Merge branch 'akpm' (patches from Andrew)

Merge more fixes from Andrew Morton:
 "The usual shower of hotfixes and some followups to the recently merged
  page_owner enhancements"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/memory-failure: poison read receives SIGKILL instead of SIGBUS if mmaped more than once
  mm/slab.c: fix kernel-doc warning for __ksize()
  xarray.h: fix kernel-doc warning
  bitmap.h: fix kernel-doc warning and typo
  fs/fs-writeback.c: fix kernel-doc warning
  fs/libfs.c: fix kernel-doc warning
  fs/direct-io.c: fix kernel-doc warning
  mm, compaction: fix wrong pfn handling in __reset_isolation_pfn()
  mm, hugetlb: allow hugepage allocations to reclaim as needed
  lib/test_meminit: add a kmem_cache_alloc_bulk() test
  mm/slub.c: init_on_free=1 should wipe freelist ptr for bulk allocations
  lib/generic-radix-tree.c: add kmemleak annotations
  mm/slub: fix a deadlock in show_slab_objects()
  mm, page_owner: rename flag indicating that page is allocated
  mm, page_owner: decouple freeing stack trace from debug_pagealloc
  mm, page_owner: fix off-by-one error in __set_page_owner_handle()

16 files changed, 152 insertions, 86 deletions

diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index b72d07d70239..525296121d89 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -41,6 +41,9 @@ smaller binary while the latter is 1.1 - 2 times faster.
 Both KASAN modes work with both SLUB and SLAB memory allocators.
 For better bug detection and nicer reporting, enable CONFIG_STACKTRACE.
 
+To augment reports with last allocation and freeing stack of the physical page,
+it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on.
+
 To disable instrumentation for specific files or directories, add a line
 similar to the following to the respective kernel Makefile:
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ae196784f487..9329ced91f1d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp)
 	}
 }
 
-/**
+/*
  * dio_complete() - called when all DIO BIO I/O has been completed
- * @offset: the byte offset in the file of the completed operation
  *
  * This drops i_dio_count, lets interested parties know that a DIO operation
  * has completed, and calculates the resulting return code for the operation.
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e88421d9a48d..8461a6322039 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -905,7 +905,7 @@ restart:
  * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
  * @bdi_id: target bdi id
  * @memcg_id: target memcg css id
- * @nr_pages: number of pages to write, 0 for best-effort dirty flushing
+ * @nr: number of pages to write, 0 for best-effort dirty flushing
  * @reason: reason why some writeback work initiated
  * @done: target wb_completion
  *
diff --git a/fs/libfs.c b/fs/libfs.c
index 540611b99b9a..1463b038ffc4 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
- * @available: See .write_end of address_space_operations
- * @file: 		"
+ * @file: See .write_end of address_space_operations
  * @mapping: 		"
  * @pos: 		"
  * @len: 		"
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 90528f12bdfa..29fc933df3bf 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1,
 }
 
 /**
- * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third
+ * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third
  * @src1:	Pointer to bitmap 1
  * @src2:	Pointer to bitmap 2 will be or'ed with bitmap 1
  * @src3:	Pointer to bitmap 3. Compare to the result of *@src1 | *@src2
+ * @nbits:	number of bits in each of these bitmaps
  *
  * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
  */
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 682fd465df06..cfce186f0c4e 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -18,7 +18,7 @@ struct page_ext_operations {
 
 enum page_ext_flags {
 	PAGE_EXT_OWNER,
-	PAGE_EXT_OWNER_ACTIVE,
+	PAGE_EXT_OWNER_ALLOCATED,
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
 	PAGE_EXT_IDLE,
@@ -36,6 +36,7 @@ struct page_ext {
 	unsigned long flags;
 };
 
+extern unsigned long page_ext_size;
 extern void pgdat_page_ext_init(struct pglist_data *pgdat);
 
 #ifdef CONFIG_SPARSEMEM
@@ -52,6 +53,13 @@ static inline void page_ext_init(void)
 
 struct page_ext *lookup_page_ext(const struct page *page);
 
+static inline struct page_ext *page_ext_next(struct page_ext *curr)
+{
+	void *next = curr;
+	next += page_ext_size;
+	return next;
+}
+
 #else /* !CONFIG_PAGE_EXTENSION */
 struct page_ext;
 
