Merge tag 'v6.17-rc3' into togreg

Linux 6.17-rc3

14 files changed, 160 insertions, 72 deletions

diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 2a4a649805c1..03c5dbabb156 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -254,4 +254,10 @@ const struct movable_operations balloon_mops = {
 	.putback_page = balloon_page_putback,
 };
 
+static int __init balloon_init(void)
+{
+	return set_movable_ops(&balloon_mops, PGTY_offline);
+}
+core_initcall(balloon_init);
+
 #endif /* CONFIG_BALLOON_COMPACTION */
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 52a48c9316bc..70eff5cbe6ee 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -845,6 +845,18 @@ static struct damos_filter *damos_nth_filter(int n, struct damos *s)
 	return NULL;
 }
 
+static struct damos_filter *damos_nth_ops_filter(int n, struct damos *s)
+{
+	struct damos_filter *filter;
+	int i = 0;
+
+	damos_for_each_ops_filter(filter, s) {
+		if (i++ == n)
+			return filter;
+	}
+	return NULL;
+}
+
 static void damos_commit_filter_arg(
 		struct damos_filter *dst, struct damos_filter *src)
 {
@@ -871,6 +883,7 @@ static void damos_commit_filter(
 {
 	dst->type = src->type;
 	dst->matching = src->matching;
+	dst->allow = src->allow;
 	damos_commit_filter_arg(dst, src);
 }
 
@@ -908,7 +921,7 @@ static int damos_commit_ops_filters(struct damos *dst, struct damos *src)
 	int i = 0, j = 0;
 
 	damos_for_each_ops_filter_safe(dst_filter, next, dst) {
-		src_filter = damos_nth_filter(i++, src);
+		src_filter = damos_nth_ops_filter(i++, src);
 		if (src_filter)
 			damos_commit_filter(dst_filter, src_filter);
 		else
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 74056bcd6a2c..6536f16006c9 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2158,8 +2158,8 @@ static void damon_sysfs_scheme_rm_dirs(struct damon_sysfs_scheme *scheme)
 {
 	damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern);
 	kobject_put(&scheme->access_pattern->kobj);
-	kobject_put(&scheme->dests->kobj);
 	damos_sysfs_dests_rm_dirs(scheme->dests);
+	kobject_put(&scheme->dests->kobj);
 	damon_sysfs_quotas_rm_dirs(scheme->quotas);
 	kobject_put(&scheme->quotas->kobj);
 	kobject_put(&scheme->watermarks->kobj);
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index d19031f275a3..830107b6dd08 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -990,29 +990,34 @@ static void __init destroy_args(struct pgtable_debug_args *args)
 
 	/* Free page table entries */
 	if (args->start_ptep) {
+		pmd_clear(args->pmdp);
 		pte_free(args->mm, args->start_ptep);
 		mm_dec_nr_ptes(args->mm);
 	}
 
 	if (args->start_pmdp) {
+		pud_clear(args->pudp);
 		pmd_free(args->mm, args->start_pmdp);
 		mm_dec_nr_pmds(args->mm);
 	}
 
 	if (args->start_pudp) {
+		p4d_clear(args->p4dp);
 		pud_free(args->mm, args->start_pudp);
 		mm_dec_nr_puds(args->mm);
 	}
 
-	if (args->start_p4dp)
+	if (args->start_p4dp) {
+		pgd_clear(args->pgdp);
 		p4d_free(args->mm, args->start_p4dp);
+	}
 
 	/* Free vma and mm struct */
 	if (args->vma)
 		vm_area_free(args->vma);
 
 	if (args->mm)
-		mmdrop(args->mm);
+		mmput(args->mm);
 }
 
 static struct page * __init
diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c
index 2aa12dfa427a..e0968acc03aa 100644
--- a/mm/kasan/kasan_test_c.c
+++ b/mm/kasan/kasan_test_c.c
@@ -47,7 +47,7 @@ static struct {
  * Some tests use these global variables to store return values from function
  * calls that could otherwise be eliminated by the compiler as dead code.
  */
-static volatile void *kasan_ptr_result;
+static void *volatile kasan_ptr_result;
 static volatile int kasan_int_result;
 
