Merge tag 'mm-hotfixes-stable-2023-08-11-13-44' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "14 hotfixes. 11 of these are cc:stable and the remainder address
  post-6.4 issues, or are not considered suitable for -stable
  backporting"

* tag 'mm-hotfixes-stable-2023-08-11-13-44' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/damon/core: initialize damo_filter->list from damos_new_filter()
  nilfs2: fix use-after-free of nilfs_root in dirtying inodes via iput
  selftests: cgroup: fix test_kmem_basic false positives
  fs/proc/kcore: reinstate bounce buffer for KCORE_TEXT regions
  MAINTAINERS: add maple tree mailing list
  mm: compaction: fix endless looping over same migrate block
  selftests: mm: ksm: fix incorrect evaluation of parameter
  hugetlb: do not clear hugetlb dtor until allocating vmemmap
  mm: memory-failure: avoid false hwpoison page mapped error info
  mm: memory-failure: fix potential unexpected return value from unpoison_memory()
  mm/swapfile: fix wrong swap entry type for hwpoisoned swapcache page
  radix tree test suite: fix incorrect allocation size for pthreads
  crypto, cifs: fix error handling in extract_iter_to_sg()
  zsmalloc: fix races between modifications of fullness and isolated

16 files changed, 135 insertions, 54 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 6dd58c05ddcd..863530587777 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12480,6 +12480,7 @@ F:	net/mctp/
 
 MAPLE TREE
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
+L:	maple-tree@lists.infradead.org
 L:	linux-mm@kvack.org
 S:	Supported
 F:	Documentation/core-api/maple_tree.rst
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index a8ce522ac747..35bc79305318 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
 
 int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 {
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 	struct buffer_head *ibh;
 	int err;
 
+	/*
+	 * Do not dirty inodes after the log writer has been detached
+	 * and its nilfs_root struct has been freed.
+	 */
+	if (unlikely(nilfs_purging(nilfs)))
+		return 0;
+
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {
 		nilfs_warn(inode->i_sb,
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index c2553024bd25..581691e4be49 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2845,6 +2845,7 @@ void nilfs_detach_log_writer(struct super_block *sb)
 		nilfs_segctor_destroy(nilfs->ns_writer);
 		nilfs->ns_writer = NULL;
 	}
+	set_nilfs_purging(nilfs);
 
 	/* Force to free the list of dirty files */
 	spin_lock(&nilfs->ns_inode_lock);
@@ -2857,4 +2858,5 @@ void nilfs_detach_log_writer(struct super_block *sb)
 	up_write(&nilfs->ns_segctor_sem);
 
 	nilfs_dispose_list(nilfs, &garbage_list, 1);
+	clear_nilfs_purging(nilfs);
 }
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 47c7dfbb7ea5..cd4ae1b8ae16 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -29,6 +29,7 @@ enum {
 	THE_NILFS_DISCONTINUED,	/* 'next' pointer chain has broken */
 	THE_NILFS_GC_RUNNING,	/* gc process is running */
 	THE_NILFS_SB_DIRTY,	/* super block is dirty */
+	THE_NILFS_PURGING,	/* disposing dirty files for cleanup */
 };
 
 /**
@@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init)
 THE_NILFS_FNS(DISCONTINUED, discontinued)
 THE_NILFS_FNS(GC_RUNNING, gc_running)
 THE_NILFS_FNS(SB_DIRTY, sb_dirty)
+THE_NILFS_FNS(PURGING, purging)
 
 /*
  * Mount option operations
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 9cb32e1a78a0..23fc24d16b31 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -309,6 +309,8 @@ static void append_kcore_note(char *notes, size_t *i, const char *name,
 
