13 hotfixes. 6 are cc:stable and the remainder address post-6.15 issues

or aren't considered necessary for -stable kernels.  11 are for MM.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCaENzlAAKCRDdBJ7gKXxA
 joNYAP9n38QNDUoRR6ChFikzzY77q4alD2NL0aqXBZdcSRXoUgEAlQ8Ea+t6xnzp
 GnH+cnsA6FDp4F6lIoZBdENJyBYrkQE=
 =ud9O
 -----END PGP SIGNATURE-----

Merge tag 'mm-hotfixes-stable-2025-06-06-16-02' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "13 hotfixes.

  6 are cc:stable and the remainder address post-6.15 issues or aren't
  considered necessary for -stable kernels. 11 are for MM"

* tag 'mm-hotfixes-stable-2025-06-06-16-02' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  kernel/rcu/tree_stall: add /sys/kernel/rcu_stall_count
  MAINTAINERS: add mm swap section
  kmsan: test: add module description
  MAINTAINERS: add tlb trace events to MMU GATHER AND TLB INVALIDATION
  mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race
  mm/hugetlb: unshare page tables during VMA split, not before
  MAINTAINERS: add Alistair as reviewer of mm memory policy
  iov_iter: use iov_offset for length calculation in iov_iter_aligned_bvec
  mm/mempolicy: fix incorrect freeing of wi_kobj
  alloc_tag: handle module codetag load errors as module load failures
  mm/madvise: handle madvise_lock() failure during race unwinding
  mm: fix vmstat after removing NR_BOUNCE
  KVM: s390: rename PROT_NONE to PROT_TYPE_DUMMY

MAINTAINERS

@@ -15818,6 +15818,7 @@ R:	Rakie Kim <rakie.kim@sk.com>
 R:	Byungchul Park <byungchul@sk.com>
 R:	Gregory Price <gourry@gourry.net>
 R:	Ying Huang <ying.huang@linux.alibaba.com>
+R:	Alistair Popple <apopple@nvidia.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org
@@ -15889,6 +15890,25 @@ S:	Maintained
 F:	include/linux/secretmem.h
 F:	mm/secretmem.c
 
+MEMORY MANAGEMENT - SWAP
+M:	Andrew Morton <akpm@linux-foundation.org>
+R:	Kemeng Shi <shikemeng@huaweicloud.com>
+R:	Kairui Song <kasong@tencent.com>
+R:	Nhat Pham <nphamcs@gmail.com>
+R:	Baoquan He <bhe@redhat.com>
+R:	Barry Song <baohua@kernel.org>
+R:	Chris Li <chrisl@kernel.org>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	include/linux/swap.h
+F:	include/linux/swapfile.h
+F:	include/linux/swapops.h
+F:	mm/page_io.c
+F:	mm/swap.c
+F:	mm/swap.h
+F:	mm/swap_state.c
+F:	mm/swapfile.c
+
 MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@redhat.com>
@@ -16727,6 +16747,7 @@ L:	linux-mm@kvack.org
 S:	Maintained
 F:	arch/*/include/asm/tlb.h
 F:	include/asm-generic/tlb.h
+F:	include/trace/events/tlb.h
 F:	mm/mmu_gather.c
 
 MN88472 MEDIA DRIVER

arch/s390/kvm/gaccess.c

@@ -319,7 +319,7 @@ enum prot_type {
 	PROT_TYPE_DAT  = 3,
 	PROT_TYPE_IEP  = 4,
 	/* Dummy value for passing an initialized value when code != PGM_PROTECTION */
-	PROT_NONE,
+	PROT_TYPE_DUMMY,
 };
 
 static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar,
@@ -335,7 +335,7 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 	switch (code) {
 	case PGM_PROTECTION:
 		switch (prot) {
-		case PROT_NONE:
+		case PROT_TYPE_DUMMY:
 			/* We should never get here, acts like termination */
 			WARN_ON_ONCE(1);
 			break;
@@ -805,7 +805,7 @@ static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 			gpa = kvm_s390_real_to_abs(vcpu, ga);
 			if (!kvm_is_gpa_in_memslot(vcpu->kvm, gpa)) {
 				rc = PGM_ADDRESSING;
-				prot = PROT_NONE;
+				prot = PROT_TYPE_DUMMY;
 			}
 		}
 		if (rc)
@@ -963,7 +963,7 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 		if (rc == PGM_PROTECTION)
 			prot = PROT_TYPE_KEYC;
 		else
-			prot = PROT_NONE;
+			prot = PROT_TYPE_DUMMY;
 		rc = trans_exc_ending(vcpu, rc, ga, ar, mode, prot, terminate);
 	}
 out_unlock:

include/linux/codetag.h

@@ -36,8 +36,8 @@ union codetag_ref {
 struct codetag_type_desc {
 	const char *section;
 	size_t tag_size;
-	void (*module_load)(struct module *mod,
+	int (*module_load)(struct module *mod,
-			    struct codetag *start, struct codetag *end);
+			   struct codetag *start, struct codetag *end);
 	void (*module_unload)(struct module *mod,
 			      struct codetag *start, struct codetag *end);
 #ifdef CONFIG_MODULES
@@ -89,7 +89,7 @@ void *codetag_alloc_module_section(struct module *mod, const char *name,
 				   unsigned long align);
 void codetag_free_module_sections(struct module *mod);
 void codetag_module_replaced(struct module *mod, struct module *new_mod);
-void codetag_load_module(struct module *mod);
+int codetag_load_module(struct module *mod);
 void codetag_unload_module(struct module *mod);
 
 #else /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */
@@ -103,7 +103,7 @@ codetag_alloc_module_section(struct module *mod, const char *name,
 			     unsigned long align) { return NULL; }
 static inline void codetag_free_module_sections(struct module *mod) {}
 static inline void codetag_module_replaced(struct module *mod, struct module *new_mod) {}
-static inline void codetag_load_module(struct module *mod) {}
+static inline int codetag_load_module(struct module *mod) { return 0; }
 static inline void codetag_unload_module(struct module *mod) {}
 
 #endif /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */

include/linux/hugetlb.h

@@ -279,6 +279,7 @@ bool is_hugetlb_entry_migration(pte_t pte);
 bool is_hugetlb_entry_hwpoisoned(pte_t pte);
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 void fixup_hugetlb_reservations(struct vm_area_struct *vma);
+void hugetlb_split(struct vm_area_struct *vma, unsigned long addr);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
@@ -476,6 +477,8 @@ static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
 {
 }
 
+static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {}
+
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #ifndef pgd_write

kernel/module/main.c

@@ -3386,11 +3386,12 @@ static int load_module(struct load_info *info, const char __user *uargs,
 			goto sysfs_cleanup;
 	}
 
+	if (codetag_load_module(mod))
+		goto sysfs_cleanup;
+
 	/* Get rid of temporary copy. */
 	free_copy(info, flags);
 
-	codetag_load_module(mod);
-
 	/* Done! */
 	trace_module_load(mod);
 

kernel/rcu/tree_stall.h

@@ -20,6 +20,28 @@
 int sysctl_panic_on_rcu_stall __read_mostly;
 int sysctl_max_rcu_stall_to_panic __read_mostly;
 
+#ifdef CONFIG_SYSFS
+
+static unsigned int rcu_stall_count;
+
+static ssize_t rcu_stall_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+				    char *page)
+{
+	return sysfs_emit(page, "%u\n", rcu_stall_count);
+}
+
+static struct kobj_attribute rcu_stall_count_attr = __ATTR_RO(rcu_stall_count);
+
+static __init int kernel_rcu_stall_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &rcu_stall_count_attr.attr, NULL);
+	return 0;
+}
+
+late_initcall(kernel_rcu_stall_sysfs_init);
+
+#endif // CONFIG_SYSFS
+
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA		(5 * HZ)
 #else
@@ -784,6 +806,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		if (kvm_check_and_clear_guest_paused())
 			return;
 
+#ifdef CONFIG_SYSFS
+		++rcu_stall_count;
+#endif
+
 		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
 		if (READ_ONCE(csd_lock_suppress_rcu_stall) && csd_lock_is_stuck()) {
 			pr_err("INFO: %s detected stall, but suppressed full report due to a stuck CSD-lock.\n", rcu_state.name);

lib/alloc_tag.c

@@ -607,15 +607,16 @@ out:
 	mas_unlock(&mas);
 }
 
-static void load_module(struct module *mod, struct codetag *start, struct codetag *stop)
+static int load_module(struct module *mod, struct codetag *start, struct codetag *stop)
 {
 	/* Allocate module alloc_tag percpu counters */
 	struct alloc_tag *start_tag;
 	struct alloc_tag *stop_tag;
 	struct alloc_tag *tag;
 
