Merge tag 'mm-stable-2025-08-03-12-35' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:
 "Significant patch series in this pull request:

   - "mseal cleanups" (Lorenzo Stoakes)

     Some mseal cleaning with no intended functional change.

   - "Optimizations for khugepaged" (David Hildenbrand)

     Improve khugepaged throughput by batching PTE operations for large
     folios. This gain is mainly for arm64.

   - "x86: enable EXECMEM_ROX_CACHE for ftrace and kprobes" (Mike Rapoport)

     A bugfix, additional debug code and cleanups to the execmem code.

   - "mm/shmem, swap: bugfix and improvement of mTHP swap in" (Kairui Song)

     Bugfixes, cleanups and performance improvememnts to the mTHP swapin
     code"

* tag 'mm-stable-2025-08-03-12-35' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (38 commits)
  mm: mempool: fix crash in mempool_free() for zero-minimum pools
  mm: correct type for vmalloc vm_flags fields
  mm/shmem, swap: fix major fault counting
  mm/shmem, swap: rework swap entry and index calculation for large swapin
  mm/shmem, swap: simplify swapin path and result handling
  mm/shmem, swap: never use swap cache and readahead for SWP_SYNCHRONOUS_IO
  mm/shmem, swap: tidy up swap entry splitting
  mm/shmem, swap: tidy up THP swapin checks
  mm/shmem, swap: avoid redundant Xarray lookup during swapin
  x86/ftrace: enable EXECMEM_ROX_CACHE for ftrace allocations
  x86/kprobes: enable EXECMEM_ROX_CACHE for kprobes allocations
  execmem: drop writable parameter from execmem_fill_trapping_insns()
  execmem: add fallback for failures in vmalloc(VM_ALLOW_HUGE_VMAP)
  execmem: move execmem_force_rw() and execmem_restore_rox() before use
  execmem: rework execmem_cache_free()
  execmem: introduce execmem_alloc_rw()
  execmem: drop unused execmem_update_copy()
  mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped
  mm/rmap: add anon_vma lifetime debug check
  mm: remove mm/io-mapping.c
  ...

21 files changed, 518 insertions, 418 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index d5d4eca947a6..e443fe8cd6cf 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1242,10 +1242,6 @@ config KMAP_LOCAL
 config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
 	bool
 
-# struct io_mapping based helper.  Selected by drivers that need them
-config IO_MAPPING
-	bool
-
 config MEMFD_CREATE
 	bool "Enable memfd_create() system call" if EXPERT
 
diff --git a/mm/Makefile b/mm/Makefile
index 1a7a11d4933d..ef54aa615d9d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -141,7 +141,6 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
-obj-$(CONFIG_IO_MAPPING) += io-mapping.o
 obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 94af19c4dfed..87e825349bdf 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -711,6 +711,10 @@ static void damos_va_migrate_dests_add(struct folio *folio,
 		target -= dests->weight_arr[i];
 	}
 
+	/* If the folio is already in the right node, don't do anything */
+	if (folio_nid(folio) == dests->node_id_arr[i])
+		return;
+
 isolate:
 	if (!folio_isolate_lru(folio))
 		return;
diff --git a/mm/execmem.c b/mm/execmem.c
index 627e6cf64f4f..0822305413ec 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -26,7 +26,7 @@ static struct execmem_info default_execmem_info __ro_after_init;
 
 #ifdef CONFIG_MMU
 static void *execmem_vmalloc(struct execmem_range *range, size_t size,
-			     pgprot_t pgprot, vm_flags_t vm_flags)
+			     pgprot_t pgprot, unsigned long vm_flags)
 {
 	bool kasan = range->flags & EXECMEM_KASAN_SHADOW;
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_NOWARN;
@@ -82,7 +82,7 @@ struct vm_struct *execmem_vmap(size_t size)
 }
 #else
 static void *execmem_vmalloc(struct execmem_range *range, size_t size,
-			     pgprot_t pgprot, vm_flags_t vm_flags)
+			     pgprot_t pgprot, unsigned long vm_flags)
 {
 	return vmalloc(size);
 }
@@ -93,8 +93,15 @@ struct execmem_cache {
 	struct mutex mutex;
 	struct maple_tree busy_areas;
 	struct maple_tree free_areas;
+	unsigned int pending_free_cnt;	/* protected by mutex */
 };
 
