Merge remote-tracking branch 'torvalds/master' into perf-tools-next

To pick up changes for other tools/ libraries used by perf and for
header synchronization with the kernel sources originals.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

12 files changed, 177 insertions, 121 deletions

diff --git a/mm/execmem.c b/mm/execmem.c
index e6c4f5076ca8..6f7a2653b280 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -254,6 +254,34 @@ out_unlock:
 	return ptr;
 }
 
+static bool execmem_cache_rox = false;
+
+void execmem_cache_make_ro(void)
+{
+	struct maple_tree *free_areas = &execmem_cache.free_areas;
+	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
+	MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
+	MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
+	struct mutex *mutex = &execmem_cache.mutex;
+	void *area;
+
+	execmem_cache_rox = true;
+
+	mutex_lock(mutex);
+
+	mas_for_each(&mas_free, area, ULONG_MAX) {
+		unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
+		set_memory_ro(mas_free.index, pages);
+	}
+
+	mas_for_each(&mas_busy, area, ULONG_MAX) {
+		unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
+		set_memory_ro(mas_busy.index, pages);
+	}
+
+	mutex_unlock(mutex);
+}
+
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
@@ -274,9 +302,15 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	err = set_memory_rox((unsigned long)p, vm->nr_pages);
-	if (err)
-		goto err_free_mem;
+	if (execmem_cache_rox) {
+		err = set_memory_rox((unsigned long)p, vm->nr_pages);
+		if (err)
+			goto err_free_mem;
+	} else {
+		err = set_memory_x((unsigned long)p, vm->nr_pages);
+		if (err)
+			goto err_free_mem;
+	}
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a47682d1ab7..47d76d03ce30 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmd, bool freeze, struct folio *folio)
 {
+	bool pmd_migration = is_pmd_migration_entry(*pmd);
+
 	VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
 	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
 	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
@@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 	 * require a folio to check the PMD against. Otherwise, there
 	 * is a risk of replacing the wrong folio.
 	 */
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd)) {
-		if (folio && folio != pmd_folio(*pmd))
+	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+		/*
+		 * Do not apply pmd_folio() to a migration entry; and folio lock
+		 * guarantees that it must be of the wrong folio anyway.
+		 */
+		if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
 			return;
 		__split_huge_pmd_locked(vma, pmd, address, freeze);
 	}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e3e6ac991b9c..7ae38bfb9096 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct folio *folio;
-	long retval, gbl_chg;
+	long retval, gbl_chg, gbl_reserve;
 	map_chg_state map_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
@@ -3163,8 +3163,16 @@ out_uncharge_cgroup_reservation:
 		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
 						    h_cg);
 out_subpool_put:
-	if (map_chg)
-		hugepage_subpool_put_pages(spool, 1);
+	/*
+	 * put page to subpool iff the quota of subpool's rsv_hpages is used
+	 * during hugepage_subpool_get_pages.
+	 */
+	if (map_chg && !gbl_chg) {
+		gbl_reserve = hugepage_subpool_put_pages(spool, 1);
+		hugetlb_acct_memory(h, -gbl_reserve);
+	}
+
+
 out_end_reservation:
 	if (map_chg != MAP_CHG_ENFORCED)
 		vma_end_reservation(h, vma, addr);
@@ -4034,10 +4042,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
 
 	list_for_each_entry_safe(folio, next, src_list, lru) {
 		int i;
+		bool cma;
 
 		if (folio_test_hugetlb_vmemmap_optimized(folio))
 			continue;
 
+		cma = folio_test_hugetlb_cma(folio);
+
 		list_del(&folio->lru);
 
 		split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
@@ -4053,6 +4064,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
 
 			new_folio->mapping = NULL;
 			init_new_hugetlb_folio(dst, new_folio);
+			/* Copy the CMA flag so that it is freed correctly */
+			if (cma)
+				folio_set_hugetlb_cma(new_folio);
 			list_add(&new_folio->lru, &dst_list);
 		}
 	}
@@ -7233,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 					struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
 {
-	long chg = -1, add = -1;
+	long chg = -1, add = -1, spool_resv, gbl_resv;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
@@ -7368,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode,
 	return true;
 
 out_put_pages:
-	/* put back original number of pages, chg */
-	(void)hugepage_subpool_put_pages(spool, chg);
+	spool_resv = chg - gbl_reserve;
+	if (spool_resv) {
+		/* put sub pool's reservation back, chg - gbl_reserve */
+		gbl_resv = hugepage_subpool_put_pages(spool, spool_resv);
+		/*
+		 * subpool's reserved pages can not be put back due to race,
+		 * return to hstate.
+		 */
+		hugetlb_acct_memory(h, -gbl_resv);
+	}
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
 					    chg * pages_per_huge_page(h), h_cg);
diff --git a/mm/internal.h b/mm/internal.h
index e9695baa5922..5c7a2b43ad76 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -248,11 +248,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
 		bool *any_writable, bool *any_young, bool *any_dirty)
 {
-	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
-	const pte_t *end_ptep = start_ptep + max_nr;
 	pte_t expected_pte, *ptep;
 	bool writable, young, dirty;
-	int nr;
+	int nr, cur_nr;
 
 	if (any_writable)
 		*any_writable = false;
@@ -265,11 +263,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 	VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
 	VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
 