+	/* percpu counters for core allocations are already statically allocated */
 	if (!mod)
-		return;
+		return 0;
 
 	start_tag = ct_to_alloc_tag(start);
 	stop_tag = ct_to_alloc_tag(stop);
@@ -627,12 +628,13 @@ static void load_module(struct module *mod, struct codetag *start, struct codeta
 				free_percpu(tag->counters);
 				tag->counters = NULL;
 			}
-			shutdown_mem_profiling(true);
+			pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s\n",
-			pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s. Memory allocation profiling is disabled!\n",
 			       mod->name);
-			break;
+			return -ENOMEM;
 		}
 	}
+
+	return 0;
 }
 
 static void replace_module(struct module *mod, struct module *new_mod)

lib/codetag.c

@@ -167,6 +167,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
 {
 	struct codetag_range range;
 	struct codetag_module *cmod;
+	int mod_id;
 	int err;
 
 	range = get_section_range(mod, cttype->desc.section);
@@ -190,11 +191,20 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
 	cmod->range = range;
 
 	down_write(&cttype->mod_lock);
-	err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL);
+	mod_id = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL);
-	if (err >= 0) {
+	if (mod_id >= 0) {
-		cttype->count += range_size(cttype, &range);
+		if (cttype->desc.module_load) {
-		if (cttype->desc.module_load)
+			err = cttype->desc.module_load(mod, range.start, range.stop);
-			cttype->desc.module_load(mod, range.start, range.stop);
+			if (!err)
+				cttype->count += range_size(cttype, &range);
+			else
+				idr_remove(&cttype->mod_idr, mod_id);
+		} else {
+			cttype->count += range_size(cttype, &range);
+			err = 0;
+		}
+	} else {
+		err = mod_id;
 	}
 	up_write(&cttype->mod_lock);
 
@@ -295,17 +305,23 @@ void codetag_module_replaced(struct module *mod, struct module *new_mod)
 	mutex_unlock(&codetag_lock);
 }
 
-void codetag_load_module(struct module *mod)
+int codetag_load_module(struct module *mod)
 {
 	struct codetag_type *cttype;
+	int ret = 0;
 
 	if (!mod)
-		return;
+		return 0;
 
 	mutex_lock(&codetag_lock);
-	list_for_each_entry(cttype, &codetag_types, link)
+	list_for_each_entry(cttype, &codetag_types, link) {
-		codetag_module_init(cttype, mod);
+		ret = codetag_module_init(cttype, mod);
+		if (ret)
+			break;
+	}
 	mutex_unlock(&codetag_lock);
+
+	return ret;
 }
 
 void codetag_unload_module(struct module *mod)

lib/iov_iter.c

@@ -817,7 +817,7 @@ static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
 	size_t size = i->count;
 
 	do {
-		size_t len = bvec->bv_len;
+		size_t len = bvec->bv_len - skip;
 
 		if (len > size)
 			len = size;

mm/hugetlb.c

@@ -121,7 +121,7 @@ static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
 static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end);
+		unsigned long start, unsigned long end, bool take_locks);
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static void hugetlb_free_folio(struct folio *folio)
@@ -5426,26 +5426,40 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (addr & ~(huge_page_mask(hstate_vma(vma))))
 		return -EINVAL;
+	return 0;
+}
 
+void hugetlb_split(struct vm_area_struct *vma, unsigned long addr)
+{
 	/*
 	 * PMD sharing is only possible for PUD_SIZE-aligned address ranges
 	 * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
 	 * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+	 * This function is called in the middle of a VMA split operation, with
+	 * MM, VMA and rmap all write-locked to prevent concurrent page table
+	 * walks (except hardware and gup_fast()).
 	 */
+	vma_assert_write_locked(vma);
+	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
+
 	if (addr & ~PUD_MASK) {
-		/*
-		 * hugetlb_vm_op_split is called right before we attempt to
-		 * split the VMA. We will need to unshare PMDs in the old and
-		 * new VMAs, so let's unshare before we split.
-		 */
 		unsigned long floor = addr & PUD_MASK;
 		unsigned long ceil = floor + PUD_SIZE;
 
-		if (floor >= vma->vm_start && ceil <= vma->vm_end)
+		if (floor >= vma->vm_start && ceil <= vma->vm_end) {
-			hugetlb_unshare_pmds(vma, floor, ceil);
+			/*
+			 * Locking:
+			 * Use take_locks=false here.
+			 * The file rmap lock is already held.
+			 * The hugetlb VMA lock can't be taken when we already
+			 * hold the file rmap lock, and we don't need it because
+			 * its purpose is to synchronize against concurrent page
+			 * table walks, which are not possible thanks to the
+			 * locks held by our caller.
+			 */
+			hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false);
+		}
 	}
-
-	return 0;
 }
 
 static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma)
@@ -7615,6 +7629,13 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 
 	pud_clear(pud);
+	/*
+	 * Once our caller drops the rmap lock, some other process might be
+	 * using this page table as a normal, non-hugetlb page table.
+	 * Wait for pending gup_fast() in other threads to finish before letting
+	 * that happen.
+	 */
+	tlb_remove_table_sync_one();
 	ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep));
 	mm_dec_nr_pmds(mm);
 	return 1;
@@ -7885,9 +7906,16 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
 	spin_unlock_irq(&hugetlb_lock);
 }
 