 /* Probe for console output: obtains test_status lines of interest. */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 374a6a5193a7..6b40bdfd224c 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 	/* check if the pmd is still valid */
+	vma_start_write(vma);
 	result = check_pmd_still_valid(mm, address, pmd);
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 
-	vma_start_write(vma);
 	anon_vma_lock_write(vma->anon_vma);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address,
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 8d588e685311..84265983f239 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -470,6 +470,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
 {
 	unsigned long flags;
 	struct kmemleak_object *object;
+	bool warn = false;
 
 	/* try the slab allocator first */
 	if (object_cache) {
@@ -488,8 +489,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
 	else if (mem_pool_free_count)
 		object = &mem_pool[--mem_pool_free_count];
 	else
-		pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n");
+		warn = true;
 	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
+	if (warn)
+		pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n");
 
 	return object;
 }
@@ -2181,6 +2184,7 @@ static const struct file_operations kmemleak_fops = {
 static void __kmemleak_do_cleanup(void)
 {
 	struct kmemleak_object *object, *tmp;
+	unsigned int cnt = 0;
 
 	/*
 	 * Kmemleak has already been disabled, no need for RCU list traversal
@@ -2189,6 +2193,10 @@ static void __kmemleak_do_cleanup(void)
 	list_for_each_entry_safe(object, tmp, &object_list, object_list) {
 		__remove_object(object);
 		__delete_object(object);
+
+		/* Call cond_resched() once per 64 iterations to avoid soft lockup */
+		if (!(++cnt & 0x3f))
+			cond_resched();
 	}
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e2e685b971bb..fc30ca4804bf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -853,9 +853,17 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
 #define hwpoison_hugetlb_range	NULL
 #endif
 
+static int hwpoison_test_walk(unsigned long start, unsigned long end,
+			     struct mm_walk *walk)
+{
+	/* We also want to consider pages mapped into VM_PFNMAP. */
+	return 0;
+}
+
 static const struct mm_walk_ops hwpoison_walk_ops = {
 	.pmd_entry = hwpoison_pte_range,
 	.hugetlb_entry = hwpoison_hugetlb_range,
+	.test_walk = hwpoison_test_walk,
 	.walk_lock = PGWALK_RDLOCK,
 };
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 425401b2d4e1..9e5ef39ce73a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -43,8 +43,6 @@
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
 #include <linux/pagewalk.h>
-#include <linux/balloon_compaction.h>
-#include <linux/zsmalloc.h>
 
 #include <asm/tlbflush.h>
 
@@ -53,6 +51,33 @@
 #include "internal.h"
 #include "swap.h"
 
+static const struct movable_operations *offline_movable_ops;
+static const struct movable_operations *zsmalloc_movable_ops;
+
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
+{
+	/*
+	 * We only allow for selected types and don't handle concurrent
+	 * registration attempts yet.
+	 */
+	switch (type) {
+	case PGTY_offline:
+		if (offline_movable_ops && ops)
+			return -EBUSY;
+		offline_movable_ops = ops;
+		break;
+	case PGTY_zsmalloc:
+		if (zsmalloc_movable_ops && ops)
+			return -EBUSY;
+		zsmalloc_movable_ops = ops;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(set_movable_ops);
+
 static const struct movable_operations *page_movable_ops(struct page *page)
 {
 	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
@@ -62,15 +87,12 @@ static const struct movable_operations *page_movable_ops(struct page *page)
 	 * it as movable, the page type must be sticky until the page gets freed
 	 * back to the buddy.
 	 */
-#ifdef CONFIG_BALLOON_COMPACTION
 	if (PageOffline(page))
 		/* Only balloon compaction sets PageOffline pages movable. */
-		return &balloon_mops;
-#endif /* CONFIG_BALLOON_COMPACTION */
-#if defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION)
+		return offline_movable_ops;
 	if (PageZsmalloc(page))
-		return &zsmalloc_mops;
-#endif /* defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) */
+		return zsmalloc_movable_ops;
+
 	return NULL;
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 78bded7acf79..113b48985834 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
 