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5921599b6dc4..86eecbd98e84 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -230,8 +230,8 @@ static inline int xa_err(void *entry)
  * This structure is used either directly or via the XA_LIMIT() macro
  * to communicate the range of IDs that are valid for allocation.
  * Two common ranges are predefined for you:
- *  * xa_limit_32b	- [0 - UINT_MAX]
- *  * xa_limit_31b	- [0 - INT_MAX]
+ * * xa_limit_32b	- [0 - UINT_MAX]
+ * * xa_limit_31b	- [0 - INT_MAX]
  */
 struct xa_limit {
 	u32 max;
diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c
index ae25e2fa2187..f25eb111c051 100644
--- a/lib/generic-radix-tree.c
+++ b/lib/generic-radix-tree.c
@@ -2,6 +2,7 @@
 #include <linux/export.h>
 #include <linux/generic-radix-tree.h>
 #include <linux/gfp.h>
+#include <linux/kmemleak.h>
 
 #define GENRADIX_ARY		(PAGE_SIZE / sizeof(struct genradix_node *))
 #define GENRADIX_ARY_SHIFT	ilog2(GENRADIX_ARY)
@@ -75,6 +76,27 @@ void *__genradix_ptr(struct __genradix *radix, size_t offset)
 }
 EXPORT_SYMBOL(__genradix_ptr);
 
+static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask)
+{
+	struct genradix_node *node;
+
+	node = (struct genradix_node *)__get_free_page(gfp_mask|__GFP_ZERO);
+
+	/*
+	 * We're using pages (not slab allocations) directly for kernel data
+	 * structures, so we need to explicitly inform kmemleak of them in order
+	 * to avoid false positive memory leak reports.
+	 */
+	kmemleak_alloc(node, PAGE_SIZE, 1, gfp_mask);
+	return node;
+}
+
+static inline void genradix_free_node(struct genradix_node *node)
+{
+	kmemleak_free(node);
+	free_page((unsigned long)node);
+}
+
 /*
  * Returns pointer to the specified byte @offset within @radix, allocating it if
  * necessary - newly allocated slots are always zeroed out:
@@ -97,8 +119,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 			break;
 
 		if (!new_node) {
-			new_node = (void *)
-				__get_free_page(gfp_mask|__GFP_ZERO);
+			new_node = genradix_alloc_node(gfp_mask);
 			if (!new_node)
 				return NULL;
 		}
@@ -121,8 +142,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 		n = READ_ONCE(*p);
 		if (!n) {
 			if (!new_node) {
-				new_node = (void *)
-					__get_free_page(gfp_mask|__GFP_ZERO);
+				new_node = genradix_alloc_node(gfp_mask);
 				if (!new_node)
 					return NULL;
 			}
@@ -133,7 +153,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 	}
 
 	if (new_node)
-		free_page((unsigned long) new_node);
+		genradix_free_node(new_node);
 
 	return &n->data[offset];
 }
@@ -191,7 +211,7 @@ static void genradix_free_recurse(struct genradix_node *n, unsigned level)
 				genradix_free_recurse(n->children[i], level - 1);
 	}
 
-	free_page((unsigned long) n);
+	genradix_free_node(n);
 }
 
 int __genradix_prealloc(struct __genradix *radix, size_t size,
diff --git a/lib/test_meminit.c b/lib/test_meminit.c
index 9729f271d150..9742e5cb853a 100644
--- a/lib/test_meminit.c
+++ b/lib/test_meminit.c
@@ -297,6 +297,32 @@ out:
 	return 1;
 }
 