+/* delay to schedule asynchronous free if fast path free fails */
+#define FREE_DELAY	(msecs_to_jiffies(10))
+
+/* mark entries in busy_areas that should be freed asynchronously */
+#define PENDING_FREE_MASK	(1 << (PAGE_SHIFT - 1))
+
 static struct execmem_cache execmem_cache = {
 	.mutex = __MUTEX_INITIALIZER(execmem_cache.mutex),
 	.busy_areas = MTREE_INIT_EXT(busy_areas, MT_FLAGS_LOCK_EXTERN,
@@ -130,6 +137,27 @@ err_restore:
 	return err;
 }
 
+static int execmem_force_rw(void *ptr, size_t size)
+{
+	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)ptr;
+	int ret;
+
+	ret = set_memory_nx(addr, nr);
+	if (ret)
+		return ret;
+
+	return set_memory_rw(addr, nr);
+}
+
+int execmem_restore_rox(void *ptr, size_t size)
+{
+	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)ptr;
+
+	return set_memory_rox(addr, nr);
+}
+
 static void execmem_cache_clean(struct work_struct *work)
 {
 	struct maple_tree *free_areas = &execmem_cache.free_areas;
@@ -155,20 +183,17 @@ static void execmem_cache_clean(struct work_struct *work)
 
 static DECLARE_WORK(execmem_cache_clean_work, execmem_cache_clean);
 
-static int execmem_cache_add(void *ptr, size_t size)
+static int execmem_cache_add_locked(void *ptr, size_t size, gfp_t gfp_mask)
 {
 	struct maple_tree *free_areas = &execmem_cache.free_areas;
-	struct mutex *mutex = &execmem_cache.mutex;
 	unsigned long addr = (unsigned long)ptr;
 	MA_STATE(mas, free_areas, addr - 1, addr + 1);
 	unsigned long lower, upper;
 	void *area = NULL;
-	int err;
 
 	lower = addr;
 	upper = addr + size - 1;
 
-	mutex_lock(mutex);
 	area = mas_walk(&mas);
 	if (area && mas.last == addr - 1)
 		lower = mas.index;
@@ -178,12 +203,14 @@ static int execmem_cache_add(void *ptr, size_t size)
 		upper = mas.last;
 
 	mas_set_range(&mas, lower, upper);
-	err = mas_store_gfp(&mas, (void *)lower, GFP_KERNEL);
-	mutex_unlock(mutex);
-	if (err)
-		return err;
+	return mas_store_gfp(&mas, (void *)lower, gfp_mask);
+}
 
-	return 0;
+static int execmem_cache_add(void *ptr, size_t size, gfp_t gfp_mask)
+{
+	guard(mutex)(&execmem_cache.mutex);
+
+	return execmem_cache_add_locked(ptr, size, gfp_mask);
 }
 
 static bool within_range(struct execmem_range *range, struct ma_state *mas,
@@ -256,7 +283,7 @@ out_unlock:
 
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
-	vm_flags_t vm_flags = VM_ALLOW_HUGE_VMAP;
+	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
 	struct vm_struct *vm;
 	size_t alloc_size;
 	int err = -ENOMEM;
@@ -264,6 +291,11 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 
 	alloc_size = round_up(size, PMD_SIZE);
 	p = execmem_vmalloc(range, alloc_size, PAGE_KERNEL, vm_flags);
+	if (!p) {
+		alloc_size = size;
+		p = execmem_vmalloc(range, alloc_size, PAGE_KERNEL, vm_flags);
+	}
+
 	if (!p)
 		return err;
 
