
 		return err;
@@ -58,7 +62,6 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode,
 
 	i_uid_write(inode, i_uid);
 	i_gid_write(inode, i_gid);
-	inode->i_ino = le32_to_cpu(sqsh_ino->inode_number);
 	inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0);
 	inode_set_atime(inode, inode_get_mtime_sec(inode), 0);
 	inode_set_ctime(inode, inode_get_mtime_sec(inode), 0);

include/linux/shmem_fs.h

@@ -110,8 +110,17 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
 int shmem_unuse(unsigned int type);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
 			  struct mm_struct *mm, unsigned long vm_flags);
+#else
+static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
+					  struct mm_struct *mm, unsigned long vm_flags)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SHMEM
 extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
 #else

include/linux/swapops.h

@@ -390,6 +390,35 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry)
 }
 #endif	/* CONFIG_MIGRATION */
 
+#ifdef CONFIG_MEMORY_FAILURE
+
+/*
+ * Support for hardware poisoned pages
+ */
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+	return swp_entry(SWP_HWPOISON, page_to_pfn(page));
+}
+
+static inline int is_hwpoison_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_HWPOISON;
+}
+
+#else
+
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+	return swp_entry(0, 0);
+}
+
+static inline int is_hwpoison_entry(swp_entry_t swp)
+{
+	return 0;
+}
+#endif
+
 typedef unsigned long pte_marker;
 
 #define  PTE_MARKER_UFFD_WP			BIT(0)
@@ -483,16 +512,17 @@ static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry)
 
 /*
  * A pfn swap entry is a special type of swap entry that always has a pfn stored
- * in the swap offset. They are used to represent unaddressable device memory
- * and to restrict access to a page undergoing migration.
+ * in the swap offset. They can either be used to represent unaddressable device
+ * memory, to restrict access to a page undergoing migration or to represent a
+ * pfn which has been hwpoisoned and unmapped.
  */
 static inline bool is_pfn_swap_entry(swp_entry_t entry)
 {
 	/* Make sure the swp offset can always store the needed fields */
 	BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS);
 
 	return is_migration_entry(entry) || is_device_private_entry(entry) ||
-	       is_device_exclusive_entry(entry);
+	       is_device_exclusive_entry(entry) || is_hwpoison_entry(entry);
 }
 
 struct page_vma_mapped_walk;
@@ -561,35 +591,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
 }
 #endif  /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
 
-#ifdef CONFIG_MEMORY_FAILURE
-
-/*
- * Support for hardware poisoned pages
- */
-static inline swp_entry_t make_hwpoison_entry(struct page *page)
-{
-	BUG_ON(!PageLocked(page));
-	return swp_entry(SWP_HWPOISON, page_to_pfn(page));
-}
-
-static inline int is_hwpoison_entry(swp_entry_t entry)
-{
-	return swp_type(entry) == SWP_HWPOISON;
-}
-
-#else
-
-static inline swp_entry_t make_hwpoison_entry(struct page *page)
-{
-	return swp_entry(0, 0);
-}
-
-static inline int is_hwpoison_entry(swp_entry_t swp)
-{
-	return 0;
-}
-#endif
-
 static inline int non_swap_entry(swp_entry_t entry)
 {
 	return swp_type(entry) >= MAX_SWAPFILES;

kernel/fork.c

@@ -714,6 +714,23 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		} else if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		vm_flags_clear(tmp, VM_LOCKED_MASK);
+		/*
+		 * Copy/update hugetlb private vma information.
+		 */
+		if (is_vm_hugetlb_page(tmp))
+			hugetlb_dup_vma_private(tmp);
+
+		/*
+		 * Link the vma into the MT. After using __mt_dup(), memory
+		 * allocation is not necessary here, so it cannot fail.
+		 */
+		vma_iter_bulk_store(&vmi, tmp);
+
+		mm->map_count++;
+
+		if (tmp->vm_ops && tmp->vm_ops->open)
+			tmp->vm_ops->open(tmp);
+
 		file = tmp->vm_file;
 		if (file) {
 			struct address_space *mapping = file->f_mapping;
@@ -730,25 +747,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			i_mmap_unlock_write(mapping);
 		}
 
