Merge tag 'mm-hotfixes-stable-2023-10-24-09-40' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "20 hotfixes. 12 are cc:stable and the remainder address post-6.5
  issues or aren't considered necessary for earlier kernel versions"

* tag 'mm-hotfixes-stable-2023-10-24-09-40' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  maple_tree: add GFP_KERNEL to allocations in mas_expected_entries()
  selftests/mm: include mman header to access MREMAP_DONTUNMAP identifier
  mailmap: correct email aliasing for Oleksij Rempel
  mailmap: map Bartosz's old address to the current one
  mm/damon/sysfs: check DAMOS regions update progress from before_terminate()
  MAINTAINERS: Ondrej has moved
  kasan: disable kasan_non_canonical_hook() for HW tags
  kasan: print the original fault addr when access invalid shadow
  hugetlbfs: close race between MADV_DONTNEED and page fault
  hugetlbfs: extend hugetlb_vma_lock to private VMAs
  hugetlbfs: clear resv_map pointer if mmap fails
  mm: zswap: fix pool refcount bug around shrink_worker()
  mm/migrate: fix do_pages_move for compat pointers
  riscv: fix set_huge_pte_at() for NAPOT mappings when a swap entry is set
  riscv: handle VM_FAULT_[HWPOISON|HWPOISON_LARGE] faults instead of panicking
  mmap: fix error paths with dup_anon_vma()
  mmap: fix vma_iterator in error path of vma_merge()
  mm: fix vm_brk_flags() to not bail out while holding lock
  mm/mempolicy: fix set_mempolicy_home_node() previous VMA pointer
  mm/page_alloc: correct start page when guard page debug is enabled

9 files changed, 128 insertions, 46 deletions

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index b86ba7b0a9214c..f60e56150feb69 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1208,6 +1208,8 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx,
 	return 0;
 }
 
+static bool damon_sysfs_schemes_regions_updating;
+
 static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
 {
 	struct damon_target *t, *next;
@@ -1219,8 +1221,10 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
 	cmd = damon_sysfs_cmd_request.cmd;
 	if (kdamond && ctx == kdamond->damon_ctx &&
 			(cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS ||
-			 cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES)) {
+			 cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES) &&
+			damon_sysfs_schemes_regions_updating) {
 		damon_sysfs_schemes_update_regions_stop(ctx);
+		damon_sysfs_schemes_regions_updating = false;
 		mutex_unlock(&damon_sysfs_lock);
 	}
 
@@ -1340,7 +1344,6 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond)
 static int damon_sysfs_cmd_request_callback(struct damon_ctx *c)
 {
 	struct damon_sysfs_kdamond *kdamond;
-	static bool damon_sysfs_schemes_regions_updating;
 	bool total_bytes_only = false;
 	int err = 0;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 52d26072dfda55..1301ba7b2c9a90 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ 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);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_read(&resv_map->rw_sema);
 	}
 }
 
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_read(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_read(&resv_map->rw_sema);
 	}
 }
 
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		down_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		down_write(&resv_map->rw_sema);
 	}
 }
 
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		up_write(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		up_write(&resv_map->rw_sema);
 	}
 }
 
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
 {
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	if (!__vma_shareable_lock(vma))
-		return 1;
+	if (__vma_shareable_lock(vma)) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
-	return down_write_trylock(&vma_lock->rw_sema);
+		return down_write_trylock(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		return down_write_trylock(&resv_map->rw_sema);
+	}
+
+	return 1;
 }
 
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		lockdep_assert_held(&vma_lock->rw_sema);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		lockdep_assert_held(&resv_map->rw_sema);
 	}
 }
 
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }
 
@@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void)
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
+	init_rwsem(&resv_map->rw_sema);
 
 	resv_map->adds_in_progress = 0;
 	/*
@@ -1138,8 +1171,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
 
-	set_vma_private_data(vma, (get_vma_private_data(vma) &
-				HPAGE_RESV_MASK) | (unsigned long)map);
+	set_vma_private_data(vma, (unsigned long)map);
 }
 
 static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
@@ -5274,9 +5306,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	return len + old_addr - old_end;
 }
 
-static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end,
-				   struct page *ref_page, zap_flags_t zap_flags)
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			    unsigned long start, unsigned long end,
+			    struct page *ref_page, zap_flags_t zap_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -5405,16 +5437,25 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		tlb_flush_mmu_tlbonly(tlb);
 }
 
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
-			  struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end, struct page *ref_page,
-			  zap_flags_t zap_flags)
+void __hugetlb_zap_begin(struct vm_area_struct *vma,
+			 unsigned long *start, unsigned long *end)
 {
+	if (!vma->vm_file)	/* hugetlbfs_file_mmap error */
+		return;
+
+	adjust_range_if_pmd_sharing_possible(vma, start, end);
 	hugetlb_vma_lock_write(vma);
-	i_mmap_lock_write(vma->vm_file->f_mapping);
+	if (vma->vm_file)
+		i_mmap_lock_write(vma->vm_file->f_mapping);
+}
 
