14 files changed, 159 insertions, 116 deletions

diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index b095457380b5..d9e01648db70 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -423,6 +423,7 @@ static ssize_t memcg_path_store(struct kobject *kobj,
 		return -ENOMEM;
 
 	strscpy(path, buf, count + 1);
+	kfree(filter->memcg_path);
 	filter->memcg_path = path;
 	return count;
 }
diff --git a/mm/gup.c b/mm/gup.c
index 90866b827b60..e323843cc5dd 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2326,13 +2326,13 @@ static void pofs_unpin(struct pages_or_folios *pofs)
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
-static void collect_longterm_unpinnable_folios(
+static unsigned long collect_longterm_unpinnable_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;
-	unsigned long i;
 
 	for (i = 0; i < pofs->nr_entries; i++) {
 		struct folio *folio = pofs_get_folio(pofs, i);
@@ -2344,6 +2344,8 @@ static void collect_longterm_unpinnable_folios(
 		if (folio_is_longterm_pinnable(folio))
 			continue;
 
+		collected++;
+
 		if (folio_is_device_coherent(folio))
 			continue;
 
@@ -2365,6 +2367,8 @@ static void collect_longterm_unpinnable_folios(
 				    NR_ISOLATED_ANON + folio_is_file_lru(folio),
 				    folio_nr_pages(folio));
 	}
+
+	return collected;
 }
 
 /*
@@ -2441,9 +2445,11 @@ static long
 check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
 {
 	LIST_HEAD(movable_folio_list);
+	unsigned long collected;
 
-	collect_longterm_unpinnable_folios(&movable_folio_list, pofs);
-	if (list_empty(&movable_folio_list))
+	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+						       pofs);
+	if (!collected)
 		return 0;
 
 	return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
diff --git a/mm/hmm.c b/mm/hmm.c
index 7e0229ae4a5a..a67776aeb019 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -173,6 +173,7 @@ static inline unsigned long hmm_pfn_flags_order(unsigned long order)
 	return order << HMM_PFN_ORDER_SHIFT;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
 						 pmd_t pmd)
 {
@@ -183,7 +184,6 @@ static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
 	       hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 			      unsigned long end, unsigned long hmm_pfns[],
 			      pmd_t pmd)
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index c7c0083203cb..f17265410156 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -398,17 +398,10 @@ static void print_address_description(void *addr, u8 tag,
 	}
 
 	if (is_vmalloc_addr(addr)) {
-		struct vm_struct *va = find_vm_area(addr);
-
-		if (va) {
-			pr_err("The buggy address belongs to the virtual mapping at\n"
-			       " [%px, %px) created by:\n"
-			       " %pS\n",
-			       va->addr, va->addr + va->size, va->caller);
-			pr_err("\n");
-
-			page = vmalloc_to_page(addr);
-		}
+		pr_err("The buggy address belongs to a");
+		if (!vmalloc_dump_obj(addr))
+			pr_cont(" vmalloc virtual mapping\n");
+		page = vmalloc_to_page(addr);
 	}
 
 	if (page) {
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b538c3d48386..abd5764e4864 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2404,7 +2404,7 @@ skip:
 			VM_BUG_ON(khugepaged_scan.address < hstart ||
 				  khugepaged_scan.address + HPAGE_PMD_SIZE >
 				  hend);
-			if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
+			if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) {
 				struct file *file = get_file(vma->vm_file);
 				pgoff_t pgoff = linear_page_index(vma,
 						khugepaged_scan.address);
@@ -2750,7 +2750,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		mmap_assert_locked(mm);
 		memset(cc->node_load, 0, sizeof(cc->node_load));
 		nodes_clear(cc->alloc_nmask);
-		if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
+		if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) {
 			struct file *file = get_file(vma->vm_file);
 			pgoff_t pgoff = linear_page_index(vma, addr);
 
diff --git a/mm/ksm.c b/mm/ksm.c
index a2e2a521df0a..17e6c16ab81d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -3643,10 +3643,10 @@ static ssize_t advisor_mode_show(struct kobject *kobj,
 {
 	const char *output;
 
-	if (ksm_advisor == KSM_ADVISOR_NONE)
-		output = "[none] scan-time";
-	else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
+	if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
 		output = "none [scan-time]";
+	else
+		output = "[none] scan-time";
 
 	return sysfs_emit(buf, "%s\n", output);
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ec1c71abe88d..70b2ccf0d51e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1559,6 +1559,10 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
 	return ret;
 }
 
+/*
+ * The caller must guarantee the folio isn't large folio, except hugetlb.
+ * try_to_unmap() can't handle it.
+ */
 int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
 	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 399552814fd0..4662f2510ae5 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -195,19 +195,11 @@ static struct file *secretmem_file_create(unsigned long flags)
 	struct file *file;
 	struct inode *inode;
 	const char *anon_name = "[secretmem]";
-	const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name));
-	int err;
 