 static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
 			   pte_t oldpte, pte_t *pte, int target_node,
-			   struct folio **foliop)
+			   struct folio *folio)
 {
-	struct folio *folio = NULL;
 	bool ret = true;
 	bool toptier;
 	int nid;
@@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
 	if (pte_protnone(oldpte))
 		goto skip;
 
-	folio = vm_normal_folio(vma, addr, oldpte);
 	if (!folio)
 		goto skip;
 
@@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
 		folio_xchg_access_time(folio, jiffies_to_msecs(jiffies));
 
 skip:
-	*foliop = folio;
 	return ret;
 }
 
@@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len,
  * retrieve sub-batches.
  */
 static void commit_anon_folio_batch(struct vm_area_struct *vma,
-		struct folio *folio, unsigned long addr, pte_t *ptep,
+		struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep,
 		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
 {
-	struct page *first_page = folio_page(folio, 0);
 	bool expected_anon_exclusive;
 	int sub_batch_idx = 0;
 	int len;
@@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma,
 }
 
 static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
-		struct folio *folio, unsigned long addr, pte_t *ptep,
+		struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep,
 		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
 {
 	bool set_write;
@@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
 				       /* idx = */ 0, set_write, tlb);
 		return;
 	}
-	commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb);
+	commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb);
 }
 
 static long change_pte_range(struct mmu_gather *tlb,
@@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb,
 			const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE;
 			int max_nr_ptes = (end - addr) >> PAGE_SHIFT;
 			struct folio *folio = NULL;
+			struct page *page;
 			pte_t ptent;
 
+			page = vm_normal_page(vma, addr, oldpte);
+			if (page)
+				folio = page_folio(page);
 			/*
 			 * Avoid trapping faults against the zero or KSM
 			 * pages. See similar comment in change_huge_pmd.
 			 */
 			if (prot_numa) {
 				int ret = prot_numa_skip(vma, addr, oldpte, pte,
-							 target_node, &folio);
+							 target_node, folio);
 				if (ret) {
 
 					/* determine batch to skip */
@@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb,
 				}
 			}
 
-			if (!folio)
-				folio = vm_normal_folio(vma, addr, oldpte);
-
 			nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags);
 
 			oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes);
@@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 			 */
 			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
 			     !pte_write(ptent))
-				set_write_prot_commit_flush_ptes(vma, folio,
+				set_write_prot_commit_flush_ptes(vma, folio, page,
 				addr, pte, oldpte, ptent, nr_ptes, tlb);
 			else
 				prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent,
diff --git a/mm/mremap.c b/mm/mremap.c
index 677a4d744df9..e618a706aff5 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -179,6 +179,10 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr
 	if (max_nr == 1)
 		return 1;
 
+	/* Avoid expensive folio lookup if we stand no chance of benefit. */
+	if (pte_batch_hint(ptep, pte) == 1)
+		return 1;
+
 	folio = vm_normal_folio(vma, addr, pte);
 	if (!folio || !folio_test_large(folio))
 		return 1;
@@ -319,6 +323,25 @@ static inline bool arch_supports_page_table_move(void)
 }
 #endif
 