 static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
+	struct file *file = iocb->ki_filp;
+	char *buf = file->private_data;
 	loff_t *fpos = &iocb->ki_pos;
 	size_t phdrs_offset, notes_offset, data_offset;
 	size_t page_offline_frozen = 1;
@@ -555,10 +557,21 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 		case KCORE_VMEMMAP:
 		case KCORE_TEXT:
 			/*
-			 * We use _copy_to_iter() to bypass usermode hardening
-			 * which would otherwise prevent this operation.
+			 * Sadly we must use a bounce buffer here to be able to
+			 * make use of copy_from_kernel_nofault(), as these
+			 * memory regions might not always be mapped on all
+			 * architectures.
 			 */
-			if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
+			if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
+				if (iov_iter_zero(tsz, iter) != tsz) {
+					ret = -EFAULT;
+					goto out;
+				}
+			/*
+			 * We know the bounce buffer is safe to copy from, so
+			 * use _copy_to_iter() directly.
+			 */
+			} else if (_copy_to_iter(buf, tsz, iter) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}
@@ -595,6 +608,10 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
+	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!filp->private_data)
+		return -ENOMEM;
+
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {
@@ -605,9 +622,16 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int release_kcore(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
 static const struct proc_ops kcore_proc_ops = {
 	.proc_read_iter	= read_kcore_iter,
 	.proc_open	= open_kcore,
+	.proc_release	= release_kcore,
 	.proc_lseek	= default_llseek,
 };
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index e86231a44c3d..c65566b4dc66 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -1148,7 +1148,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter,
 
 failed:
 	while (sgtable->nents > sgtable->orig_nents)
-		put_page(sg_page(&sgtable->sgl[--sgtable->nents]));
+		unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents]));
 	return res;
 }
 
diff --git a/mm/compaction.c b/mm/compaction.c
index dbc9f86b1934..eacca2794e47 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -912,11 +912,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		/*
 		 * Check if the pageblock has already been marked skipped.
-		 * Only the aligned PFN is checked as the caller isolates
+		 * Only the first PFN is checked as the caller isolates
 		 * COMPACT_CLUSTER_MAX at a time so the second call must
 		 * not falsely conclude that the block should be skipped.
 		 */
-		if (!valid_page && pageblock_aligned(low_pfn)) {
+		if (!valid_page && (pageblock_aligned(low_pfn) ||
+				    low_pfn == cc->zone->zone_start_pfn)) {
 			if (!isolation_suitable(cc, page)) {
 				low_pfn = end_pfn;
 				folio = NULL;
@@ -2002,7 +2003,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 		 * before making it "skip" so other compaction instances do
 		 * not scan the same block.
 		 */
-		if (pageblock_aligned(low_pfn) &&
+		if ((pageblock_aligned(low_pfn) ||
+		     low_pfn == cc->zone->zone_start_pfn) &&
 		    !fast_find_block && !isolation_suitable(cc, page))
 			continue;
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 91cff7f2997e..eb9580942a5c 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -273,6 +273,7 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type,
 		return NULL;
 	filter->type = type;
 	filter->matching = matching;
+	INIT_LIST_HEAD(&filter->list);
 	return filter;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 64a3239b6407..6da626bfb52e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1579,9 +1579,37 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio,
 						unsigned int order) { }
 #endif
 
+static inline void __clear_hugetlb_destructor(struct hstate *h,
+						struct folio *folio)
+{
+	lockdep_assert_held(&hugetlb_lock);
+
+	/*
+	 * Very subtle
+	 *
+	 * For non-gigantic pages set the destructor to the normal compound
+	 * page dtor.  This is needed in case someone takes an additional
+	 * temporary ref to the page, and freeing is delayed until they drop
+	 * their reference.
+	 *
+	 * For gigantic pages set the destructor to the null dtor.  This
+	 * destructor will never be called.  Before freeing the gigantic
+	 * page destroy_compound_gigantic_folio will turn the folio into a
+	 * simple group of pages.  After this the destructor does not
+	 * apply.
+	 *
+	 */
+	if (hstate_is_gigantic(h))
+		folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR);
+	else
+		folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
+}
+
 /*
- * Remove hugetlb folio from lists, and update dtor so that the folio appears
- * as just a compound page.
+ * Remove hugetlb folio from lists.
+ * If vmemmap exists for the folio, update dtor so that the folio appears
+ * as just a compound page.  Otherwise, wait until after allocating vmemmap
+ * to update dtor.
  *
  * A reference is held on the folio, except in the case of demote.
  *
@@ -1612,31 +1640,19 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio,
 	}
 