-	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	inode = anon_inode_make_secure_inode(secretmem_mnt->mnt_sb, anon_name, NULL);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	err = security_inode_init_security_anon(inode, &qname, NULL);
-	if (err) {
-		file = ERR_PTR(err);
-		goto err_free_inode;
-	}
-
 	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
 				 O_RDWR, &secretmem_fops);
 	if (IS_ERR(file))
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b0a9071cfe1d..c02493d9c7be 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3237,43 +3237,30 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
 #define SWAP_CLUSTER_COLS						\
 	max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS)
 
-static int setup_swap_map_and_extents(struct swap_info_struct *si,
-					union swap_header *swap_header,
-					unsigned char *swap_map,
-					unsigned long maxpages,
-					sector_t *span)
+static int setup_swap_map(struct swap_info_struct *si,
+			  union swap_header *swap_header,
+			  unsigned char *swap_map,
+			  unsigned long maxpages)
 {
-	unsigned int nr_good_pages;
 	unsigned long i;
-	int nr_extents;
-
-	nr_good_pages = maxpages - 1;	/* omit header page */
 
+	swap_map[0] = SWAP_MAP_BAD; /* omit header page */
 	for (i = 0; i < swap_header->info.nr_badpages; i++) {
 		unsigned int page_nr = swap_header->info.badpages[i];
 		if (page_nr == 0 || page_nr > swap_header->info.last_page)
 			return -EINVAL;
 		if (page_nr < maxpages) {
 			swap_map[page_nr] = SWAP_MAP_BAD;
-			nr_good_pages--;
+			si->pages--;
 		}
 	}
 
-	if (nr_good_pages) {
-		swap_map[0] = SWAP_MAP_BAD;
-		si->max = maxpages;
-		si->pages = nr_good_pages;
-		nr_extents = setup_swap_extents(si, span);
-		if (nr_extents < 0)
-			return nr_extents;
-		nr_good_pages = si->pages;
-	}
-	if (!nr_good_pages) {
+	if (!si->pages) {
 		pr_warn("Empty swap-file\n");
 		return -EINVAL;
 	}
 
-	return nr_extents;
+	return 0;
 }
 
 static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
@@ -3318,13 +3305,17 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 	 * Mark unusable pages as unavailable. The clusters aren't
 	 * marked free yet, so no list operations are involved yet.
 	 *
-	 * See setup_swap_map_and_extents(): header page, bad pages,
+	 * See setup_swap_map(): header page, bad pages,
 	 * and the EOF part of the last cluster.
 	 */
 	inc_cluster_info_page(si, cluster_info, 0);
-	for (i = 0; i < swap_header->info.nr_badpages; i++)
-		inc_cluster_info_page(si, cluster_info,
-				      swap_header->info.badpages[i]);
+	for (i = 0; i < swap_header->info.nr_badpages; i++) {
+		unsigned int page_nr = swap_header->info.badpages[i];
+
+		if (page_nr >= maxpages)
+			continue;
+		inc_cluster_info_page(si, cluster_info, page_nr);
+	}
 	for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++)
 		inc_cluster_info_page(si, cluster_info, i);
 
@@ -3456,6 +3447,21 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
+	si->max = maxpages;
+	si->pages = maxpages - 1;
+	nr_extents = setup_swap_extents(si, &span);
+	if (nr_extents < 0) {
+		error = nr_extents;
+		goto bad_swap_unlock_inode;
+	}
+	if (si->pages != si->max - 1) {
+		pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max);
+		error = -EINVAL;
+		goto bad_swap_unlock_inode;
+	}
+
+	maxpages = si->max;
+
 	/* OK, set up the swap map and apply the bad block list */
 	swap_map = vzalloc(maxpages);
 	if (!swap_map) {
@@ -3467,12 +3473,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (error)
 		goto bad_swap_unlock_inode;
 
-	nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map,
-						maxpages, &span);
-	if (unlikely(nr_extents < 0)) {
-		error = nr_extents;
+	error = setup_swap_map(si, swap_header, swap_map, maxpages);
+	if (error)
 		goto bad_swap_unlock_inode;
-	}
 
 	/*
 	 * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e06e3d270961..2646b75163d5 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1078,8 +1078,18 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 			 pte_t *dst_pte, pte_t *src_pte,
 			 pte_t orig_dst_pte, pte_t orig_src_pte,
 			 spinlock_t *dst_ptl, spinlock_t *src_ptl,
-			 struct folio *src_folio)
+			 struct folio *src_folio,
+			 struct swap_info_struct *si, swp_entry_t entry)
 {
+	/*
+	 * Check if the folio still belongs to the target swap entry after
+	 * acquiring the lock. Folio can be freed in the swap cache while
+	 * not locked.
+	 */
+	if (src_folio && unlikely(!folio_test_swapcache(src_folio) ||
+				  entry.val != src_folio->swap.val))
+		return -EAGAIN;
+
 	double_pt_lock(dst_ptl, src_ptl);
 