+static inline bool uffd_supports_page_table_move(struct pagetable_move_control *pmc)
+{
+	/*
+	 * If we are moving a VMA that has uffd-wp registered but with
+	 * remap events disabled (new VMA will not be registered with uffd), we
+	 * need to ensure that the uffd-wp state is cleared from all pgtables.
+	 * This means recursing into lower page tables in move_page_tables().
+	 *
+	 * We might get called with VMAs reversed when recovering from a
+	 * failed page table move. In that case, the
+	 * "old"-but-actually-"originally new" VMA during recovery will not have
+	 * a uffd context. Recursing into lower page tables during the original
+	 * move but not during the recovery move will cause trouble, because we
+	 * run into already-existing page tables. So check both VMAs.
+	 */
+	return !vma_has_uffd_without_event_remap(pmc->old) &&
+	       !vma_has_uffd_without_event_remap(pmc->new);
+}
+
 #ifdef CONFIG_HAVE_MOVE_PMD
 static bool move_normal_pmd(struct pagetable_move_control *pmc,
 			pmd_t *old_pmd, pmd_t *new_pmd)
@@ -331,6 +354,8 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc,
 
 	if (!arch_supports_page_table_move())
 		return false;
+	if (!uffd_supports_page_table_move(pmc))
+		return false;
 	/*
 	 * The destination pmd shouldn't be established, free_pgtables()
 	 * should have released it.
@@ -357,15 +382,6 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc,
 	if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
 		return false;
 
-	/* If this pmd belongs to a uffd vma with remap events disabled, we need
-	 * to ensure that the uffd-wp state is cleared from all pgtables. This
-	 * means recursing into lower page tables in move_page_tables(), and we
-	 * can reuse the existing code if we simply treat the entry as "not
-	 * moved".
-	 */
-	if (vma_has_uffd_without_event_remap(vma))
-		return false;
-
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_lock prevents deadlock.
@@ -414,6 +430,8 @@ static bool move_normal_pud(struct pagetable_move_control *pmc,
 
 	if (!arch_supports_page_table_move())
 		return false;
+	if (!uffd_supports_page_table_move(pmc))
+		return false;
 	/*
 	 * The destination pud shouldn't be established, free_pgtables()
 	 * should have released it.
@@ -421,15 +439,6 @@ static bool move_normal_pud(struct pagetable_move_control *pmc,
 	if (WARN_ON_ONCE(!pud_none(*new_pud)))
 		return false;
 
-	/* If this pud belongs to a uffd vma with remap events disabled, we need
-	 * to ensure that the uffd-wp state is cleared from all pgtables. This
-	 * means recursing into lower page tables in move_page_tables(), and we
-	 * can reuse the existing code if we simply treat the entry as "not
-	 * moved".
-	 */
-	if (vma_has_uffd_without_event_remap(vma))
-		return false;
-
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_lock prevents deadlock.
@@ -1616,7 +1625,7 @@ static void notify_uffd(struct vma_remap_struct *vrm, bool failed)
 
 static bool vma_multi_allowed(struct vm_area_struct *vma)
 {
-	struct file *file;
+	struct file *file = vma->vm_file;
 
 	/*
 	 * We can't support moving multiple uffd VMAs as notify requires
@@ -1629,15 +1638,17 @@ static bool vma_multi_allowed(struct vm_area_struct *vma)
 	 * Custom get unmapped area might result in MREMAP_FIXED not
 	 * being obeyed.
 	 */
-	file = vma->vm_file;
-	if (file && !vma_is_shmem(vma) && !is_vm_hugetlb_page(vma)) {
-		const struct file_operations *fop = file->f_op;
-
-		if (fop->get_unmapped_area)
-			return false;
-	}
+	if (!file || !file->f_op->get_unmapped_area)
+		return true;
+	/* Known good. */
+	if (vma_is_shmem(vma))
+		return true;
+	if (is_vm_hugetlb_page(vma))
+		return true;
+	if (file->f_op->get_unmapped_area == thp_get_unmapped_area)
+		return true;
 
