Merge tag 'mm-hotfixes-stable-2022-07-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
"Thirteen hotfixes.

Eight are cc:stable and the remainder are for post-5.18 issues or are
too minor to warrant backporting"

* tag 'mm-hotfixes-stable-2022-07-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
mailmap: update Gao Xiang's email addresses
userfaultfd: provide properly masked address for huge-pages
Revert "ocfs2: mount shared volume without ha stack"
hugetlb: fix memoryleak in hugetlb_mcopy_atomic_pte
fs: sendfile handles O_NONBLOCK of out_fd
ntfs: fix use-after-free in ntfs_ucsncmp()
secretmem: fix unhandled fault in truncate
mm/hugetlb: separate path for hwpoison entry in copy_hugetlb_page_range()
mm: fix missing wake-up event for FSDAX pages
mm: fix page leak with multiple threads mapping the same page
mailmap: update Seth Forshee's email address
tmpfs: fix the issue that the mount and remount results are inconsistent.
mm: kfence: apply kmemleak_ignore_phys on early allocated pool

.mailmap

···
 Frank Zago <[e-mail]>
 Gao Xiang <[e-mail]> <[e-mail]>
 Gao Xiang <[e-mail]> <[e-mail]>
+Gao Xiang <[e-mail]> <[e-mail]>
+Gao Xiang <[e-mail]> <[e-mail]>
 Gerald Schaefer <[e-mail]> <[e-mail]>
 Gerald Schaefer <[e-mail]> <[e-mail]>
 Gerald Schaefer <[e-mail]> <[e-mail]>
···
 Sebastian Reichel <[e-mail]> <[e-mail]>
 Sebastian Reichel <[e-mail]> <[e-mail]>
 Sedat Dilek <[e-mail]> <[e-mail]>
+Seth Forshee <[e-mail]> <[e-mail]>
 Shiraz Hashim <[e-mail]> <[e-mail]>
 Shuah Khan <[e-mail]> <[e-mail]>
 Shuah Khan <[e-mail]> <[e-mail]>

fs/ntfs/attrib.c

···
 		a = (ATTR_RECORD*)((u8*)ctx->attr +
 				le32_to_cpu(ctx->attr->length));
 	for (;;	a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
-		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_allocated))
+		u8 *mrec_end = (u8 *)ctx->mrec +
+		               le32_to_cpu(ctx->mrec->bytes_allocated);
+		u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
+			       a->name_length * sizeof(ntfschar);
+		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end ||
+		    name_end > mrec_end)
 			break;
 		ctx->attr = a;
 		if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||

fs/ocfs2/ocfs2.h

···
 	OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15,  /* Journal Async Commit */
 	OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
 	OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
-	OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
 };
 
 #define OCFS2_OSB_SOFT_RO	0x0001
···
 
 static inline int ocfs2_mount_local(struct ocfs2_super *osb)
 {
-	return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
-		|| (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
+	return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
 }
 
 static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)

fs/ocfs2/slot_map.c

···
 	int i, ret = -ENOSPC;
 
 	if ((preferred >= 0) && (preferred < si->si_num_slots)) {
-		if (!si->si_slots[preferred].sl_valid ||
-		    !si->si_slots[preferred].sl_node_num) {
+		if (!si->si_slots[preferred].sl_valid) {
 			ret = preferred;
 			goto out;
 		}
 	}
 
 	for(i = 0; i < si->si_num_slots; i++) {
-		if (!si->si_slots[i].sl_valid ||
-		    !si->si_slots[i].sl_node_num) {
+		if (!si->si_slots[i].sl_valid) {
 			ret = i;
 			break;
 		}
···
 	spin_lock(&osb->osb_lock);
 	ocfs2_update_slot_info(si);
 
-	if (ocfs2_mount_local(osb))
-		/* use slot 0 directly in local mode */
-		slot = 0;
-	else {
-		/* search for ourselves first and take the slot if it already
-		 * exists. Perhaps we need to mark this in a variable for our
-		 * own journal recovery? Possibly not, though we certainly
-		 * need to warn to the user */
-		slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+	/* search for ourselves first and take the slot if it already
+	 * exists. Perhaps we need to mark this in a variable for our
+	 * own journal recovery? Possibly not, though we certainly
+	 * need to warn to the user */
+	slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+	if (slot < 0) {
+		/* if no slot yet, then just take 1st available
+		 * one. */
+		slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
 		if (slot < 0) {
-			/* if no slot yet, then just take 1st available
-			 * one. */
-			slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
-			if (slot < 0) {
-				spin_unlock(&osb->osb_lock);
-				mlog(ML_ERROR, "no free slots available!\n");
-				status = -EINVAL;
-				goto bail;
-			}
-		} else
-			printk(KERN_INFO "ocfs2: Slot %d on device (%s) was "
-			       "already allocated to this node!\n",
-			       slot, osb->dev_str);
-	}
+			spin_unlock(&osb->osb_lock);
+			mlog(ML_ERROR, "no free slots available!\n");
+			status = -EINVAL;
+			goto bail;
+		}
+	} else
+		printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+		       "allocated to this node!\n", slot, osb->dev_str);
 
 	ocfs2_set_slot(si, slot, osb->node_num);
 	osb->slot_num = slot;

fs/ocfs2/super.c

···
 	Opt_dir_resv_level,
 	Opt_journal_async_commit,
 	Opt_err_cont,
-	Opt_nocluster,
 	Opt_err,
 };
 