+static int __init do_kmem_cache_size_bulk(int size, int *total_failures)
+{
+	struct kmem_cache *c;
+	int i, iter, maxiter = 1024;
+	int num, bytes;
+	bool fail = false;
+	void *objects[10];
+
+	c = kmem_cache_create("test_cache", size, size, 0, NULL);
+	for (iter = 0; (iter < maxiter) && !fail; iter++) {
+		num = kmem_cache_alloc_bulk(c, GFP_KERNEL, ARRAY_SIZE(objects),
+					    objects);
+		for (i = 0; i < num; i++) {
+			bytes = count_nonzero_bytes(objects[i], size);
+			if (bytes)
+				fail = true;
+			fill_with_garbage(objects[i], size);
+		}
+
+		if (num)
+			kmem_cache_free_bulk(c, num, objects);
+	}
+	*total_failures += fail;
+	return 1;
+}
+
 /*
  * Test kmem_cache allocation by creating caches of different sizes, with and
  * without constructors, with and without SLAB_TYPESAFE_BY_RCU.
@@ -318,6 +344,7 @@ static int __init test_kmemcache(int *total_failures)
 			num_tests += do_kmem_cache_size(size, ctor, rcu, zero,
 							&failures);
 		}
+		num_tests += do_kmem_cache_size_bulk(size, &failures);
 	}
 	REPORT_FAILURES_IN_FN();
 	*total_failures += failures;
diff --git a/mm/compaction.c b/mm/compaction.c
index ce08b39d85d4..672d3c78c6ab 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 
 	/* Ensure the start of the pageblock or zone is online and valid */
 	block_pfn = pageblock_start_pfn(pfn);
-	block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+	block_pfn = max(block_pfn, zone->zone_start_pfn);
+	block_page = pfn_to_online_page(block_pfn);
 	if (block_page) {
 		page = block_page;
 		pfn = block_pfn;
 	}
 
 	/* Ensure the end of the pageblock or zone is online and valid */
-	block_pfn += pageblock_nr_pages;
+	block_pfn = pageblock_end_pfn(pfn) - 1;
 	block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
 	end_page = pfn_to_online_page(block_pfn);
 	if (!end_page)
@@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 
 		page += (1 << PAGE_ALLOC_COSTLY_ORDER);
 		pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
-	} while (page < end_page);
+	} while (page <= end_page);
 
 	return false;
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7ef849da8278..0ae72b6acee7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -199,7 +199,6 @@ struct to_kill {
 	struct task_struct *tsk;
 	unsigned long addr;
 	short size_shift;
-	char addr_valid;
 };
 
 /*
@@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 		}
 	}
 	tk->addr = page_address_in_vma(p, vma);
-	tk->addr_valid = 1;
 	if (is_zone_device_page(p))
 		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
 	else
 		tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
 
 	/*
-	 * In theory we don't have to kill when the page was
-	 * munmaped. But it could be also a mremap. Since that's
-	 * likely very rare kill anyways just out of paranoia, but use
-	 * a SIGKILL because the error is not contained anymore.
+	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
+	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
+	 * so "tk->size_shift == 0" effectively checks no mapping on
+	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
+	 * to a process' address space, it's possible not all N VMAs
+	 * contain mappings for the page, but at least one VMA does.
+	 * Only deliver SIGBUS with payload derived from the VMA that
+	 * has a mapping for the page.
 	 */
-	if (tk->addr == -EFAULT || tk->size_shift == 0) {
+	if (tk->addr == -EFAULT) {
 		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
 			page_to_pfn(p), tsk->comm);
-		tk->addr_valid = 0;
+	} else if (tk->size_shift == 0) {
+		kfree(tk);
+		return;
 	}
 	get_task_struct(tsk);
 	tk->tsk = tsk;
@@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
 			 * make sure the process doesn't catch the
 			 * signal and then access the memory. Just kill it.
 			 */
-			if (fail || tk->addr_valid == 0) {
+			if (fail || tk->addr == -EFAULT) {
 				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
 				       pfn, tk->tsk->comm, tk->tsk->pid);
 				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c0b2e0306720..ecc3dbad606b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4473,12 +4473,14 @@ retry_cpuset:
 		if (page)
 			goto got_pg;
 
-		 if (order >= pageblock_order && (gfp_mask & __GFP_IO)) {
+		 if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
+		     !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
 			/*
 			 * If allocating entire pageblock(s) and compaction
 			 * failed because all zones are below low watermarks
 			 * or is prohibited because it recently failed at this
-			 * order, fail immediately.
+			 * order, fail immediately unless the allocator has
+			 * requested compaction and reclaim retry.
 			 *
 			 * Reclaim is
 			 *  - potentially very expensive because zones are far
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 5f5769c7db3b..4ade843ff588 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = {
 #endif
 };
 
+unsigned long page_ext_size = sizeof(struct page_ext);
+
 static unsigned long total_usage;
-static unsigned long extra_mem;
 
 static bool __init invoke_need_callbacks(void)
 {
@@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void)
 
 	for (i = 0; i < entries; i++) {
 		if (page_ext_ops[i]->need && page_ext_ops[i]->need()) {
-			page_ext_ops[i]->offset = sizeof(struct page_ext) +
-						extra_mem;
-			extra_mem += page_ext_ops[i]->size;
+			page_ext_ops[i]->offset = page_ext_size;
+			page_ext_size += page_ext_ops[i]->size;
 			need = true;
 		}
 	}
@@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void)
 	}
 }
 
