Merge tag 'mm-hotfixes-stable-2024-09-03-20-19' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "17 hotfixes, 15 of which are cc:stable.

  Mostly MM, no identifiable theme.  And a few nilfs2 fixups"

* tag 'mm-hotfixes-stable-2024-09-03-20-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  alloc_tag: fix allocation tag reporting when CONFIG_MODULES=n
  mm: vmalloc: optimize vmap_lazy_nr arithmetic when purging each vmap_area
  mailmap: update entry for Jan Kuliga
  codetag: debug: mark codetags for poisoned page as empty
  mm/memcontrol: respect zswap.writeback setting from parent cg too
  scripts: fix gfp-translate after ___GFP_*_BITS conversion to an enum
  Revert "mm: skip CMA pages when they are not available"
  maple_tree: remove rcu_read_lock() from mt_validate()
  kexec_file: fix elfcorehdr digest exclusion when CONFIG_CRASH_HOTPLUG=y
  mm/slub: add check for s->flags in the alloc_tagging_slab_free_hook
  nilfs2: fix state management in error path of log writing function
  nilfs2: fix missing cleanup on rollforward recovery error
  nilfs2: protect references to superblock parameters exposed in sysfs
  userfaultfd: don't BUG_ON() if khugepaged yanks our page table
  userfaultfd: fix checks for huge PMDs
  mm: vmalloc: ensure vmap_block is initialised before adding to queue
  selftests: mm: fix build errors on armhf

.mailmap

@@ -269,6 +269,7 @@ James Ketrenos <jketreno@io.(none)>
 Jan Glauber <jan.glauber@gmail.com> <jang@de.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com>
+Jan Kuliga <jtkuliga.kdev@gmail.com> <jankul@alatek.krakow.pl>
 Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com>
 Jarkko Sakkinen <jarkko@kernel.org> <jarkko@profian.com>
 Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@tuni.fi>

Documentation/admin-guide/cgroup-v2.rst

@@ -1717,9 +1717,10 @@ The following nested keys are defined.
 	entries fault back in or are written out to disk.
 
   memory.zswap.writeback
-	A read-write single value file. The default value is "1". The
-	initial value of the root cgroup is 1, and when a new cgroup is
-	created, it inherits the current value of its parent.
+	A read-write single value file. The default value is "1".
+	Note that this setting is hierarchical, i.e. the writeback would be
+	implicitly disabled for child cgroups if the upper hierarchy
+	does so.
 
 	When this is set to 0, all swapping attempts to swapping devices
 	are disabled. This included both zswap writebacks, and swapping due

fs/nilfs2/recovery.c

@@ -715,6 +715,33 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
 	brelse(bh);
 }
 
+/**
+ * nilfs_abort_roll_forward - cleaning up after a failed rollforward recovery
+ * @nilfs: nilfs object
+ */
+static void nilfs_abort_roll_forward(struct the_nilfs *nilfs)
+{
+	struct nilfs_inode_info *ii, *n;
+	LIST_HEAD(head);
+
+	/* Abandon inodes that have read recovery data */
+	spin_lock(&nilfs->ns_inode_lock);
+	list_splice_init(&nilfs->ns_dirty_files, &head);
+	spin_unlock(&nilfs->ns_inode_lock);
+	if (list_empty(&head))
+		return;
+
+	set_nilfs_purging(nilfs);
+	list_for_each_entry_safe(ii, n, &head, i_dirty) {
+		spin_lock(&nilfs->ns_inode_lock);
+		list_del_init(&ii->i_dirty);
+		spin_unlock(&nilfs->ns_inode_lock);
+
+		iput(&ii->vfs_inode);
+	}
+	clear_nilfs_purging(nilfs);
+}
+
 /**
  * nilfs_salvage_orphan_logs - salvage logs written after the latest checkpoint
  * @nilfs: nilfs object
@@ -773,15 +800,19 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 		if (unlikely(err)) {
 			nilfs_err(sb, "error %d writing segment for recovery",
 				  err);
-			goto failed;
+			goto put_root;
 		}
 
 		nilfs_finish_roll_forward(nilfs, ri);
 	}
 
- failed:
+put_root:
 	nilfs_put_root(root);
 	return err;
+
+failed:
+	nilfs_abort_roll_forward(nilfs);
+	goto put_root;
 }
 