@@ -272,13 +304,13 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 		goto err_free_mem;
 
 	/* fill memory with instructions that will trap */
-	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
+	execmem_fill_trapping_insns(p, alloc_size);
 
 	err = set_memory_rox((unsigned long)p, vm->nr_pages);
 	if (err)
 		goto err_free_mem;
 
-	err = execmem_cache_add(p, alloc_size);
+	err = execmem_cache_add(p, alloc_size, GFP_KERNEL);
 	if (err)
 		goto err_reset_direct_map;
 
@@ -307,57 +339,117 @@ static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
 	return __execmem_cache_alloc(range, size);
 }
 
-static bool execmem_cache_free(void *ptr)
+static inline bool is_pending_free(void *ptr)
 {
-	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
-	struct mutex *mutex = &execmem_cache.mutex;
-	unsigned long addr = (unsigned long)ptr;
-	MA_STATE(mas, busy_areas, addr, addr);
-	size_t size;
-	void *area;
+	return ((unsigned long)ptr & PENDING_FREE_MASK);
+}
 
-	mutex_lock(mutex);
-	area = mas_walk(&mas);
-	if (!area) {
-		mutex_unlock(mutex);
-		return false;
-	}
-	size = mas_range_len(&mas);
+static inline void *pending_free_set(void *ptr)
+{
+	return (void *)((unsigned long)ptr | PENDING_FREE_MASK);
+}
 
-	mas_store_gfp(&mas, NULL, GFP_KERNEL);
-	mutex_unlock(mutex);
+static inline void *pending_free_clear(void *ptr)
+{
+	return (void *)((unsigned long)ptr & ~PENDING_FREE_MASK);
+}
 
-	execmem_fill_trapping_insns(ptr, size, /* writable = */ false);
+static int __execmem_cache_free(struct ma_state *mas, void *ptr, gfp_t gfp_mask)
+{
+	size_t size = mas_range_len(mas);
+	int err;
 
-	execmem_cache_add(ptr, size);
+	err = execmem_force_rw(ptr, size);
+	if (err)
+		return err;
 
-	schedule_work(&execmem_cache_clean_work);
+	execmem_fill_trapping_insns(ptr, size);
+	execmem_restore_rox(ptr, size);
 
-	return true;
+	err = execmem_cache_add_locked(ptr, size, gfp_mask);
+	if (err)
+		return err;
+
+	mas_store_gfp(mas, NULL, gfp_mask);
+	return 0;
 }
 
-int execmem_make_temp_rw(void *ptr, size_t size)
+static void execmem_cache_free_slow(struct work_struct *work);
+static DECLARE_DELAYED_WORK(execmem_cache_free_work, execmem_cache_free_slow);
+
+static void execmem_cache_free_slow(struct work_struct *work)
 {
-	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long addr = (unsigned long)ptr;
-	int ret;
+	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
+	MA_STATE(mas, busy_areas, 0, ULONG_MAX);
+	void *area;
 
-	ret = set_memory_nx(addr, nr);
-	if (ret)
-		return ret;
+	guard(mutex)(&execmem_cache.mutex);
 
-	return set_memory_rw(addr, nr);
+	if (!execmem_cache.pending_free_cnt)
+		return;
+
+	mas_for_each(&mas, area, ULONG_MAX) {
+		if (!is_pending_free(area))
+			continue;
+
+		area = pending_free_clear(area);
+		if (__execmem_cache_free(&mas, area, GFP_KERNEL))
+			continue;
+
+		execmem_cache.pending_free_cnt--;
+	}
+
+	if (execmem_cache.pending_free_cnt)
+		schedule_delayed_work(&execmem_cache_free_work, FREE_DELAY);
+	else
+		schedule_work(&execmem_cache_clean_work);
 }
 
-int execmem_restore_rox(void *ptr, size_t size)
+static bool execmem_cache_free(void *ptr)
 {
-	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
 	unsigned long addr = (unsigned long)ptr;
+	MA_STATE(mas, busy_areas, addr, addr);
+	void *area;
+	int err;
 