+	/* Limit max_nr to the actual remaining PFNs in the folio we could batch. */
+	max_nr = min_t(unsigned long, max_nr,
+		       folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte));
+
 	nr = pte_batch_hint(start_ptep, pte);
 	expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
 	ptep = start_ptep + nr;
 
-	while (ptep < end_ptep) {
+	while (nr < max_nr) {
 		pte = ptep_get(ptep);
 		if (any_writable)
 			writable = !!pte_write(pte);
@@ -282,14 +284,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		if (!pte_same(pte, expected_pte))
 			break;
 
-		/*
-		 * Stop immediately once we reached the end of the folio. In
-		 * corner cases the next PFN might fall into a different
-		 * folio.
-		 */
-		if (pte_pfn(pte) >= folio_end_pfn)
-			break;
-
 		if (any_writable)
 			*any_writable |= writable;
 		if (any_young)
@@ -297,12 +291,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		if (any_dirty)
 			*any_dirty |= dirty;
 
-		nr = pte_batch_hint(ptep, pte);
-		expected_pte = pte_advance_pfn(expected_pte, nr);
-		ptep += nr;
+		cur_nr = pte_batch_hint(ptep, pte);
+		expected_pte = pte_advance_pfn(expected_pte, cur_nr);
+		ptep += cur_nr;
+		nr += cur_nr;
 	}
 
-	return min(ptep - start_ptep, max_nr);
+	return min(nr, max_nr);
 }
 
 /**
@@ -1595,7 +1590,6 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc);
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 void accept_page(struct page *page);
-void unaccepted_cleanup_work(struct work_struct *work);
 #else /* CONFIG_UNACCEPTED_MEMORY */
 static inline void accept_page(struct page *page)
 {
diff --git a/mm/memblock.c b/mm/memblock.c
index d3509414b8c3..0e9ebb8aa7fe 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -457,7 +457,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 				min(new_area_start, memblock.current_limit),
 				new_alloc_size, PAGE_SIZE);
 
-		new_array = addr ? __va(addr) : NULL;
+		if (addr) {
+			/* The memory may not have been accepted, yet. */
+			accept_memory(addr, new_alloc_size);
+
+			new_array = __va(addr);
+		} else {
+			new_array = NULL;
+		}
 	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
diff --git a/mm/memory.c b/mm/memory.c
index ba3ea0a82f7f..49199410805c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3751,7 +3751,7 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
 
 	/* Stabilize the mapcount vs. refcount and recheck. */
 	folio_lock_large_mapcount(folio);
-	VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+	VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio);
 
 	if (folio_test_large_maybe_mapped_shared(folio))
 		goto unlock;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 9659689b8ace..eedce9321e13 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1441,7 +1441,6 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	INIT_LIST_HEAD(&zone->unaccepted_pages);
-	INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work);
 #endif
 }
 
@@ -1786,7 +1785,7 @@ static bool arch_has_descending_max_zone_pfns(void)
 	return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
 }
 
-static void set_high_memory(void)
+static void __init set_high_memory(void)
 {
 	phys_addr_t highmem = memblock_end_of_DRAM();
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5669baf2a6fe..8258349e49ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -290,7 +290,8 @@ EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
 static bool page_contains_unaccepted(struct page *page, unsigned int order);
-static bool cond_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags);
 static bool __free_unaccepted(struct page *page);
 
 int page_group_by_mobility_disabled __read_mostly;
@@ -1151,14 +1152,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
 		__pgalloc_tag_sub(page, nr);
 }
 
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
+/* When tag is not NULL, assuming mem_alloc_profiling_enabled */
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
 {
-	struct alloc_tag *tag;
-
-	if (!mem_alloc_profiling_enabled())
-		return;
-
-	tag = __pgalloc_tag_get(page);
 	if (tag)
 		this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
 }
@@ -1168,7 +1164,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
 				   unsigned int nr) {}
 static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) {}
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
@@ -3616,7 +3612,7 @@ retry:
 			}
 		}
 
-		cond_accept_memory(zone, order);
+		cond_accept_memory(zone, order, alloc_flags);
 
 		/*
 		 * Detect whether the number of free pages is below high
@@ -3643,7 +3639,7 @@ check_alloc_wmark:
 				       gfp_mask)) {
 			int ret;
 