 /**

fs/nilfs2/segment.c

@@ -1812,6 +1812,9 @@ static void nilfs_segctor_abort_construction(struct nilfs_sc_info *sci,
 	nilfs_abort_logs(&logs, ret ? : err);
 
 	list_splice_tail_init(&sci->sc_segbufs, &logs);
+	if (list_empty(&logs))
+		return; /* if the first segment buffer preparation failed */
+
 	nilfs_cancel_segusage(&logs, nilfs->ns_sufile);
 	nilfs_free_incomplete_logs(&logs, nilfs);
 
@@ -2056,7 +2059,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 
 		err = nilfs_segctor_begin_construction(sci, nilfs);
 		if (unlikely(err))
-			goto out;
+			goto failed;
 
 		/* Update time stamp */
 		sci->sc_seg_ctime = ktime_get_real_seconds();
@@ -2120,10 +2123,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 	return err;
 
  failed_to_write:
-	if (sci->sc_stage.flags & NILFS_CF_IFILE_STARTED)
-		nilfs_redirty_inodes(&sci->sc_dirty_files);
-
  failed:
+	if (mode == SC_LSEG_SR && nilfs_sc_cstage_get(sci) >= NILFS_ST_IFILE)
+		nilfs_redirty_inodes(&sci->sc_dirty_files);
 	if (nilfs_doing_gc())
 		nilfs_redirty_inodes(&sci->sc_gc_inodes);
 	nilfs_segctor_abort_construction(sci, nilfs, err);

fs/nilfs2/sysfs.c

@@ -836,9 +836,15 @@ ssize_t nilfs_dev_revision_show(struct nilfs_dev_attr *attr,
 				struct the_nilfs *nilfs,
 				char *buf)
 {
-	struct nilfs_super_block **sbp = nilfs->ns_sbp;
-	u32 major = le32_to_cpu(sbp[0]->s_rev_level);
-	u16 minor = le16_to_cpu(sbp[0]->s_minor_rev_level);
+	struct nilfs_super_block *raw_sb;
+	u32 major;
+	u16 minor;
+
+	down_read(&nilfs->ns_sem);
+	raw_sb = nilfs->ns_sbp[0];
+	major = le32_to_cpu(raw_sb->s_rev_level);
+	minor = le16_to_cpu(raw_sb->s_minor_rev_level);
+	up_read(&nilfs->ns_sem);
 
 	return sysfs_emit(buf, "%d.%d\n", major, minor);
 }
@@ -856,8 +862,13 @@ ssize_t nilfs_dev_device_size_show(struct nilfs_dev_attr *attr,
 				    struct the_nilfs *nilfs,
 				    char *buf)
 {
-	struct nilfs_super_block **sbp = nilfs->ns_sbp;
-	u64 dev_size = le64_to_cpu(sbp[0]->s_dev_size);
+	struct nilfs_super_block *raw_sb;
+	u64 dev_size;
+
+	down_read(&nilfs->ns_sem);
+	raw_sb = nilfs->ns_sbp[0];
+	dev_size = le64_to_cpu(raw_sb->s_dev_size);
+	up_read(&nilfs->ns_sem);
 
 	return sysfs_emit(buf, "%llu\n", dev_size);
 }
@@ -879,20 +890,32 @@ ssize_t nilfs_dev_uuid_show(struct nilfs_dev_attr *attr,
 			    struct the_nilfs *nilfs,
 			    char *buf)
 {
-	struct nilfs_super_block **sbp = nilfs->ns_sbp;
+	struct nilfs_super_block *raw_sb;
+	ssize_t len;
 