-	return set_memory_rox(addr, nr);
+	guard(mutex)(&execmem_cache.mutex);
+
+	area = mas_walk(&mas);
+	if (!area)
+		return false;
+
+	err = __execmem_cache_free(&mas, area, GFP_KERNEL | __GFP_NORETRY);
+	if (err) {
+		/*
+		 * mas points to exact slot we've got the area from, nothing
+		 * else can modify the tree because of the mutex, so there
+		 * won't be any allocations in mas_store_gfp() and it will just
+		 * change the pointer.
+		 */
+		area = pending_free_set(area);
+		mas_store_gfp(&mas, area, GFP_KERNEL);
+		execmem_cache.pending_free_cnt++;
+		schedule_delayed_work(&execmem_cache_free_work, FREE_DELAY);
+		return true;
+	}
+
+	schedule_work(&execmem_cache_clean_work);
+
+	return true;
 }
 
 #else /* CONFIG_ARCH_HAS_EXECMEM_ROX */
+/*
+ * when ROX cache is not used the permissions defined by architectures for
+ * execmem ranges that are updated before use (e.g. EXECMEM_MODULE_TEXT) must
+ * be writable anyway
+ */
+static inline int execmem_force_rw(void *ptr, size_t size)
+{
+	return 0;
+}
+
 static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
 {
 	return NULL;
@@ -373,9 +465,9 @@ void *execmem_alloc(enum execmem_type type, size_t size)
 {
 	struct execmem_range *range = &execmem_info->ranges[type];
 	bool use_cache = range->flags & EXECMEM_ROX_CACHE;
-	vm_flags_t vm_flags = VM_FLUSH_RESET_PERMS;
+	unsigned long vm_flags = VM_FLUSH_RESET_PERMS;
 	pgprot_t pgprot = range->pgprot;
-	void *p;
+	void *p = NULL;
 
 	size = PAGE_ALIGN(size);
 
@@ -387,6 +479,21 @@ void *execmem_alloc(enum execmem_type type, size_t size)
 	return kasan_reset_tag(p);
 }
 
+void *execmem_alloc_rw(enum execmem_type type, size_t size)
+{
+	void *p __free(execmem) = execmem_alloc(type, size);
+	int err;
+
+	if (!p)
+		return NULL;
+
+	err = execmem_force_rw(p, size);
+	if (err)
+		return NULL;
+
+	return no_free_ptr(p);
+}
+
 void execmem_free(void *ptr)
 {
 	/*
@@ -399,11 +506,6 @@ void execmem_free(void *ptr)
 		vfree(ptr);
 }
 
-void *execmem_update_copy(void *dst, const void *src, size_t size)
-{
-	return text_poke_copy(dst, src, size);
-}
-
 bool execmem_is_rox(enum execmem_type type)
 {
 	return !!(execmem_info->ranges[type].flags & EXECMEM_ROX_CACHE);
diff --git a/mm/internal.h b/mm/internal.h
index 1da16d550a45..45b725c3dc03 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1391,7 +1391,7 @@ int migrate_device_coherent_folio(struct folio *folio);
 
 struct vm_struct *__get_vm_area_node(unsigned long size,
 				     unsigned long align, unsigned long shift,
-				     vm_flags_t vm_flags, unsigned long start,
+				     unsigned long vm_flags, unsigned long start,
 				     unsigned long end, int node, gfp_t gfp_mask,
 				     const void *caller);
 