-		/*
-		 * Copy/update hugetlb private vma information.
-		 */
-		if (is_vm_hugetlb_page(tmp))
-			hugetlb_dup_vma_private(tmp);
-
-		/*
-		 * Link the vma into the MT. After using __mt_dup(), memory
-		 * allocation is not necessary here, so it cannot fail.
-		 */
-		vma_iter_bulk_store(&vmi, tmp);
-
-		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
 			retval = copy_page_range(tmp, mpnt);
 
-		if (tmp->vm_ops && tmp->vm_ops->open)
-			tmp->vm_ops->open(tmp);
-
 		if (retval) {
 			mpnt = vma_next(&vmi);
 			goto loop_out;

mm/gup.c

@@ -1206,6 +1206,22 @@ static long __get_user_pages(struct mm_struct *mm,
 
 		/* first iteration or cross vma bound */
 		if (!vma || start >= vma->vm_end) {
+			/*
+			 * MADV_POPULATE_(READ|WRITE) wants to handle VMA
+			 * lookups+error reporting differently.
+			 */
+			if (gup_flags & FOLL_MADV_POPULATE) {
+				vma = vma_lookup(mm, start);
+				if (!vma) {
+					ret = -ENOMEM;
+					goto out;
+				}
+				if (check_vma_flags(vma, gup_flags)) {
+					ret = -EINVAL;
+					goto out;
+				}
+				goto retry;
+			}
 			vma = gup_vma_lookup(mm, start);
 			if (!vma && in_gate_area(mm, start)) {
 				ret = get_gate_page(mm, start & PAGE_MASK,
@@ -1685,35 +1701,35 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 }
 
 /*
- * faultin_vma_page_range() - populate (prefault) page tables inside the
- *			      given VMA range readable/writable
+ * faultin_page_range() - populate (prefault) page tables inside the
+ *			  given range readable/writable
  *
  * This takes care of mlocking the pages, too, if VM_LOCKED is set.
  *
- * @vma: target vma
+ * @mm: the mm to populate page tables in
  * @start: start address
  * @end: end address
  * @write: whether to prefault readable or writable
  * @locked: whether the mmap_lock is still held
  *
- * Returns either number of processed pages in the vma, or a negative error
- * code on error (see __get_user_pages()).
+ * Returns either number of processed pages in the MM, or a negative error
+ * code on error (see __get_user_pages()). Note that this function reports
+ * errors related to VMAs, such as incompatible mappings, as expected by
+ * MADV_POPULATE_(READ|WRITE).
  *
- * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and
- * covered by the VMA. If it's released, *@locked will be set to 0.
+ * The range must be page-aligned.
+ *
+ * mm->mmap_lock must be held. If it's released, *@locked will be set to 0.
  */
-long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
-			    unsigned long end, bool write, int *locked)
+long faultin_page_range(struct mm_struct *mm, unsigned long start,
+			unsigned long end, bool write, int *locked)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	unsigned long nr_pages = (end - start) / PAGE_SIZE;
 	int gup_flags;
 	long ret;
 
 	VM_BUG_ON(!PAGE_ALIGNED(start));
 	VM_BUG_ON(!PAGE_ALIGNED(end));
-	VM_BUG_ON_VMA(start < vma->vm_start, vma);
-	VM_BUG_ON_VMA(end > vma->vm_end, vma);
 	mmap_assert_locked(mm);
 
 	/*
@@ -1725,19 +1741,13 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
 	 *		  a poisoned page.
 	 * !FOLL_FORCE: Require proper access permissions.
 	 */
-	gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE;
+	gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE |
+		    FOLL_MADV_POPULATE;
 	if (write)
 		gup_flags |= FOLL_WRITE;
 
-	/*
-	 * We want to report -EINVAL instead of -EFAULT for any permission
-	 * problems or incompatible mappings.
-	 */
-	if (check_vma_flags(vma, gup_flags))
-		return -EINVAL;
-
-	ret = __get_user_pages(mm, start, nr_pages, gup_flags,
-			       NULL, locked);
+	ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked,
+				      gup_flags);
 	lru_add_drain();
 	return ret;
 }