-	return sysfs_emit(buf, "%pUb\n", sbp[0]->s_uuid);
+	down_read(&nilfs->ns_sem);
+	raw_sb = nilfs->ns_sbp[0];
+	len = sysfs_emit(buf, "%pUb\n", raw_sb->s_uuid);
+	up_read(&nilfs->ns_sem);
+
+	return len;
 }
 
 static
 ssize_t nilfs_dev_volume_name_show(struct nilfs_dev_attr *attr,
 				    struct the_nilfs *nilfs,
 				    char *buf)
 {
-	struct nilfs_super_block **sbp = nilfs->ns_sbp;
+	struct nilfs_super_block *raw_sb;
+	ssize_t len;
+
+	down_read(&nilfs->ns_sem);
+	raw_sb = nilfs->ns_sbp[0];
+	len = scnprintf(buf, sizeof(raw_sb->s_volume_name), "%s\n",
+			raw_sb->s_volume_name);
+	up_read(&nilfs->ns_sem);
 
-	return scnprintf(buf, sizeof(sbp[0]->s_volume_name), "%s\n",
-			 sbp[0]->s_volume_name);
+	return len;
 }
 
 static const char dev_readme_str[] =

kernel/kexec_file.c

@@ -752,7 +752,7 @@ static int kexec_calculate_store_digests(struct kimage *image)
 
 #ifdef CONFIG_CRASH_HOTPLUG
 		/* Exclude elfcorehdr segment to allow future changes via hotplug */
-		if (j == image->elfcorehdr_index)
+		if (i == image->elfcorehdr_index)
 			continue;
 #endif
 

lib/codetag.c

@@ -125,7 +125,6 @@ static inline size_t range_size(const struct codetag_type *cttype,
 			cttype->desc.tag_size;
 }
 
-#ifdef CONFIG_MODULES
 static void *get_symbol(struct module *mod, const char *prefix, const char *name)
 {
 	DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN);
@@ -155,6 +154,15 @@ static struct codetag_range get_section_range(struct module *mod,
 	};
 }
 
+static const char *get_mod_name(__maybe_unused struct module *mod)
+{
+#ifdef CONFIG_MODULES
+	if (mod)
+		return mod->name;
+#endif
+	return "(built-in)";
+}
+
 static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
 {
 	struct codetag_range range;
@@ -164,8 +172,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
 	range = get_section_range(mod, cttype->desc.section);
 	if (!range.start || !range.stop) {
 		pr_warn("Failed to load code tags of type %s from the module %s\n",
-			cttype->desc.section,
-			mod ? mod->name : "(built-in)");
+			cttype->desc.section, get_mod_name(mod));
 		return -EINVAL;
 	}
 
@@ -199,6 +206,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
 	return 0;
 }
 
+#ifdef CONFIG_MODULES
 void codetag_load_module(struct module *mod)
 {
 	struct codetag_type *cttype;
@@ -248,9 +256,6 @@ bool codetag_unload_module(struct module *mod)
 
 	return unload_ok;
 }
-
-#else /* CONFIG_MODULES */
-static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; }
 #endif /* CONFIG_MODULES */
 
 struct codetag_type *

lib/maple_tree.c

@@ -7566,14 +7566,14 @@ static void mt_validate_nulls(struct maple_tree *mt)
  * 2. The gap is correctly set in the parents
  */
 void mt_validate(struct maple_tree *mt)
+	__must_hold(mas->tree->ma_lock)
 {
 	unsigned char end;
 