diff --git a/mm/io-mapping.c b/mm/io-mapping.c
deleted file mode 100644
index d3586e95c12c..000000000000
--- a/mm/io-mapping.c
+++ /dev/null
@@ -1,30 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-
-#include <linux/mm.h>
-#include <linux/io-mapping.h>
-
-/**
- * io_mapping_map_user - remap an I/O mapping to userspace
- * @iomap: the source io_mapping
- * @vma: user vma to map to
- * @addr: target user address to start at
- * @pfn: physical address of kernel memory
- * @size: size of map area
- *
- *  Note: this is only safe if the mm semaphore is held when called.
- */
-int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pfn, unsigned long size)
-{
-	vm_flags_t expected_flags = VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
-
-	if (WARN_ON_ONCE((vma->vm_flags & expected_flags) != expected_flags))
-		return -EINVAL;
-
-	pgprot_t remap_prot = __pgprot((pgprot_val(iomap->prot) & _PAGE_CACHE_MASK) |
-				       (pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK));
-
-	/* We rely on prevalidation of the io-mapping to skip pfnmap tracking. */
-	return remap_pfn_range_notrack(vma, addr, pfn, size, remap_prot);
-}
-EXPORT_SYMBOL_GPL(io_mapping_map_user);
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index ed4873e18c75..9142964ab9c9 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -230,16 +230,12 @@ static bool check_slab_allocation(struct kmem_cache *cache, void *object,
 }
 
 static inline void poison_slab_object(struct kmem_cache *cache, void *object,
-				      bool init, bool still_accessible)
+				      bool init)
 {
 	void *tagged_object = object;
 
 	object = kasan_reset_tag(object);
 
-	/* RCU slabs could be legally used after free within the RCU period. */
-	if (unlikely(still_accessible))
-		return;
-
 	kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
 			KASAN_SLAB_FREE, init);
 
@@ -261,7 +257,22 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init,
 	if (!kasan_arch_is_ready() || is_kfence_address(object))
 		return false;
 
-	poison_slab_object(cache, object, init, still_accessible);
+	/*
+	 * If this point is reached with an object that must still be
+	 * accessible under RCU, we can't poison it; in that case, also skip the
+	 * quarantine. This should mostly only happen when CONFIG_SLUB_RCU_DEBUG
+	 * has been disabled manually.
+	 *
+	 * Putting the object on the quarantine wouldn't help catch UAFs (since
+	 * we can't poison it here), and it would mask bugs caused by
+	 * SLAB_TYPESAFE_BY_RCU users not being careful enough about object
+	 * reuse; so overall, putting the object into the quarantine here would
+	 * be counterproductive.
+	 */
+	if (still_accessible)
+		return false;
+
+	poison_slab_object(cache, object, init);
 
 	/*
 	 * If the object is put into quarantine, do not let slab put the object
@@ -519,7 +530,7 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 	if (check_slab_allocation(slab->slab_cache, ptr, ip))
 		return false;
 
-	poison_slab_object(slab->slab_cache, ptr, false, false);
+	poison_slab_object(slab->slab_cache, ptr, false);
 	return true;
 }
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a55fb1dcd224..374a6a5193a7 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -700,12 +700,15 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 						spinlock_t *ptl,
 						struct list_head *compound_pagelist)
 {
+	unsigned long end = address + HPAGE_PMD_SIZE;
 	struct folio *src, *tmp;
-	pte_t *_pte;
 	pte_t pteval;
+	pte_t *_pte;
+	unsigned int nr_ptes;
 
-	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
-	     _pte++, address += PAGE_SIZE) {
+	for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte += nr_ptes,
+	     address += nr_ptes * PAGE_SIZE) {
+		nr_ptes = 1;
 		pteval = ptep_get(_pte);
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
@@ -722,18 +725,26 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 			struct page *src_page = pte_page(pteval);
 