 	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
@@ -1096,6 +1106,25 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 	if (src_folio) {
 		folio_move_anon_rmap(src_folio, dst_vma);
 		src_folio->index = linear_page_index(dst_vma, dst_addr);
+	} else {
+		/*
+		 * Check if the swap entry is cached after acquiring the src_pte
+		 * lock. Otherwise, we might miss a newly loaded swap cache folio.
+		 *
+		 * Check swap_map directly to minimize overhead, READ_ONCE is sufficient.
+		 * We are trying to catch newly added swap cache, the only possible case is
+		 * when a folio is swapped in and out again staying in swap cache, using the
+		 * same entry before the PTE check above. The PTL is acquired and released
+		 * twice, each time after updating the swap_map's flag. So holding
+		 * the PTL here ensures we see the updated value. False positive is possible,
+		 * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the
+		 * cache, or during the tiny synchronization window between swap cache and
+		 * swap_map, but it will be gone very quickly, worst result is retry jitters.
+		 */
+		if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) {
+			double_pt_unlock(dst_ptl, src_ptl);
+			return -EAGAIN;
+		}
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
@@ -1391,7 +1420,7 @@ retry:
 		}
 		err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte,
 				orig_dst_pte, orig_src_pte,
-				dst_ptl, src_ptl, src_folio);
+				dst_ptl, src_ptl, src_folio, si, entry);
 	}
 
 out:
diff --git a/mm/vma.c b/mm/vma.c
index 1d82ec4ee7bb..140f7017bb63 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -836,9 +836,6 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *
 		err = dup_anon_vma(next, vma, &anon_dup);
 	}
 
-	if (err)
-		goto abort;
-
 	/*
 	 * In nearly all cases, we expand vmg->vma. There is one exception -
 	 * merge_right where we partially span the VMA. In this case we shrink
@@ -846,22 +843,11 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *
 	 */
 	expanded = !merge_right || merge_will_delete_vma;
 
-	if (commit_merge(vmg, adjust,
-			 merge_will_delete_vma ? vma : NULL,
-			 merge_will_delete_next ? next : NULL,
-			 adj_start, expanded)) {
-		if (anon_dup)
-			unlink_anon_vmas(anon_dup);
-
-		/*
-		 * We've cleaned up any cloned anon_vma's, no VMAs have been
-		 * modified, no harm no foul if the user requests that we not
-		 * report this and just give up, leaving the VMAs unmerged.
-		 */
-		if (!vmg->give_up_on_oom)
-			vmg->state = VMA_MERGE_ERROR_NOMEM;
-		return NULL;
-	}
+	if (err || commit_merge(vmg, adjust,
+			merge_will_delete_vma ? vma : NULL,
+			merge_will_delete_next ? next : NULL,
+			adj_start, expanded))
+		goto abort;
 
 	res = merge_left ? prev : next;
 	khugepaged_enter_vma(res, vmg->flags);
@@ -873,6 +859,9 @@ abort:
 	vma_iter_set(vmg->vmi, start);
 	vma_iter_load(vmg->vmi);
 
+	if (anon_dup)
+		unlink_anon_vmas(anon_dup);
+
 	/*
 	 * This means we have failed to clone anon_vma's correctly, but no
 	 * actual changes to VMAs have occurred, so no harm no foul - if the
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cc04e501b1c5..3519c4e4f841 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -487,6 +487,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
 		pgtbl_mod_mask *mask)
 {
+	int err = 0;
 	pte_t *pte;
 
 	/*
@@ -500,18 +501,25 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	do {
 		struct page *page = pages[*nr];
 
-		if (WARN_ON(!pte_none(ptep_get(pte))))
-			return -EBUSY;
-		if (WARN_ON(!page))
-			return -ENOMEM;
-		if (WARN_ON(!pfn_valid(page_to_pfn(page))))
-			return -EINVAL;
+		if (WARN_ON(!pte_none(ptep_get(pte)))) {
+			err = -EBUSY;
+			break;
+		}
+		if (WARN_ON(!page)) {
+			err = -ENOMEM;
+			break;
+		}
+		if (WARN_ON(!pfn_valid(page_to_pfn(page)))) {
+			err = -EINVAL;
+			break;
+		}
 