 	MA_STATE(mas, mt, 0, 0);
-	rcu_read_lock();
 	mas_start(&mas);
 	if (!mas_is_active(&mas))
-		goto done;
+		return;
 
 	while (!mte_is_leaf(mas.node))
 		mas_descend(&mas);
@@ -7594,9 +7594,6 @@ void mt_validate(struct maple_tree *mt)
 		mas_dfs_postorder(&mas, ULONG_MAX);
 	}
 	mt_validate_nulls(mt);
-done:
-	rcu_read_unlock();
-
 }
 EXPORT_SYMBOL_GPL(mt_validate);
 

mm/memcontrol.c

@@ -3613,8 +3613,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	memcg1_soft_limit_reset(memcg);
 #ifdef CONFIG_ZSWAP
 	memcg->zswap_max = PAGE_COUNTER_MAX;
-	WRITE_ONCE(memcg->zswap_writeback,
-		!parent || READ_ONCE(parent->zswap_writeback));
+	WRITE_ONCE(memcg->zswap_writeback, true);
 #endif
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	if (parent) {
@@ -5320,7 +5319,14 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
 bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
 {
 	/* if zswap is disabled, do not block pages going to the swapping device */
-	return !zswap_is_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
+	if (!zswap_is_enabled())
+		return true;
+
+	for (; memcg; memcg = parent_mem_cgroup(memcg))
+		if (!READ_ONCE(memcg->zswap_writeback))
+			return false;
+
+	return true;
 }
 
 static u64 zswap_current_read(struct cgroup_subsys_state *css,

mm/page_alloc.c

@@ -1054,6 +1054,13 @@ __always_inline bool free_pages_prepare(struct page *page,
 		reset_page_owner(page, order);
 		page_table_check_free(page, order);
 		pgalloc_tag_sub(page, 1 << order);
+
+		/*
+		 * The page is isolated and accounted for.
+		 * Mark the codetag as empty to avoid accounting error
+		 * when the page is freed by unpoison_memory().
+		 */
+		clear_page_tag_ref(page);
 		return false;
 	}
 

mm/slub.c

@@ -2116,6 +2116,10 @@ alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
 	if (!mem_alloc_profiling_enabled())
 		return;
 
+	/* slab->obj_exts might not be NULL if it was created for MEMCG accounting. */
+	if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
+		return;
+
 	obj_exts = slab_obj_exts(slab);
 	if (!obj_exts)
 		return;

mm/userfaultfd.c

@@ -787,27 +787,30 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
 		}
 
 		dst_pmdval = pmdp_get_lockless(dst_pmd);
-		/*
-		 * If the dst_pmd is mapped as THP don't
-		 * override it and just be strict.
-		 */
-		if (unlikely(pmd_trans_huge(dst_pmdval))) {
-			err = -EEXIST;
-			break;
-		}
 		if (unlikely(pmd_none(dst_pmdval)) &&
 		    unlikely(__pte_alloc(dst_mm, dst_pmd))) {
 			err = -ENOMEM;
 			break;
 		}
-		/* If an huge pmd materialized from under us fail */
-		if (unlikely(pmd_trans_huge(*dst_pmd))) {
+		dst_pmdval = pmdp_get_lockless(dst_pmd);
+		/*
+		 * If the dst_pmd is THP don't override it and just be strict.
+		 * (This includes the case where the PMD used to be THP and
+		 * changed back to none after __pte_alloc().)
+		 */
+		if (unlikely(!pmd_present(dst_pmdval) || pmd_trans_huge(dst_pmdval) ||
+			     pmd_devmap(dst_pmdval))) {
+			err = -EEXIST;
+			break;
+		}
+		if (unlikely(pmd_bad(dst_pmdval))) {
 			err = -EFAULT;
 			break;
 		}
-
-		BUG_ON(pmd_none(*dst_pmd));
-		BUG_ON(pmd_trans_huge(*dst_pmd));
+		/*
+		 * For shmem mappings, khugepaged is allowed to remove page
+		 * tables under us; pte_offset_map_lock() will deal with that.
+		 */
 
 		err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr,
 				       src_addr, flags, &folio);