Merge tag 'mm-hotfixes-stable-2024-11-12-16-39' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "10 hotfixes, 7 of which are cc:stable. 7 are MM, 3 are not. All
  singletons"

* tag 'mm-hotfixes-stable-2024-11-12-16-39' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm: swapfile: fix cluster reclaim work crash on rotational devices
  selftests: hugetlb_dio: fixup check for initial conditions to skip in the start
  mm/thp: fix deferred split queue not partially_mapped: fix
  mm/gup: avoid an unnecessary allocation call for FOLL_LONGTERM cases
  nommu: pass NULL argument to vma_iter_prealloc()
  ocfs2: fix UBSAN warning in ocfs2_verify_volume()
  nilfs2: fix null-ptr-deref in block_dirty_buffer tracepoint
  nilfs2: fix null-ptr-deref in block_touch_buffer tracepoint
  mm: page_alloc: move mlocked flag clearance into free_pages_prepare()
  mm: count zeromap read and set for swapout and swapin

10 files changed, 122 insertions, 59 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 4637dab7b54f..ad0c8922dac3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2273,20 +2273,57 @@ struct page *get_dump_page(unsigned long addr)
 #endif /* CONFIG_ELF_CORE */
 
 #ifdef CONFIG_MIGRATION
+
+/*
+ * An array of either pages or folios ("pofs"). Although it may seem tempting to
+ * avoid this complication, by simply interpreting a list of folios as a list of
+ * pages, that approach won't work in the longer term, because eventually the
+ * layouts of struct page and struct folio will become completely different.
+ * Furthermore, this pof approach avoids excessive page_folio() calls.
+ */
+struct pages_or_folios {
+	union {
+		struct page **pages;
+		struct folio **folios;
+		void **entries;
+	};
+	bool has_folios;
+	long nr_entries;
+};
+
+static struct folio *pofs_get_folio(struct pages_or_folios *pofs, long i)
+{
+	if (pofs->has_folios)
+		return pofs->folios[i];
+	return page_folio(pofs->pages[i]);
+}
+
+static void pofs_clear_entry(struct pages_or_folios *pofs, long i)
+{
+	pofs->entries[i] = NULL;
+}
+
+static void pofs_unpin(struct pages_or_folios *pofs)
+{
+	if (pofs->has_folios)
+		unpin_folios(pofs->folios, pofs->nr_entries);
+	else
+		unpin_user_pages(pofs->pages, pofs->nr_entries);
+}
+
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
 static unsigned long collect_longterm_unpinnable_folios(
-					struct list_head *movable_folio_list,
-					unsigned long nr_folios,
-					struct folio **folios)
+		struct list_head *movable_folio_list,
+		struct pages_or_folios *pofs)
 {
 	unsigned long i, collected = 0;
 	struct folio *prev_folio = NULL;
 	bool drain_allow = true;
 
-	for (i = 0; i < nr_folios; i++) {
-		struct folio *folio = folios[i];
+	for (i = 0; i < pofs->nr_entries; i++) {
+		struct folio *folio = pofs_get_folio(pofs, i);
 
 		if (folio == prev_folio)
 			continue;
@@ -2327,16 +2364,15 @@ static unsigned long collect_longterm_unpinnable_folios(
  * Returns -EAGAIN if all folios were successfully migrated or -errno for
  * failure (or partial success).
  */
-static int migrate_longterm_unpinnable_folios(
-					struct list_head *movable_folio_list,
-					unsigned long nr_folios,
-					struct folio **folios)
+static int
+migrate_longterm_unpinnable_folios(struct list_head *movable_folio_list,
+				   struct pages_or_folios *pofs)
 {
 	int ret;
 	unsigned long i;
 
-	for (i = 0; i < nr_folios; i++) {
-		struct folio *folio = folios[i];
+	for (i = 0; i < pofs->nr_entries; i++) {
+		struct folio *folio = pofs_get_folio(pofs, i);
 
 		if (folio_is_device_coherent(folio)) {
 			/*
@@ -2344,7 +2380,7 @@ static int migrate_longterm_unpinnable_folios(
 			 * convert the pin on the source folio to a normal
 			 * reference.
 			 */
-			folios[i] = NULL;
+			pofs_clear_entry(pofs, i);
 			folio_get(folio);
 			gup_put_folio(folio, 1, FOLL_PIN);
 