-			if (cond_accept_memory(zone, order))
+			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
 			/*
@@ -3696,7 +3692,7 @@ try_this_zone:
 
 			return page;
 		} else {
-			if (cond_accept_memory(zone, order))
+			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
 			/* Try again if zone has deferred pages */
@@ -4849,7 +4845,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 			goto failed;
 		}
 
-		cond_accept_memory(zone, 0);
+		cond_accept_memory(zone, 0, alloc_flags);
 retry_this_zone:
 		mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
 		if (zone_watermark_fast(zone, 0,  mark,
@@ -4858,7 +4854,7 @@ retry_this_zone:
 			break;
 		}
 
-		if (cond_accept_memory(zone, 0))
+		if (cond_accept_memory(zone, 0, alloc_flags))
 			goto retry_this_zone;
 
 		/* Try again if zone has deferred pages */
@@ -5065,11 +5061,13 @@ static void ___free_pages(struct page *page, unsigned int order,
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
+	/* get alloc tag in case the page is released by others */
+	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
 		__free_frozen_pages(page, order, fpi_flags);
 	else if (!head) {
-		pgalloc_tag_sub_pages(page, (1 << order) - 1);
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
 			__free_frozen_pages(page + (1 << order), order,
 					    fpi_flags);
@@ -7174,16 +7172,8 @@ bool has_managed_dma(void)
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 
-/* Counts number of zones with unaccepted pages. */
-static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
-
 static bool lazy_accept = true;
 
-void unaccepted_cleanup_work(struct work_struct *work)
-{
-	static_branch_dec(&zones_with_unaccepted_pages);
-}
-
 static int __init accept_memory_parse(char *p)
 {
 	if (!strcmp(p, "lazy")) {
@@ -7208,11 +7198,7 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
 static void __accept_page(struct zone *zone, unsigned long *flags,
 			  struct page *page)
 {
-	bool last;
-
 	list_del(&page->lru);
-	last = list_empty(&zone->unaccepted_pages);
-
 	account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
 	__ClearPageUnaccepted(page);
@@ -7221,28 +7207,6 @@ static void __accept_page(struct zone *zone, unsigned long *flags,
 	accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER);
 
 	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
-
-	if (last) {
-		/*
-		 * There are two corner cases:
-		 *
-		 * - If allocation occurs during the CPU bring up,
-		 *   static_branch_dec() cannot be used directly as
-		 *   it causes a deadlock on cpu_hotplug_lock.
-		 *
-		 *   Instead, use schedule_work() to prevent deadlock.
-		 *
-		 * - If allocation occurs before workqueues are initialized,
-		 *   static_branch_dec() should be called directly.
-		 *
-		 *   Workqueues are initialized before CPU bring up, so this
-		 *   will not conflict with the first scenario.
-		 */
-		if (system_wq)
-			schedule_work(&zone->unaccepted_cleanup);
-		else
-			unaccepted_cleanup_work(&zone->unaccepted_cleanup);
-	}
 }
 
 void accept_page(struct page *page)
@@ -7279,20 +7243,17 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	return true;
 }
 
-static inline bool has_unaccepted_memory(void)
-{
-	return static_branch_unlikely(&zones_with_unaccepted_pages);
-}
-
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags)
 {
 	long to_accept, wmark;
 	bool ret = false;
 
-	if (!has_unaccepted_memory())
+	if (list_empty(&zone->unaccepted_pages))
 		return false;
 
-	if (list_empty(&zone->unaccepted_pages))
+	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
+	if (alloc_flags & ALLOC_TRYLOCK)
 		return false;
 
 	wmark = promo_wmark_pages(zone);
@@ -7325,22 +7286,17 @@ static bool __free_unaccepted(struct page *page)
 {
 	struct zone *zone = page_zone(page);
 	unsigned long flags;
-	bool first = false;
 
 	if (!lazy_accept)
 		return false;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	first = list_empty(&zone->unaccepted_pages);
 	list_add_tail(&page->lru, &zone->unaccepted_pages);
 	account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
 	__SetPageUnaccepted(page);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
-	if (first)
-		static_branch_inc(&zones_with_unaccepted_pages);
-
 	return true;
 }
 
@@ -7351,7 +7307,8 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
 	return false;
 }
 
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags)
 {
 	return false;
 }
@@ -7422,11 +7379,6 @@ struct page *try_alloc_pages_noprof(int nid, unsigned int order)
 	if (!pcp_allowed_order(order))
 		return NULL;
 
-#ifdef CONFIG_UNACCEPTED_MEMORY
-	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
-	if (has_unaccepted_memory())
-		return NULL;
-#endif
 	/* Bailout, since _deferred_grow_zone() needs to take a lock */
 	if (deferred_pages_enabled())
 		return NULL;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2eff8b51a945..412ccd6543b3 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
 