 	/*
-	 * Very subtle
-	 *
-	 * For non-gigantic pages set the destructor to the normal compound
-	 * page dtor.  This is needed in case someone takes an additional
-	 * temporary ref to the page, and freeing is delayed until they drop
-	 * their reference.
-	 *
-	 * For gigantic pages set the destructor to the null dtor.  This
-	 * destructor will never be called.  Before freeing the gigantic
-	 * page destroy_compound_gigantic_folio will turn the folio into a
-	 * simple group of pages.  After this the destructor does not
-	 * apply.
-	 *
-	 * This handles the case where more than one ref is held when and
-	 * after update_and_free_hugetlb_folio is called.
-	 *
-	 * In the case of demote we do not ref count the page as it will soon
-	 * be turned into a page of smaller size.
+	 * We can only clear the hugetlb destructor after allocating vmemmap
+	 * pages.  Otherwise, someone (memory error handling) may try to write
+	 * to tail struct pages.
+	 */
+	if (!folio_test_hugetlb_vmemmap_optimized(folio))
+		__clear_hugetlb_destructor(h, folio);
+
+	 /*
+	  * In the case of demote we do not ref count the page as it will soon
+	  * be turned into a page of smaller size.
 	 */
 	if (!demote)
 		folio_ref_unfreeze(folio, 1);
-	if (hstate_is_gigantic(h))
-		folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR);
-	else
-		folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[nid]--;
@@ -1705,6 +1721,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h,
 {
 	int i;
 	struct page *subpage;
+	bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio);
 
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
@@ -1735,6 +1752,16 @@ static void __update_and_free_hugetlb_folio(struct hstate *h,
 	if (unlikely(folio_test_hwpoison(folio)))
 		folio_clear_hugetlb_hwpoison(folio);
 
+	/*
+	 * If vmemmap pages were allocated above, then we need to clear the
+	 * hugetlb destructor under the hugetlb lock.
+	 */
+	if (clear_dtor) {
+		spin_lock_irq(&hugetlb_lock);
+		__clear_hugetlb_destructor(h, folio);
+		spin_unlock_irq(&hugetlb_lock);
+	}
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		subpage = folio_page(folio, i);
 		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
diff --git a/mm/ksm.c b/mm/ksm.c
index ba266359da55..d20d7662419b 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2784,6 +2784,8 @@ struct page *ksm_might_need_to_copy(struct page *page,
 			anon_vma->root == vma->anon_vma->root) {
 		return page;		/* still no need to copy it */
 	}
+	if (PageHWPoison(page))
+		return ERR_PTR(-EHWPOISON);
 	if (!PageUptodate(page))
 		return page;		/* let do_swap_page report the error */
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ece5d481b5ff..9a285038d765 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2466,7 +2466,7 @@ int unpoison_memory(unsigned long pfn)
 {
 	struct folio *folio;
 	struct page *p;
-	int ret = -EBUSY;
+	int ret = -EBUSY, ghp;
 	unsigned long count = 1;
 	bool huge = false;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
@@ -2499,6 +2499,13 @@ int unpoison_memory(unsigned long pfn)
 		goto unlock_mutex;
 	}
 
+	if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio))
+		goto unlock_mutex;
+
+	/*
+	 * Note that folio->_mapcount is overloaded in SLAB, so the simple test
+	 * in folio_mapped() has to be done after folio_test_slab() is checked.
+	 */
 	if (folio_mapped(folio)) {
 		unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n",
 				 pfn, &unpoison_rs);
@@ -2511,32 +2518,28 @@ int unpoison_memory(unsigned long pfn)
 		goto unlock_mutex;
 	}
 
-	if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio))
-		goto unlock_mutex;
-
-	ret = get_hwpoison_page(p, MF_UNPOISON);
-	if (!ret) {
+	ghp = get_hwpoison_page(p, MF_UNPOISON);
+	if (!ghp) {
 		if (PageHuge(p)) {
 			huge = true;
 			count = folio_free_raw_hwp(folio, false);
-			if (count == 0) {
-				ret = -EBUSY;
+			if (count == 0)
 				goto unlock_mutex;
-			}
 		}
 		ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY;
-	} else if (ret < 0) {
-		if (ret == -EHWPOISON) {
+	} else if (ghp < 0) {
+		if (ghp == -EHWPOISON) {
 			ret = put_page_back_buddy(p) ? 0 : -EBUSY;
-		} else
+		} else {
+			ret = ghp;
 			unpoison_pr_info("Unpoison: failed to grab page %#lx\n",
 					 pfn, &unpoison_rs);
+		}
 	} else {
 		if (PageHuge(p)) {
 			huge = true;
 			count = folio_free_raw_hwp(folio, false);
 			if (count == 0) {
-				ret = -EBUSY;
 				folio_put(folio);
 				goto unlock_mutex;
 			}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8e6dde68b389..b15112b1f1a8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1746,7 +1746,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *swapcache;
 	spinlock_t *ptl;
 	pte_t *pte, new_pte, old_pte;
-	bool hwposioned = false;
+	bool hwpoisoned = PageHWPoison(page);
 	int ret = 1;
 