 		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
 		(*nr)++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	*mask |= PGTBL_PTE_MODIFIED;
-	return 0;
+
+	return err;
 }
 
 static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
@@ -3095,7 +3103,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm)
 	/*
 	 * Before removing VM_UNINITIALIZED,
 	 * we should make sure that vm has proper values.
-	 * Pair with smp_rmb() in show_numa_info().
+	 * Pair with smp_rmb() in vread_iter() and vmalloc_info_show().
 	 */
 	smp_wmb();
 	vm->flags &= ~VM_UNINITIALIZED;
@@ -4938,28 +4946,29 @@ bool vmalloc_dump_obj(void *object)
 #endif
 
 #ifdef CONFIG_PROC_FS
-static void show_numa_info(struct seq_file *m, struct vm_struct *v)
-{
-	if (IS_ENABLED(CONFIG_NUMA)) {
-		unsigned int nr, *counters = m->private;
-		unsigned int step = 1U << vm_area_page_order(v);
 
-		if (!counters)
-			return;
+/*
+ * Print number of pages allocated on each memory node.
+ *
+ * This function can only be called if CONFIG_NUMA is enabled
+ * and VM_UNINITIALIZED bit in v->flags is disabled.
+ */
+static void show_numa_info(struct seq_file *m, struct vm_struct *v,
+				 unsigned int *counters)
+{
+	unsigned int nr;
+	unsigned int step = 1U << vm_area_page_order(v);
 
-		if (v->flags & VM_UNINITIALIZED)
-			return;
-		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
-		smp_rmb();
+	if (!counters)
+		return;
 
-		memset(counters, 0, nr_node_ids * sizeof(unsigned int));
+	memset(counters, 0, nr_node_ids * sizeof(unsigned int));
 
-		for (nr = 0; nr < v->nr_pages; nr += step)
-			counters[page_to_nid(v->pages[nr])] += step;
-		for_each_node_state(nr, N_HIGH_MEMORY)
-			if (counters[nr])
-				seq_printf(m, " N%u=%u", nr, counters[nr]);
-	}
+	for (nr = 0; nr < v->nr_pages; nr += step)
+		counters[page_to_nid(v->pages[nr])] += step;
+	for_each_node_state(nr, N_HIGH_MEMORY)
+		if (counters[nr])
+			seq_printf(m, " N%u=%u", nr, counters[nr]);
 }
 
 static void show_purge_info(struct seq_file *m)
@@ -4987,6 +4996,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 	struct vmap_area *va;
 	struct vm_struct *v;
 	int i;
+	unsigned int *counters;
+
+	if (IS_ENABLED(CONFIG_NUMA))
+		counters = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
 
 	for (i = 0; i < nr_vmap_nodes; i++) {
 		vn = &vmap_nodes[i];
@@ -5003,6 +5016,11 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 			}
 
 			v = va->vm;
+			if (v->flags & VM_UNINITIALIZED)
+				continue;
+
+			/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
+			smp_rmb();
 
 			seq_printf(m, "0x%pK-0x%pK %7ld",
 				v->addr, v->addr + v->size, v->size);
@@ -5037,7 +5055,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 			if (is_vmalloc_addr(v->pages))
 				seq_puts(m, " vpages");
 
-			show_numa_info(m, v);
+			if (IS_ENABLED(CONFIG_NUMA))
+				show_numa_info(m, v, counters);
+
 			seq_putc(m, '\n');
 		}
 		spin_unlock(&vn->busy.lock);
@@ -5047,19 +5067,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p)
 	 * As a final step, dump "unpurged" areas.
 	 */
 	show_purge_info(m);
+	if (IS_ENABLED(CONFIG_NUMA))
+		kfree(counters);
 	return 0;
 }
 
 static int __init proc_vmalloc_init(void)
 {
-	void *priv_data = NULL;
-
-	if (IS_ENABLED(CONFIG_NUMA))
-		priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
-
-	proc_create_single_data("vmallocinfo",
-		0400, NULL, vmalloc_info_show, priv_data);
-
+	proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show);
 	return 0;
 }
 module_init(proc_vmalloc_init);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0eb5d510d4f6..e3c1e2e1560d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1080,6 +1080,14 @@ retry:
 			goto keep;
 
 		if (folio_contain_hwpoisoned_page(folio)) {
+			/*
+			 * unmap_poisoned_folio() can't handle large
+			 * folio, just skip it. memory_failure() will
+			 * handle it if the UCE is triggered again.
+			 */
+			if (folio_test_large(folio))
+				goto keep_locked;
+
 			unmap_poisoned_folio(folio, folio_pfn(folio), false);
 			folio_unlock(folio);
 			folio_put(folio);
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 16a07def09c9..e4326af00e5e 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -976,6 +976,9 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
 	if (!zspage)
 		return NULL;
 
+	if (!IS_ENABLED(CONFIG_COMPACTION))
+		gfp &= ~__GFP_MOVABLE;
+
 	zspage->magic = ZSPAGE_MAGIC;
 	migrate_lock_init(zspage);