-	/*
-	 * Should not even be attempting large allocations when huge
-	 * page swap is disabled. Warn and fail the allocation.
-	 */
-	if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
-		VM_WARN_ON_ONCE(1);
-		return -EINVAL;
+	if (order) {
+		/*
+		 * Reject large allocation when THP_SWAP is disabled,
+		 * the caller should split the folio and try again.
+		 */
+		if (!IS_ENABLED(CONFIG_THP_SWAP))
+			return -EAGAIN;
+
+		/*
+		 * Allocation size should never exceed cluster size
+		 * (HPAGE_PMD_SIZE).
+		 */
+		if (size > SWAPFILE_CLUSTER) {
+			VM_WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 	}
 
 	local_lock(&percpu_swap_cluster.lock);
@@ -3323,6 +3332,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 
 	/*
+	 * The swap subsystem needs a major overhaul to support this.
+	 * It doesn't work yet so just disable it for now.
+	 */
+	if (mapping_min_folio_order(mapping) > 0) {
+		error = -EINVAL;
+		goto bad_swap_unlock_inode;
+	}
+
+	/*
 	 * Read the swap header.
 	 */
 	if (!mapping->a_ops->read_folio) {
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 7d5d709cc838..e0db855c89b4 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_struct *mm,
 	src_folio->index = linear_page_index(dst_vma, dst_addr);
 
 	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
-	/* Follow mremap() behavior and treat the entry dirty after the move */
-	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+	/* Set soft dirty bit so userspace can notice the pte was moved */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
+#endif
+	if (pte_dirty(orig_src_pte))
+		orig_dst_pte = pte_mkdirty(orig_dst_pte);
+	orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma);
 
 	set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
 out:
@@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
+#endif
 	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
 	double_pt_unlock(dst_ptl, src_ptl);
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a787ec..2d7511654831 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm,
 {
 	vm->flags = flags;
 	vm->addr = (void *)va->va_start;
-	vm->size = va_size(va);
+	vm->size = vm->requested_size = va_size(va);
 	vm->caller = caller;
 	va->vm = vm;
 }
@@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size,
 
 	area->flags = flags;
 	area->caller = caller;
+	area->requested_size = requested_size;
 
 	va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
 	if (IS_ERR(va)) {
@@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof);
  */
 void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 {
+	struct vm_struct *vm = NULL;
+	size_t alloced_size = 0;
 	size_t old_size = 0;
 	void *n;
 
@@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 	}
 
 	if (p) {
-		struct vm_struct *vm;
-
 		vm = find_vm_area(p);
 		if (unlikely(!vm)) {
 			WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
 			return NULL;
 		}
 
-		old_size = get_vm_area_size(vm);
+		alloced_size = get_vm_area_size(vm);
+		old_size = vm->requested_size;
+		if (WARN(alloced_size < old_size,
+			 "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
+			return NULL;
 	}
 
 	/*
@@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 	 * would be a good heuristic for when to shrink the vm_area?
 	 */
 	if (size <= old_size) {
-		/* Zero out spare memory. */
-		if (want_init_on_alloc(flags))
+		/* Zero out "freed" memory. */
+		if (want_init_on_free())
 			memset((void *)p + size, 0, old_size - size);
+		vm->requested_size = size;
 		kasan_poison_vmalloc(p + size, old_size - size);
-		kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
 		return (void *)p;
 	}
 
+	/*
+	 * We already have the bytes available in the allocation; use them.
+	 */
+	if (size <= alloced_size) {
+		kasan_unpoison_vmalloc(p + old_size, size - old_size,
+				       KASAN_VMALLOC_PROT_NORMAL);
+		/* Zero out "alloced" memory. */
+		if (want_init_on_alloc(flags))
+			memset((void *)p + old_size, 0, size - old_size);
+		vm->requested_size = size;
+	}
+
 	/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
 	n = __vmalloc_noprof(size, flags);
 	if (!n)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 961b270f023c..d14a7e317ac8 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1243,19 +1243,19 @@ void zs_obj_write(struct zs_pool *pool, unsigned long handle,
 	class = zspage_class(pool, zspage);
 	off = offset_in_page(class->size * obj_idx);
 
-	if (off + class->size <= PAGE_SIZE) {
+	if (!ZsHugePage(zspage))
+		off += ZS_HANDLE_SIZE;
+
+	if (off + mem_len <= PAGE_SIZE) {
 		/* this object is contained entirely within a page */
 		void *dst = kmap_local_zpdesc(zpdesc);
 
-		if (!ZsHugePage(zspage))
-			off += ZS_HANDLE_SIZE;
 		memcpy(dst + off, handle_mem, mem_len);
 		kunmap_local(dst);
 	} else {
 		/* this object spans two pages */
 		size_t sizes[2];
 
-		off += ZS_HANDLE_SIZE;
 		sizes[0] = PAGE_SIZE - off;
 		sizes[1] = mem_len - sizes[0];