 			src = page_folio(src_page);
-			if (!folio_test_large(src))
+
+			if (folio_test_large(src)) {
+				unsigned int max_nr_ptes = (end - address) >> PAGE_SHIFT;
+
+				nr_ptes = folio_pte_batch(src, _pte, pteval, max_nr_ptes);
+			} else {
 				release_pte_folio(src);
+			}
+
 			/*
 			 * ptl mostly unnecessary, but preempt has to
 			 * be disabled to update the per-cpu stats
 			 * inside folio_remove_rmap_pte().
 			 */
 			spin_lock(ptl);
-			ptep_clear(vma->vm_mm, address, _pte);
-			folio_remove_rmap_pte(src, src_page, vma);
+			clear_ptes(vma->vm_mm, address, _pte, nr_ptes);
+			folio_remove_rmap_ptes(src, src_page, nr_ptes, vma);
 			spin_unlock(ptl);
-			free_folio_and_swap_cache(src);
+			free_swap_cache(src);
+			folio_put_refs(src, nr_ptes);
 		}
 	}
 
@@ -1492,15 +1503,17 @@ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
 int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 			    bool install_pmd)
 {
+	int nr_mapped_ptes = 0, result = SCAN_FAIL;
+	unsigned int nr_batch_ptes;
 	struct mmu_notifier_range range;
 	bool notified = false;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	unsigned long end = haddr + HPAGE_PMD_SIZE;
 	struct vm_area_struct *vma = vma_lookup(mm, haddr);
 	struct folio *folio;
 	pte_t *start_pte, *pte;
 	pmd_t *pmd, pgt_pmd;
 	spinlock_t *pml = NULL, *ptl;
-	int nr_ptes = 0, result = SCAN_FAIL;
 	int i;
 
 	mmap_assert_locked(mm);
@@ -1614,11 +1627,15 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		goto abort;
 
 	/* step 2: clear page table and adjust rmap */
-	for (i = 0, addr = haddr, pte = start_pte;
-	     i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
+	for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR;
+	     i += nr_batch_ptes, addr += nr_batch_ptes * PAGE_SIZE,
+	     pte += nr_batch_ptes) {
+		unsigned int max_nr_batch_ptes = (end - addr) >> PAGE_SHIFT;
 		struct page *page;
 		pte_t ptent = ptep_get(pte);
 
+		nr_batch_ptes = 1;
+
 		if (pte_none(ptent))
 			continue;
 		/*
@@ -1632,26 +1649,29 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 			goto abort;
 		}
 		page = vm_normal_page(vma, addr, ptent);
+
 		if (folio_page(folio, i) != page)
 			goto abort;
 
+		nr_batch_ptes = folio_pte_batch(folio, pte, ptent, max_nr_batch_ptes);
+
 		/*
 		 * Must clear entry, or a racing truncate may re-remove it.
 		 * TLB flush can be left until pmdp_collapse_flush() does it.
 		 * PTE dirty? Shmem page is already dirty; file is read-only.
 		 */
-		ptep_clear(mm, addr, pte);
-		folio_remove_rmap_pte(folio, page, vma);
-		nr_ptes++;
+		clear_ptes(mm, addr, pte, nr_batch_ptes);
+		folio_remove_rmap_ptes(folio, page, nr_batch_ptes, vma);
+		nr_mapped_ptes += nr_batch_ptes;
 	}
 
 	if (!pml)
 		spin_unlock(ptl);
 
 	/* step 3: set proper refcount and mm_counters. */
-	if (nr_ptes) {
-		folio_ref_sub(folio, nr_ptes);
-		add_mm_counter(mm, mm_counter_file(folio), -nr_ptes);
+	if (nr_mapped_ptes) {
+		folio_ref_sub(folio, nr_mapped_ptes);
+		add_mm_counter(mm, mm_counter_file(folio), -nr_mapped_ptes);
 	}
 