-	return true;
+	return false;
 }
 
 static int check_prep_vma(struct vma_remap_struct *vrm)
@@ -1814,10 +1825,11 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 	unsigned long start = vrm->addr;
 	unsigned long end = vrm->addr + vrm->old_len;
 	unsigned long new_addr = vrm->new_addr;
-	bool allowed = true, seen_vma = false;
 	unsigned long target_addr = new_addr;
 	unsigned long res = -EFAULT;
 	unsigned long last_end;
+	bool seen_vma = false;
+
 	VMA_ITERATOR(vmi, current->mm, start);
 
 	/*
@@ -1830,9 +1842,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 		unsigned long addr = max(vma->vm_start, start);
 		unsigned long len = min(end, vma->vm_end) - addr;
 		unsigned long offset, res_vma;
-
-		if (!allowed)
-			return -EFAULT;
+		bool multi_allowed;
 
 		/* No gap permitted at the start of the range. */
 		if (!seen_vma && start < vma->vm_start)
@@ -1861,9 +1871,15 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 		vrm->new_addr = target_addr + offset;
 		vrm->old_len = vrm->new_len = len;
 
-		allowed = vma_multi_allowed(vma);
-		if (seen_vma && !allowed)
-			return -EFAULT;
+		multi_allowed = vma_multi_allowed(vma);
+		if (!multi_allowed) {
+			/* This is not the first VMA, abort immediately. */
+			if (seen_vma)
+				return -EFAULT;
+			/* This is the first, but there are more, abort. */
+			if (vma->vm_end < end)
+				return -EFAULT;
+		}
 
 		res_vma = check_prep_vma(vrm);
 		if (!res_vma)
@@ -1872,7 +1888,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 			return res_vma;
 
 		if (!seen_vma) {
-			VM_WARN_ON_ONCE(allowed && res_vma != new_addr);
+			VM_WARN_ON_ONCE(multi_allowed && res_vma != new_addr);
 			res = res_vma;
 		}
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index cbed91b09640..45e6290e2e8b 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1821,13 +1821,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
 			/* Check if we can move the pmd without splitting it. */
 			if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) ||
 			    !pmd_none(dst_pmdval)) {
-				struct folio *folio = pmd_folio(*src_pmd);
-
-				if (!folio || (!is_huge_zero_folio(folio) &&
-					       !PageAnonExclusive(&folio->page))) {
-					spin_unlock(ptl);
-					err = -EBUSY;
-					break;
+				/* Can be a migration entry */
+				if (pmd_present(*src_pmd)) {
+					struct folio *folio = pmd_folio(*src_pmd);
+
+					if (!is_huge_zero_folio(folio) &&
+					    !PageAnonExclusive(&folio->page)) {
+						spin_unlock(ptl);
+						err = -EBUSY;
+						break;
+					}
 				}
 
 				spin_unlock(ptl);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7de11524a936..a48aec8bfd92 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5772,9 +5772,9 @@ static int __init init_lru_gen(void)
 	if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
 		pr_err("lru_gen: failed to create sysfs group\n");
 
-	debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, 1,
+	debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, false,
 				    &lru_gen_rw_fops);
-	debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, 0,
+	debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, true,
 				    &lru_gen_ro_fops);
 
 	return 0;
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2c5e56a65354..805a10b41266 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2246,9 +2246,16 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool);
 
 static int __init zs_init(void)
 {
+	int rc __maybe_unused;
+
 #ifdef CONFIG_ZPOOL
 	zpool_register_driver(&zs_zpool_driver);
 #endif
+#ifdef CONFIG_COMPACTION
+	rc = set_movable_ops(&zsmalloc_mops, PGTY_zsmalloc);
+	if (rc)
+		return rc;
+#endif
 	zs_stat_init();
 	return 0;
 }
@@ -2258,6 +2265,9 @@ static void __exit zs_exit(void)
 #ifdef CONFIG_ZPOOL
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
+#ifdef CONFIG_COMPACTION
+	set_movable_ops(NULL, PGTY_zsmalloc);
+#endif
 	zs_stat_exit();
 }