@@ -2363,8 +2399,8 @@ static int migrate_longterm_unpinnable_folios(
 		 * calling folio_isolate_lru() which takes a reference so the
 		 * folio won't be freed if it's migrating.
 		 */
-		unpin_folio(folios[i]);
-		folios[i] = NULL;
+		unpin_folio(folio);
+		pofs_clear_entry(pofs, i);
 	}
 
 	if (!list_empty(movable_folio_list)) {
@@ -2387,12 +2423,26 @@ static int migrate_longterm_unpinnable_folios(
 	return -EAGAIN;
 
 err:
-	unpin_folios(folios, nr_folios);
+	pofs_unpin(pofs);
 	putback_movable_pages(movable_folio_list);
 
 	return ret;
 }
 
+static long
+check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
+{
+	LIST_HEAD(movable_folio_list);
+	unsigned long collected;
+
+	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+						       pofs);
+	if (!collected)
+		return 0;
+
+	return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
+}
+
 /*
  * Check whether all folios are *allowed* to be pinned indefinitely (long term).
  * Rather confusingly, all folios in the range are required to be pinned via
@@ -2417,16 +2467,13 @@ err:
 static long check_and_migrate_movable_folios(unsigned long nr_folios,
 					     struct folio **folios)
 {
-	unsigned long collected;
-	LIST_HEAD(movable_folio_list);
+	struct pages_or_folios pofs = {
+		.folios = folios,
+		.has_folios = true,
+		.nr_entries = nr_folios,
+	};
 
-	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
-						       nr_folios, folios);
-	if (!collected)
-		return 0;
-
-	return migrate_longterm_unpinnable_folios(&movable_folio_list,
-						  nr_folios, folios);
+	return check_and_migrate_movable_pages_or_folios(&pofs);
 }
 
 /*
@@ -2436,22 +2483,13 @@ static long check_and_migrate_movable_folios(unsigned long nr_folios,
 static long check_and_migrate_movable_pages(unsigned long nr_pages,
 					    struct page **pages)
 {
-	struct folio **folios;
-	long i, ret;
+	struct pages_or_folios pofs = {
+		.pages = pages,
+		.has_folios = false,
+		.nr_entries = nr_pages,
+	};
 
-	folios = kmalloc_array(nr_pages, sizeof(*folios), GFP_KERNEL);
-	if (!folios) {
-		unpin_user_pages(pages, nr_pages);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nr_pages; i++)
-		folios[i] = page_folio(pages[i]);
-
-	ret = check_and_migrate_movable_folios(nr_pages, folios);
-
-	kfree(folios);
-	return ret;
+	return check_and_migrate_movable_pages_or_folios(&pofs);
 }
 #else
 static long check_and_migrate_movable_pages(unsigned long nr_pages,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 03fd4bc39ea1..5734d5d5060f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3790,7 +3790,9 @@ next:
 		 * in the case it was underused, then consider it used and
 		 * don't add it back to split_queue.
 		 */
-		if (!did_split && !folio_test_partially_mapped(folio)) {
+		if (did_split) {
+			; /* folio already removed from list */
+		} else if (!folio_test_partially_mapped(folio)) {
 			list_del_init(&folio->_deferred_list);
 			removed++;
 		} else {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 06df2af97415..53db98d2c4a1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -431,6 +431,10 @@ static const unsigned int memcg_vm_event_stat[] = {
 	PGDEACTIVATE,
 	PGLAZYFREE,
 	PGLAZYFREED,
+#ifdef CONFIG_SWAP
+	SWPIN_ZERO,
+	SWPOUT_ZERO,
+#endif
 #ifdef CONFIG_ZSWAP
 	ZSWPIN,
 	ZSWPOUT,
diff --git a/mm/nommu.c b/mm/nommu.c
index e9b5f527ab5b..9cb6e99215e2 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -573,7 +573,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma)
 	VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start);
 
 	vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
-	if (vma_iter_prealloc(&vmi, vma)) {
+	if (vma_iter_prealloc(&vmi, NULL)) {
 		pr_warn("Allocation of vma tree for process %d failed\n",
 		       current->pid);
 		return -ENOMEM;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c6c7bb3ea71b..216fbbfbedcf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1048,6 +1048,7 @@ __always_inline bool free_pages_prepare(struct page *page,
 	bool skip_kasan_poison = should_skip_kasan_poison(page);
 	bool init = want_init_on_free();
 	bool compound = PageCompound(page);
+	struct folio *folio = page_folio(page);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
@@ -1057,6 +1058,20 @@ __always_inline bool free_pages_prepare(struct page *page,
 	if (memcg_kmem_online() && PageMemcgKmem(page))
 		__memcg_kmem_uncharge_page(page, order);
 