-	/* mmu notification performed in caller */
-	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
+void __hugetlb_zap_end(struct vm_area_struct *vma,
+		       struct zap_details *details)
+{
+	zap_flags_t zap_flags = details ? details->zap_flags : 0;
+
+	if (!vma->vm_file)	/* hugetlbfs_file_mmap error */
+		return;
 
 	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
 		/*
@@ -5427,11 +5468,12 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 		 * someone else.
 		 */
 		__hugetlb_vma_unlock_write_free(vma);
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
 	} else {
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
 		hugetlb_vma_unlock_write(vma);
 	}
+
+	if (vma->vm_file)
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
@@ -6811,8 +6853,10 @@ out_err:
 		 */
 		if (chg >= 0 && add < 0)
 			region_abort(resv_map, from, to, regions_needed);
-	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
 		kref_put(&resv_map->refs, resv_map_release);
+		set_vma_resv_map(vma, NULL);
+	}
 	return false;
 }
 
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index ca4b6ff080a64c..6e3cb118d20ed5 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -621,7 +621,7 @@ void kasan_report_async(void)
 }
 #endif /* CONFIG_KASAN_HW_TAGS */
 
-#ifdef CONFIG_KASAN_INLINE
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 /*
  * With CONFIG_KASAN_INLINE, accesses to bogus pointers (outside the high
  * canonical half of the address space) cause out-of-bounds shadow memory reads
diff --git a/mm/memory.c b/mm/memory.c
index 6c264d2f969c02..517221f0130353 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1683,7 +1683,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			if (vma->vm_file) {
 				zap_flags_t zap_flags = details ?
 				    details->zap_flags : 0;
-				__unmap_hugepage_range_final(tlb, vma, start, end,
+				__unmap_hugepage_range(tlb, vma, start, end,
 							     NULL, zap_flags);
 			}
 		} else
@@ -1728,8 +1728,12 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	do {
-		unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+		unsigned long start = start_addr;
+		unsigned long end = end_addr;
+		hugetlb_zap_begin(vma, &start, &end);
+		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
+		hugetlb_zap_end(vma, &details);
 	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
 	mmu_notifier_invalidate_range_end(&range);
 }
@@ -1753,9 +1757,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, end);
-	if (is_vm_hugetlb_page(vma))
-		adjust_range_if_pmd_sharing_possible(vma, &range.start,
-						     &range.end);
+	hugetlb_zap_begin(vma, &range.start, &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
@@ -1766,6 +1768,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	unmap_single_vma(&tlb, vma, address, end, details, false);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
+	hugetlb_zap_end(vma, details);
 }
 
 /**
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f1b00d6ac7ee5c..29ebf1e7898cf0 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1543,8 +1543,10 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
 		 * the home node for vmas we already updated before.
 		 */
 		old = vma_policy(vma);
-		if (!old)
+		if (!old) {
+			prev = vma;
 			continue;
+		}
 		if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) {
 			err = -EOPNOTSUPP;
 			break;
diff --git a/mm/migrate.c b/mm/migrate.c
index 2053b54556ca5b..06086dc9da288f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2162,6 +2162,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			 const int __user *nodes,
 			 int __user *status, int flags)
 {
+	compat_uptr_t __user *compat_pages = (void __user *)pages;
 	int current_node = NUMA_NO_NODE;
 	LIST_HEAD(pagelist);
 	int start, i;
@@ -2174,8 +2175,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		int node;
 
 		err = -EFAULT;
-		if (get_user(p, pages + i))
-			goto out_flush;
+		if (in_compat_syscall()) {
+			compat_uptr_t cp;
+
+			if (get_user(cp, compat_pages + i))
+				goto out_flush;
+
+			p = compat_ptr(cp);
+		} else {
+			if (get_user(p, pages + i))
+				goto out_flush;
+		}
 		if (get_user(node, nodes + i))
 			goto out_flush;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index b56a7f0c9f8565..9e018d8dd7d693 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -583,11 +583,12 @@ again:
  * dup_anon_vma() - Helper function to duplicate anon_vma
  * @dst: The destination VMA
  * @src: The source VMA
+ * @dup: Pointer to the destination VMA when successful.
  *
  * Returns: 0 on success.
  */
 static inline int dup_anon_vma(struct vm_area_struct *dst,
-			       struct vm_area_struct *src)
+		struct vm_area_struct *src, struct vm_area_struct **dup)
 {
 	/*
 	 * Easily overlooked: when mprotect shifts the boundary, make sure the
@@ -595,9 +596,15 @@ static inline int dup_anon_vma(struct vm_area_struct *dst,
 	 * anon pages imported.
 	 */
 	if (src->anon_vma && !dst->anon_vma) {
+		int ret;
+
 		vma_assert_write_locked(dst);
 		dst->anon_vma = src->anon_vma;
-		return anon_vma_clone(dst, src);
+		ret = anon_vma_clone(dst, src);
+		if (ret)
+			return ret;
+
+		*dup = dst;
 	}
 
 	return 0;
@@ -624,6 +631,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	       unsigned long start, unsigned long end, pgoff_t pgoff,
 	       struct vm_area_struct *next)
 {
+	struct vm_area_struct *anon_dup = NULL;
 	bool remove_next = false;
 	struct vma_prepare vp;
 