-static unsigned long get_entry_size(void)
-{
-	return sizeof(struct page_ext) + extra_mem;
-}
-
 static inline struct page_ext *get_entry(void *base, unsigned long index)
 {
-	return base + get_entry_size() * index;
+	return base + page_ext_size * index;
 }
 
 #if !defined(CONFIG_SPARSEMEM)
@@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid)
 		!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
 		nr_pages += MAX_ORDER_NR_PAGES;
 
-	table_size = get_entry_size() * nr_pages;
+	table_size = page_ext_size * nr_pages;
 
 	base = memblock_alloc_try_nid(
 			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
@@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	if (section->page_ext)
 		return 0;
 
-	table_size = get_entry_size() * PAGES_PER_SECTION;
+	table_size = page_ext_size * PAGES_PER_SECTION;
 	base = alloc_page_ext(table_size, nid);
 
 	/*
@@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	 * we need to apply a mask.
 	 */
 	pfn &= PAGE_SECTION_MASK;
-	section->page_ext = (void *)base - get_entry_size() * pfn;
+	section->page_ext = (void *)base - page_ext_size * pfn;
 	total_usage += table_size;
 	return 0;
 }
@@ -267,7 +262,7 @@ static void free_page_ext(void *addr)
 		struct page *page = virt_to_page(addr);
 		size_t table_size;
 
-		table_size = get_entry_size() * PAGES_PER_SECTION;
+		table_size = page_ext_size * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
 		kmemleak_free(addr);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index dee931184788..e327bcd0380e 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -24,12 +24,10 @@ struct page_owner {
 	short last_migrate_reason;
 	gfp_t gfp_mask;
 	depot_stack_handle_t handle;
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	depot_stack_handle_t free_handle;
-#endif
 };
 
-static bool page_owner_disabled = true;
+static bool page_owner_enabled = false;
 DEFINE_STATIC_KEY_FALSE(page_owner_inited);
 
 static depot_stack_handle_t dummy_handle;
@@ -44,7 +42,7 @@ static int __init early_page_owner_param(char *buf)
 		return -EINVAL;
 
 	if (strcmp(buf, "on") == 0)
-		page_owner_disabled = false;
+		page_owner_enabled = true;
 
 	return 0;
 }
@@ -52,10 +50,7 @@ early_param("page_owner", early_page_owner_param);
 
 static bool need_page_owner(void)
 {
-	if (page_owner_disabled)
-		return false;
-
-	return true;
+	return page_owner_enabled;
 }
 
 static __always_inline depot_stack_handle_t create_dummy_stack(void)
@@ -84,7 +79,7 @@ static noinline void register_early_stack(void)
 
 static void init_page_owner(void)
 {
-	if (page_owner_disabled)
+	if (!page_owner_enabled)
 		return;
 
 	register_dummy_stack();
@@ -148,25 +143,19 @@ void __reset_page_owner(struct page *page, unsigned int order)
 {
 	int i;
 	struct page_ext *page_ext;
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	depot_stack_handle_t handle = 0;
 	struct page_owner *page_owner;
 
-	if (debug_pagealloc_enabled())
-		handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
-#endif
+	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
 
+	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
 	for (i = 0; i < (1 << order); i++) {
-		page_ext = lookup_page_ext(page + i);
-		if (unlikely(!page_ext))
-			continue;
-		__clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		if (debug_pagealloc_enabled()) {
-			page_owner = get_page_owner(page_ext);
-			page_owner->free_handle = handle;
-		}
-#endif
+		__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+		page_owner = get_page_owner(page_ext);
+		page_owner->free_handle = handle;
+		page_ext = page_ext_next(page_ext);
 	}
 }
 
@@ -184,9 +173,9 @@ static inline void __set_page_owner_handle(struct page *page,
 		page_owner->gfp_mask = gfp_mask;
 		page_owner->last_migrate_reason = -1;
 		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
-		__set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
+		__set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
 
-		page_ext = lookup_page_ext(page + i);
+		page_ext = page_ext_next(page_ext);
 	}
 }
 