 	/* step 4: remove empty page table */
@@ -1684,10 +1704,10 @@ maybe_install_pmd:
 			: SCAN_SUCCEED;
 	goto drop_folio;
 abort:
-	if (nr_ptes) {
+	if (nr_mapped_ptes) {
 		flush_tlb_mm(mm);
-		folio_ref_sub(folio, nr_ptes);
-		add_mm_counter(mm, mm_counter_file(folio), -nr_ptes);
+		folio_ref_sub(folio, nr_mapped_ptes);
+		add_mm_counter(mm, mm_counter_file(folio), -nr_mapped_ptes);
 	}
 unlock:
 	if (start_pte)
diff --git a/mm/madvise.c b/mm/madvise.c
index bb80fc5ea08f..35ed4ab0d7c5 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/mm_inline.h>
+#include <linux/mmu_context.h>
 #include <linux/string.h>
 #include <linux/uio.h>
 #include <linux/ksm.h>
@@ -1256,6 +1257,74 @@ static long madvise_guard_remove(struct madvise_behavior *madv_behavior)
 			       &guard_remove_walk_ops, NULL);
 }
 
+#ifdef CONFIG_64BIT
+/* Does the madvise operation result in discarding of mapped data? */
+static bool is_discard(int behavior)
+{
+	switch (behavior) {
+	case MADV_FREE:
+	case MADV_DONTNEED:
+	case MADV_DONTNEED_LOCKED:
+	case MADV_REMOVE:
+	case MADV_DONTFORK:
+	case MADV_WIPEONFORK:
+	case MADV_GUARD_INSTALL:
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * We are restricted from madvise()'ing mseal()'d VMAs only in very particular
+ * circumstances - discarding of data from read-only anonymous SEALED mappings.
+ *
+ * This is because users cannot trivally discard data from these VMAs, and may
+ * only do so via an appropriate madvise() call.
+ */
+static bool can_madvise_modify(struct madvise_behavior *madv_behavior)
+{
+	struct vm_area_struct *vma = madv_behavior->vma;
+
+	/* If the VMA isn't sealed we're good. */
+	if (!vma_is_sealed(vma))
+		return true;
+
+	/* For a sealed VMA, we only care about discard operations. */
+	if (!is_discard(madv_behavior->behavior))
+		return true;
+
+	/*
+	 * We explicitly permit all file-backed mappings, whether MAP_SHARED or
+	 * MAP_PRIVATE.
+	 *
+	 * The latter causes some complications. Because now, one can mmap()
+	 * read/write a MAP_PRIVATE mapping, write to it, then mprotect()
+	 * read-only, mseal() and a discard will be permitted.
+	 *
+	 * However, in order to avoid issues with potential use of madvise(...,
+	 * MADV_DONTNEED) of mseal()'d .text mappings we, for the time being,
+	 * permit this.
+	 */
+	if (!vma_is_anonymous(vma))
+		return true;
+
+	/* If the user could write to the mapping anyway, then this is fine. */
+	if ((vma->vm_flags & VM_WRITE) &&
+	    arch_vma_access_permitted(vma, /* write= */ true,
+			/* execute= */ false, /* foreign= */ false))
+		return true;
+
+	/* Otherwise, we are not permitted to perform this operation. */
+	return false;
+}
+#else
+static bool can_madvise_modify(struct madvise_behavior *madv_behavior)
+{
+	return true;
+}
+#endif
+
 /*
  * Apply an madvise behavior to a region of a vma.  madvise_update_vma
  * will handle splitting a vm area into separate areas, each area with its own
@@ -1269,7 +1338,7 @@ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior)
 	struct madvise_behavior_range *range = &madv_behavior->range;
 	int error;
 
-	if (unlikely(!can_modify_vma_madv(madv_behavior->vma, behavior)))
+	if (unlikely(!can_madvise_modify(madv_behavior)))
 		return -EPERM;
 
 	switch (behavior) {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 3047b9ac667e..e2e685b971bb 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -837,11 +837,17 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
 			    struct mm_walk *walk)
 {
 	struct hwpoison_walk *hwp = walk->private;
-	pte_t pte = huge_ptep_get(walk->mm, addr, ptep);
 	struct hstate *h = hstate_vma(walk->vma);
+	spinlock_t *ptl;
+	pte_t pte;
+	int ret;
 