@@ -633,7 +641,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 		remove_next = true;
 		vma_start_write(next);
-		ret = dup_anon_vma(vma, next);
+		ret = dup_anon_vma(vma, next, &anon_dup);
 		if (ret)
 			return ret;
 	}
@@ -661,6 +669,8 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	return 0;
 
 nomem:
+	if (anon_dup)
+		unlink_anon_vmas(anon_dup);
 	return -ENOMEM;
 }
 
@@ -860,6 +870,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 {
 	struct vm_area_struct *curr, *next, *res;
 	struct vm_area_struct *vma, *adjust, *remove, *remove2;
+	struct vm_area_struct *anon_dup = NULL;
 	struct vma_prepare vp;
 	pgoff_t vma_pgoff;
 	int err = 0;
@@ -927,18 +938,18 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 		vma_start_write(next);
 		remove = next;				/* case 1 */
 		vma_end = next->vm_end;
-		err = dup_anon_vma(prev, next);
+		err = dup_anon_vma(prev, next, &anon_dup);
 		if (curr) {				/* case 6 */
 			vma_start_write(curr);
 			remove = curr;
 			remove2 = next;
 			if (!next->anon_vma)
-				err = dup_anon_vma(prev, curr);
+				err = dup_anon_vma(prev, curr, &anon_dup);
 		}
 	} else if (merge_prev) {			/* case 2 */
 		if (curr) {
 			vma_start_write(curr);
-			err = dup_anon_vma(prev, curr);
+			err = dup_anon_vma(prev, curr, &anon_dup);
 			if (end == curr->vm_end) {	/* case 7 */
 				remove = curr;
 			} else {			/* case 5 */
@@ -954,7 +965,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 			vma_end = addr;
 			adjust = next;
 			adj_start = -(prev->vm_end - addr);
-			err = dup_anon_vma(next, prev);
+			err = dup_anon_vma(next, prev, &anon_dup);
 		} else {
 			/*
 			 * Note that cases 3 and 8 are the ONLY ones where prev
@@ -968,14 +979,14 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 				vma_pgoff = curr->vm_pgoff;
 				vma_start_write(curr);
 				remove = curr;
-				err = dup_anon_vma(next, curr);
+				err = dup_anon_vma(next, curr, &anon_dup);
 			}
 		}
 	}
 
 	/* Error in anon_vma clone. */
 	if (err)
-		return NULL;
+		goto anon_vma_fail;
 
 	if (vma_start < vma->vm_start || vma_end > vma->vm_end)
 		vma_expanded = true;
@@ -988,7 +999,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 	}
 
 	if (vma_iter_prealloc(vmi, vma))
-		return NULL;
+		goto prealloc_fail;
 
 	init_multi_vma_prep(&vp, vma, adjust, remove, remove2);
 	VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma &&
@@ -1016,6 +1027,15 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 	vma_complete(&vp, vmi, mm);
 	khugepaged_enter_vma(res, vm_flags);
 	return res;
+
+prealloc_fail:
+	if (anon_dup)
+		unlink_anon_vmas(anon_dup);
+
+anon_vma_fail:
+	vma_iter_set(vmi, addr);
+	vma_iter_load(vmi);
+	return NULL;
 }
 
 /*
@@ -3143,13 +3163,13 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 	if (!len)
 		return 0;
 
-	if (mmap_write_lock_killable(mm))
-		return -EINTR;
-
 	/* Until we need other flags, refuse anything except VM_EXEC. */
 	if ((flags & (~VM_EXEC)) != 0)
 		return -EINVAL;
 
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
 	ret = check_brk_limits(addr, len);
 	if (ret)
 		goto limits_failed;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 95546f3763021a..85741403948f55 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6475,6 +6475,7 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page,
 			next_page = page;
 			current_buddy = page + size;
 		}
+		page = next_page;
 
 		if (set_page_guard(zone, current_buddy, high, migratetype))
 			continue;
@@ -6482,7 +6483,6 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page,
 		if (current_buddy != target) {
 			add_to_free_list(current_buddy, zone, high, migratetype);
 			set_buddy_order(current_buddy, high);
-			page = next_page;
 		}
 	}
 }
diff --git a/mm/zswap.c b/mm/zswap.c
index 083c693602b820..37d2b1cb2ecb46 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1383,8 +1383,8 @@ reject:
 
 shrink:
 	pool = zswap_pool_last_get();
-	if (pool)
-		queue_work(shrink_wq, &pool->shrink_work);
+	if (pool && !queue_work(shrink_wq, &pool->shrink_work))
+		zswap_pool_put(pool);
 	goto reject;
 }