+	/*
+	 * In rare cases, when truncation or holepunching raced with
+	 * munlock after VM_LOCKED was cleared, Mlocked may still be
+	 * found set here.  This does not indicate a problem, unless
+	 * "unevictable_pgs_cleared" appears worryingly large.
+	 */
+	if (unlikely(folio_test_mlocked(folio))) {
+		long nr_pages = folio_nr_pages(folio);
+
+		__folio_clear_mlocked(folio);
+		zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);
+		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
+	}
+
 	if (unlikely(PageHWPoison(page)) && !order) {
 		/* Do not let hwpoison pages hit pcplists/buddy */
 		reset_page_owner(page, order);
diff --git a/mm/page_io.c b/mm/page_io.c
index 69536a2b3c13..01749b99fb54 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -204,7 +204,9 @@ static bool is_folio_zero_filled(struct folio *folio)
 
 static void swap_zeromap_folio_set(struct folio *folio)
 {
+	struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio);
 	struct swap_info_struct *sis = swp_swap_info(folio->swap);
+	int nr_pages = folio_nr_pages(folio);
 	swp_entry_t entry;
 	unsigned int i;
 
@@ -212,6 +214,12 @@ static void swap_zeromap_folio_set(struct folio *folio)
 		entry = page_swap_entry(folio_page(folio, i));
 		set_bit(swp_offset(entry), sis->zeromap);
 	}
+
+	count_vm_events(SWPOUT_ZERO, nr_pages);
+	if (objcg) {
+		count_objcg_events(objcg, SWPOUT_ZERO, nr_pages);
+		obj_cgroup_put(objcg);
+	}
 }
 
 static void swap_zeromap_folio_clear(struct folio *folio)
@@ -503,6 +511,7 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
 static bool swap_read_folio_zeromap(struct folio *folio)
 {
 	int nr_pages = folio_nr_pages(folio);
+	struct obj_cgroup *objcg;
 	bool is_zeromap;
 
 	/*
@@ -517,6 +526,13 @@ static bool swap_read_folio_zeromap(struct folio *folio)
 	if (!is_zeromap)
 		return false;
 
+	objcg = get_obj_cgroup_from_folio(folio);
+	count_vm_events(SWPIN_ZERO, nr_pages);
+	if (objcg) {
+		count_objcg_events(objcg, SWPIN_ZERO, nr_pages);
+		obj_cgroup_put(objcg);
+	}
+
 	folio_zero_range(folio, 0, folio_size(folio));
 	folio_mark_uptodate(folio);
 	return true;
diff --git a/mm/swap.c b/mm/swap.c
index b8e3259ea2c4..59f30a981c6f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,20 +78,6 @@ static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp,
 		lruvec_del_folio(*lruvecp, folio);
 		__folio_clear_lru_flags(folio);
 	}
-
-	/*
-	 * In rare cases, when truncation or holepunching raced with
-	 * munlock after VM_LOCKED was cleared, Mlocked may still be
-	 * found set here.  This does not indicate a problem, unless
-	 * "unevictable_pgs_cleared" appears worryingly large.
-	 */
-	if (unlikely(folio_test_mlocked(folio))) {
-		long nr_pages = folio_nr_pages(folio);
-
-		__folio_clear_mlocked(folio);
-		zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);
-		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
-	}
 }
 
 /*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 46bd4b1a3c07..9c85bd46ab7f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -929,7 +929,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
 		si->highest_bit = 0;
 		del_from_avail_list(si);
 
-		if (vm_swap_full())
+		if (si->cluster_info && vm_swap_full())
 			schedule_work(&si->reclaim_work);
 	}
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b5a4cea423e1..ac6a5aa34eab 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1415,6 +1415,8 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SWAP
 	"swap_ra",
 	"swap_ra_hit",
+	"swpin_zero",
+	"swpout_zero",
 #ifdef CONFIG_KSM
 	"ksm_swpin_copy",
 #endif
diff --git a/mm/zswap.c b/mm/zswap.c
index 162013952074..0030ce8fecfc 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1053,7 +1053,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 
 	count_vm_event(ZSWPWB);
 	if (entry->objcg)
-		count_objcg_event(entry->objcg, ZSWPWB);
+		count_objcg_events(entry->objcg, ZSWPWB, 1);
 
 	zswap_entry_free(entry);
 
@@ -1483,7 +1483,7 @@ bool zswap_store(struct folio *folio)
 
 	if (objcg) {
 		obj_cgroup_charge_zswap(objcg, entry->length);
-		count_objcg_event(objcg, ZSWPOUT);
+		count_objcg_events(objcg, ZSWPOUT, 1);
 	}
 
 	/*
@@ -1577,7 +1577,7 @@ bool zswap_load(struct folio *folio)
 
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
-		count_objcg_event(entry->objcg, ZSWPIN);
+		count_objcg_events(entry->objcg, ZSWPIN, 1);
 
 	if (swapcache) {
 		zswap_entry_free(entry);