-	return check_hwpoisoned_entry(pte, addr, huge_page_shift(h),
-				      hwp->pfn, &hwp->tk);
+	ptl = huge_pte_lock(h, walk->mm, ptep);
+	pte = huge_ptep_get(walk->mm, addr, ptep);
+	ret = check_hwpoisoned_entry(pte, addr, huge_page_shift(h),
+					hwp->pfn, &hwp->tk);
+	spin_unlock(ptl);
+	return ret;
 }
 #else
 #define hwpoison_hugetlb_range	NULL
diff --git a/mm/mempool.c b/mm/mempool.c
index 204a216b6418..1c38e873e546 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -136,7 +136,7 @@ static void kasan_unpoison_element(mempool_t *pool, void *element)
 
 static __always_inline void add_element(mempool_t *pool, void *element)
 {
-	BUG_ON(pool->curr_nr >= pool->min_nr);
+	BUG_ON(pool->min_nr != 0 && pool->curr_nr >= pool->min_nr);
 	poison_element(pool, element);
 	if (kasan_poison_element(pool, element))
 		pool->elements[pool->curr_nr++] = element;
@@ -202,16 +202,20 @@ int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
 	pool->alloc	= alloc_fn;
 	pool->free	= free_fn;
 	init_waitqueue_head(&pool->wait);
-
-	pool->elements = kmalloc_array_node(min_nr, sizeof(void *),
+	/*
+	 * max() used here to ensure storage for at least 1 element to support
+	 * zero minimum pool
+	 */
+	pool->elements = kmalloc_array_node(max(1, min_nr), sizeof(void *),
 					    gfp_mask, node_id);
 	if (!pool->elements)
 		return -ENOMEM;
 
 	/*
-	 * First pre-allocate the guaranteed number of buffers.
+	 * First pre-allocate the guaranteed number of buffers,
+	 * also pre-allocate 1 element for zero minimum pool.
 	 */
-	while (pool->curr_nr < pool->min_nr) {
+	while (pool->curr_nr < max(1, pool->min_nr)) {
 		void *element;
 
 		element = pool->alloc(gfp_mask, pool->pool_data);
@@ -555,20 +559,12 @@ void mempool_free(void *element, mempool_t *pool)
 	 * wake-up path of previous test. This explicit check ensures the
 	 * allocation of element when both min_nr and curr_nr are 0, and
 	 * any active waiters are properly awakened.
-	 *
-	 * Inline the same logic as previous test, add_element() cannot be
-	 * directly used here since it has BUG_ON to deny if min_nr equals
-	 * curr_nr, so here picked rest of add_element() to use without
-	 * BUG_ON check.
 	 */
 	if (unlikely(pool->min_nr == 0 &&
 		     READ_ONCE(pool->curr_nr) == 0)) {
 		spin_lock_irqsave(&pool->lock, flags);
 		if (likely(pool->curr_nr == 0)) {
-			/* Inline the logic of add_element() */
-			poison_element(pool, element);
-			if (kasan_poison_element(pool, element))
-				pool->elements[pool->curr_nr++] = element;
+			add_element(pool, element);
 			spin_unlock_irqrestore(&pool->lock, flags);
 			if (wq_has_sleeper(&pool->wait))
 				wake_up(&pool->wait);
diff --git a/mm/mincore.c b/mm/mincore.c
index 42d6c9c8da86..10dabefc3acc 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -29,7 +29,9 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
 #ifdef CONFIG_HUGETLB_PAGE
 	unsigned char present;
 	unsigned char *vec = walk->private;
+	spinlock_t *ptl;
 
+	ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
 	/*
 	 * Hugepages under user process are always in RAM and never
 	 * swapped out, but theoretically it needs to be checked.
@@ -38,6 +40,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
 	for (; addr != end; vec++, addr += PAGE_SIZE)
 		*vec = present;
 	walk->private = vec;
+	spin_unlock(ptl);
 #else
 	BUG();
 #endif
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
index 729fb7d0dd59..b006cec8e6fe 100644
--- a/mm/mmap_lock.c
+++ b/