···
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
 	{Opt_journal_async_commit, "journal_async_commit"},
 	{Opt_err_cont, "errors=continue"},
-	{Opt_nocluster, "nocluster"},
 	{Opt_err, NULL}
 };
 
···
 		goto out;
 	}
 
-	tmp = OCFS2_MOUNT_NOCLUSTER;
-	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
-		ret = -EINVAL;
-		mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
-		goto out;
-	}
-
 	tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
 		OCFS2_MOUNT_HB_NONE;
 	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
···
 	}
 
 	if (ocfs2_userspace_stack(osb) &&
-	    !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
 	    strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
 		    OCFS2_STACK_LABEL_LEN)) {
 		mlog(ML_ERROR,
···
 	       osb->dev_str, nodestr, osb->slot_num,
 	       osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
 	       "ordered");
-
-	if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
-	   !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
-		printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
-		       "without cluster aware mode.\n", osb->dev_str);
 
 	atomic_set(&osb->vol_state, VOLUME_MOUNTED);
 	wake_up(&osb->osb_mount_event);
···
 		case Opt_journal_async_commit:
 			mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
 			break;
-		case Opt_nocluster:
-			mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
-			break;
 		default:
 			mlog(ML_ERROR,
 			     "Unrecognized mount option \"%s\" "
···
 
 	if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
 		seq_printf(s, ",journal_async_commit");
-
-	if (opts & OCFS2_MOUNT_NOCLUSTER)
-		seq_printf(s, ",nocluster");
 
 	return 0;
 }

fs/read_write.c

···
 					  count, fl);
 		file_end_write(out.file);
 	} else {
+		if (out.file->f_flags & O_NONBLOCK)
+			fl |= SPLICE_F_NONBLOCK;
+
 		retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
 	}
 

fs/userfaultfd.c

···
 }
 
 static inline struct uffd_msg userfault_msg(unsigned long address,
+					    unsigned long real_address,
 					    unsigned int flags,
 					    unsigned long reason,
 					    unsigned int features)
 {
 	struct uffd_msg msg;
+
 	msg_init(&msg);
 	msg.event = UFFD_EVENT_PAGEFAULT;
 
-	if (!(features & UFFD_FEATURE_EXACT_ADDRESS))
-		address &= PAGE_MASK;
-	msg.arg.pagefault.address = address;
+	msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
+				    real_address : address;
+
 	/*
 	 * These flags indicate why the userfault occurred:
 	 * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
···
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(vmf->real_address, vmf->flags, reason,
-			ctx->features);
+	uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
+				reason, ctx->features);
 	uwq.ctx = ctx;
 	uwq.waken = false;
 

include/linux/mm.h

···
 #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
 DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
 
-bool __put_devmap_managed_page(struct page *page);
-static inline bool put_devmap_managed_page(struct page *page)
+bool __put_devmap_managed_page_refs(struct page *page, int refs);
+static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
 {
 	if (!static_branch_unlikely(&devmap_managed_key))
 		return false;
 	if (!is_zone_device_page(page))
 		return false;
-	return __put_devmap_managed_page(page);
+	return __put_devmap_managed_page_refs(page, refs);
 }
-
 #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
 {
 	return false;
 }
 #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
+
+static inline bool put_devmap_managed_page(struct page *page)
+{
+	return put_devmap_managed_page_refs(page, 1);
+}
 
 /* 127: arbitrary random number, small enough to assemble well */
 #define folio_ref_zero_or_close_to_overflow(folio) \

mm/gup.c

···
 	 * belongs to this folio.
 	 */
 	if (unlikely(page_folio(page) != folio)) {
-		folio_put_refs(folio, refs);
+		if (!put_devmap_managed_page_refs(&folio->page, refs))
+			folio_put_refs(folio, refs);
 		goto retry;
 	}
 
···
 			refs *= GUP_PIN_COUNTING_BIAS;
 	}
 
-	folio_put_refs(folio, refs);
+	if (!put_devmap_managed_page_refs(&folio->page, refs))
+		folio_put_refs(folio, refs);
 }
 
 /**

mm/hugetlb.c

···
 			 * sharing with another vma.
 			 */
 			;
-		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
-				    is_hugetlb_entry_hwpoisoned(entry))) {
+		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
+			bool uffd_wp = huge_pte_uffd_wp(entry);
+
+			if (!userfaultfd_wp(dst_vma) && uffd_wp)
+				entry = huge_pte_clear_uffd_wp(entry);
+			set_huge_pte_at(dst, addr, dst_pte, entry);
+		} else if (unlikely(is_hugetlb_entry_migration(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
 			bool uffd_wp = huge_pte_uffd_wp(entry);
 