 	swapcache = page;
@@ -1754,7 +1754,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	if (unlikely(!page))
 		return -ENOMEM;
 	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
-		hwposioned = true;
+		hwpoisoned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
@@ -1765,11 +1765,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 
 	old_pte = ptep_get(pte);
 
-	if (unlikely(hwposioned || !PageUptodate(page))) {
+	if (unlikely(hwpoisoned || !PageUptodate(page))) {
 		swp_entry_t swp_entry;
 
 		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
-		if (hwposioned) {
+		if (hwpoisoned) {
 			swp_entry = make_hwpoison_entry(swapcache);
 			page = swapcache;
 		} else {
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 3f057970504e..32916d28d9d9 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1798,6 +1798,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage,
 
 static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 {
+	struct zs_pool *pool;
 	struct zspage *zspage;
 
 	/*
@@ -1807,9 +1808,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 	VM_BUG_ON_PAGE(PageIsolated(page), page);
 
 	zspage = get_zspage(page);
-	migrate_write_lock(zspage);
+	pool = zspage->pool;
+	spin_lock(&pool->lock);
 	inc_zspage_isolation(zspage);
-	migrate_write_unlock(zspage);
+	spin_unlock(&pool->lock);
 
 	return true;
 }
@@ -1875,12 +1877,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 	kunmap_atomic(s_addr);
 
 	replace_sub_page(class, zspage, newpage, page);
+	dec_zspage_isolation(zspage);
 	/*
 	 * Since we complete the data copy and set up new zspage structure,
 	 * it's okay to release the pool's lock.
 	 */
 	spin_unlock(&pool->lock);
-	dec_zspage_isolation(zspage);
 	migrate_write_unlock(zspage);
 
 	get_page(newpage);
@@ -1897,14 +1899,16 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 
 static void zs_page_putback(struct page *page)
 {
+	struct zs_pool *pool;
 	struct zspage *zspage;
 
 	VM_BUG_ON_PAGE(!PageIsolated(page), page);
 
 	zspage = get_zspage(page);
-	migrate_write_lock(zspage);
+	pool = zspage->pool;
+	spin_lock(&pool->lock);
 	dec_zspage_isolation(zspage);
-	migrate_write_unlock(zspage);
+	spin_unlock(&pool->lock);
 }
 
 static const struct movable_operations zsmalloc_mops = {
diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index a61c7bcbc72d..63f468bf8245 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -177,7 +177,7 @@ void regression1_test(void)
 	nr_threads = 2;
 	pthread_barrier_init(&worker_barrier, NULL, nr_threads);
 
-	threads = malloc(nr_threads * sizeof(pthread_t *));
+	threads = malloc(nr_threads * sizeof(*threads));
 
 	for (i = 0; i < nr_threads; i++) {
 		arg = i;
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 258ddc565deb..1b2cec9d18a4 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -70,6 +70,10 @@ static int test_kmem_basic(const char *root)
 		goto cleanup;
 
 	cg_write(cg, "memory.high", "1M");
+
+	/* wait for RCU freeing */
+	sleep(1);
+
 	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
 	if (slab1 <= 0)
 		goto cleanup;
diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
index 435acebdc325..380b691d3eb9 100644
--- a/tools/testing/selftests/mm/ksm_tests.c
+++ b/tools/testing/selftests/mm/ksm_tests.c
@@ -831,6 +831,7 @@ int main(int argc, char *argv[])
 				printf("Size must be greater than 0\n");
 				return KSFT_FAIL;
 			}
+			break;
 		case 't':
 			{
 				int tmp = atoi(optarg);