+/*
+ * If @take_locks is false, the caller must ensure that no concurrent page table
+ * access can happen (except for gup_fast() and hardware page walks).
+ * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like
+ * concurrent page fault handling) and the file rmap lock.
+ */
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 				   unsigned long start,
-				   unsigned long end)
+				   unsigned long end,
+				   bool take_locks)
 {
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
@@ -7911,8 +7939,12 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
 				start, end);
 	mmu_notifier_invalidate_range_start(&range);
-	hugetlb_vma_lock_write(vma);
+	if (take_locks) {
-	i_mmap_lock_write(vma->vm_file->f_mapping);
+		hugetlb_vma_lock_write(vma);
+		i_mmap_lock_write(vma->vm_file->f_mapping);
+	} else {
+		i_mmap_assert_write_locked(vma->vm_file->f_mapping);
+	}
 	for (address = start; address < end; address += PUD_SIZE) {
 		ptep = hugetlb_walk(vma, address, sz);
 		if (!ptep)
@@ -7922,8 +7954,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 	}
 	flush_hugetlb_tlb_range(vma, start, end);
-	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	if (take_locks) {
-	hugetlb_vma_unlock_write(vma);
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+		hugetlb_vma_unlock_write(vma);
+	}
 	/*
 	 * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see
 	 * Documentation/mm/mmu_notifier.rst.
@@ -7938,7 +7972,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 {
 	hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
-			ALIGN_DOWN(vma->vm_end, PUD_SIZE));
+			ALIGN_DOWN(vma->vm_end, PUD_SIZE),
+			/* take_locks = */ true);
 }
 
 /*

mm/kmsan/kmsan_test.c

@@ -732,3 +732,4 @@ kunit_test_suites(&kmsan_test_suite);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alexander Potapenko <glider@google.com>");
+MODULE_DESCRIPTION("Test cases for KMSAN");

mm/madvise.c

@@ -1881,7 +1881,9 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
 			/* Drop and reacquire lock to unwind race. */
 			madvise_finish_tlb(&madv_behavior);
 			madvise_unlock(mm, behavior);
-			madvise_lock(mm, behavior);
+			ret = madvise_lock(mm, behavior);
+			if (ret)
+				goto out;
 			madvise_init_tlb(&madv_behavior, mm);
 			continue;
 		}
@@ -1892,6 +1894,7 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
 	madvise_finish_tlb(&madv_behavior);
 	madvise_unlock(mm, behavior);
 
+out:
 	ret = (total_len - iov_iter_count(iter)) ? : ret;
 
 	return ret;

mm/mempolicy.c

@@ -3708,15 +3708,13 @@ static void wi_state_free(void)
 			lockdep_is_held(&wi_state_lock));
 	if (!old_wi_state) {
 		mutex_unlock(&wi_state_lock);
-		goto out;
+		return;
 	}
 
 	rcu_assign_pointer(wi_state, NULL);
 	mutex_unlock(&wi_state_lock);
 	synchronize_rcu();
 	kfree(old_wi_state);
-out:
-	kfree(&wi_group->wi_kobj);
 }
 
 static struct kobj_attribute wi_auto_attr =

mm/vma.c

@@ -539,7 +539,14 @@ __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	init_vma_prep(&vp, vma);
 	vp.insert = new;
 	vma_prepare(&vp);
+
+	/*
+	 * Get rid of huge pages and shared page tables straddling the split
+	 * boundary.
+	 */
 	vma_adjust_trans_huge(vma, vma->vm_start, addr, NULL);
+	if (is_vm_hugetlb_page(vma))
+		hugetlb_split(vma, addr);
 
 	if (new_below) {
 		vma->vm_start = addr;

mm/vmstat.c

@@ -1201,7 +1201,6 @@ const char * const vmstat_text[] = {
 	"nr_zone_unevictable",
 	"nr_zone_write_pending",
 	"nr_mlock",
-	"nr_bounce",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",
 #endif

tools/testing/vma/vma_internal.h

@@ -932,6 +932,8 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	(void)next;
 }
 
+static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {}
+
 static inline void vma_iter_free(struct vma_iterator *vmi)
 {
 	mas_destroy(&vmi->mas);