···
 
 		page = alloc_huge_page(dst_vma, dst_addr, 0);
 		if (IS_ERR(page)) {
+			put_page(*pagep);
 			ret = -ENOMEM;
 			*pagep = NULL;
 			goto out;

mm/kfence/core.c

···
 		addr += 2 * PAGE_SIZE;
 	}
 
-	/*
-	 * The pool is live and will never be deallocated from this point on.
-	 * Remove the pool object from the kmemleak object tree, as it would
-	 * otherwise overlap with allocations returned by kfence_alloc(), which
-	 * are registered with kmemleak through the slab post-alloc hook.
-	 */
-	kmemleak_free(__kfence_pool);
-
 	return 0;
 }
 
···
 
 	addr = kfence_init_pool();
 
-	if (!addr)
+	if (!addr) {
+		/*
+		 * The pool is live and will never be deallocated from this point on.
+		 * Ignore the pool object from the kmemleak phys object tree, as it would
+		 * otherwise overlap with allocations returned by kfence_alloc(), which
+		 * are registered with kmemleak through the slab post-alloc hook.
+		 */
+		kmemleak_ignore_phys(__pa(__kfence_pool));
 		return true;
+	}
 
 	/*
 	 * Only release unprotected pages, and do not try to go back and change

mm/memory.c

···
 			return VM_FAULT_OOM;
 	}
 
-	/* See comment in handle_pte_fault() */
+	/*
+	 * See comment in handle_pte_fault() for how this scenario happens, we
+	 * need to return NOPAGE so that we drop this page.
+	 */
 	if (pmd_devmap_trans_unstable(vmf->pmd))
-		return 0;
+		return VM_FAULT_NOPAGE;
 
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 				      vmf->address, &vmf->ptl);

mm/memremap.c

···
 }
 
 #ifdef CONFIG_FS_DAX
-bool __put_devmap_managed_page(struct page *page)
+bool __put_devmap_managed_page_refs(struct page *page, int refs)
 {
 	if (page->pgmap->type != MEMORY_DEVICE_FS_DAX)
 		return false;
···
 	 * refcount is 1, then the page is free and the refcount is
 	 * stable because nobody holds a reference on the page.
 	 */
-	if (page_ref_dec_return(page) == 1)
+	if (page_ref_sub_return(page, refs) == 1)
 		wake_up_var(&page->_refcount);
 	return true;
 }
-EXPORT_SYMBOL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page_refs);
 #endif /* CONFIG_FS_DAX */

mm/secretmem.c

···
 	gfp_t gfp = vmf->gfp_mask;
 	unsigned long addr;
 	struct page *page;
+	vm_fault_t ret;
 	int err;
 
 	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
 		return vmf_error(-EINVAL);
 
+	filemap_invalidate_lock_shared(mapping);
+
 retry:
 	page = find_lock_page(mapping, offset);
 	if (!page) {
 		page = alloc_page(gfp | __GFP_ZERO);
-		if (!page)
-			return VM_FAULT_OOM;
+		if (!page) {
+			ret = VM_FAULT_OOM;
+			goto out;
+		}
 
 		err = set_direct_map_invalid_noflush(page);
 		if (err) {
 			put_page(page);
-			return vmf_error(err);
+			ret = vmf_error(err);
+			goto out;
 		}
 
 		__SetPageUptodate(page);
···
 			if (err == -EEXIST)
 				goto retry;
 
-			return vmf_error(err);
+			ret = vmf_error(err);
+			goto out;
 		}
 
 		addr = (unsigned long)page_address(page);
···
 	}
 
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = VM_FAULT_LOCKED;
+
+out:
+	filemap_invalidate_unlock_shared(mapping);
+	return ret;
 }
 
 static const struct vm_operations_struct secretmem_vm_ops = {
···
 			     struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
+	struct address_space *mapping = inode->i_mapping;
 	unsigned int ia_valid = iattr->ia_valid;
+	int ret;
+
+	filemap_invalidate_lock(mapping);
 
 	if ((ia_valid & ATTR_SIZE) && inode->i_size)
-		return -EINVAL;
+		ret = -EINVAL;
+	else
+		ret = simple_setattr(mnt_userns, dentry, iattr);
 
-	return simple_setattr(mnt_userns, dentry, iattr);
+	filemap_invalidate_unlock(mapping);
+
+	return ret;
 }
 
 static const struct inode_operations secretmem_iops = {

mm/shmem.c

···
 		break;
 	case Opt_nr_blocks:
 		ctx->blocks = memparse(param->string, &rest);
-		if (*rest)
+		if (*rest || ctx->blocks > S64_MAX)
 			goto bad_value;
 		ctx->seen |= SHMEM_SEEN_BLOCKS;
 		break;
···
 
 	raw_spin_lock(&sbinfo->stat_lock);
 	inodes = sbinfo->max_inodes - sbinfo->free_inodes;
-	if (ctx->blocks > S64_MAX) {
-		err = "Number of blocks too large";
-		goto out;
-	}
+
 	if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
 		if (!sbinfo->max_blocks) {
 			err = "Cannot retroactively limit size";