@@ -224,12 +213,10 @@ void __split_page_owner(struct page *page, unsigned int order)
 	if (unlikely(!page_ext))
 		return;
 
-	page_owner = get_page_owner(page_ext);
-	page_owner->order = 0;
-	for (i = 1; i < (1 << order); i++) {
-		page_ext = lookup_page_ext(page + i);
+	for (i = 0; i < (1 << order); i++) {
 		page_owner = get_page_owner(page_ext);
 		page_owner->order = 0;
+		page_ext = page_ext_next(page_ext);
 	}
 }
 
@@ -260,7 +247,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 	 * the new page, which will be freed.
 	 */
 	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
-	__set_bit(PAGE_EXT_OWNER_ACTIVE, &new_ext->flags);
+	__set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
 }
 
 void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -320,7 +307,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 			if (unlikely(!page_ext))
 				continue;
 
-			if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+			if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
 				continue;
 
 			page_owner = get_page_owner(page_ext);
@@ -435,7 +422,7 @@ void __dump_page_owner(struct page *page)
 		return;
 	}
 
-	if (test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+	if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
 		pr_alert("page_owner tracks the page as allocated\n");
 	else
 		pr_alert("page_owner tracks the page as freed\n");
@@ -451,7 +438,6 @@ void __dump_page_owner(struct page *page)
 		stack_trace_print(entries, nr_entries, 0);
 	}
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	handle = READ_ONCE(page_owner->free_handle);
 	if (!handle) {
 		pr_alert("page_owner free stack trace missing\n");
@@ -460,7 +446,6 @@ void __dump_page_owner(struct page *page)
 		pr_alert("page last free stack trace:\n");
 		stack_trace_print(entries, nr_entries, 0);
 	}
-#endif
 
 	if (page_owner->last_migrate_reason != -1)
 		pr_alert("page has been migrated, last migrate reason: %s\n",
@@ -527,7 +512,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		 * Although we do have the info about past allocation of free
 		 * pages, it's not relevant for current memory usage.
 		 */
-		if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+		if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
 			continue;
 
 		page_owner = get_page_owner(page_ext);
diff --git a/mm/slab.c b/mm/slab.c
index 9df370558e5d..66e5d8032bae 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4206,9 +4206,12 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 
 /**
  * __ksize -- Uninstrumented ksize.
+ * @objp: pointer to the object
  *
  * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same
  * safety checks as ksize() with KASAN instrumentation enabled.
+ *
+ * Return: size of the actual memory used by @objp in bytes
  */
 size_t __ksize(const void *objp)
 {
diff --git a/mm/slub.c b/mm/slub.c
index 3d63ae320d31..b25c807a111f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2672,6 +2672,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 }
 
 /*
+ * If the object has been wiped upon free, make sure it's fully initialized by
+ * zeroing out freelist pointer.
+ */
+static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
+						   void *obj)
+{
+	if (unlikely(slab_want_init_on_free(s)) && obj)
+		memset((void *)((char *)obj + s->offset), 0, sizeof(void *));
+}
+
+/*
  * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
  * have the fastpath folded into their functions. So no function call
  * overhead for requests that can be satisfied on the fastpath.
@@ -2759,12 +2770,8 @@ redo:
 		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
-	/*
-	 * If the object has been wiped upon free, make sure it's fully
-	 * initialized by zeroing out freelist pointer.
-	 */
-	if (unlikely(slab_want_init_on_free(s)) && object)
-		memset(object + s->offset, 0, sizeof(void *));
+
+	maybe_wipe_obj_freeptr(s, object);
 
 	if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
 		memset(object, 0, s->object_size);
@@ -3178,10 +3185,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 				goto error;
 
 			c = this_cpu_ptr(s->cpu_slab);
+			maybe_wipe_obj_freeptr(s, p[i]);
+
 			continue; /* goto for-loop */
 		}
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
+		maybe_wipe_obj_freeptr(s, p[i]);
 	}
 	c->tid = next_tid(c->tid);
 	local_irq_enable();
@@ -4846,7 +4856,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 		}
 	}
 
-	get_online_mems();
+	/*
+	 * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex"
+	 * already held which will conflict with an existing lock order:
+	 *
+	 * mem_hotplug_lock->slab_mutex->kernfs_mutex
+	 *
+	 * We don't really need mem_hotplug_lock (to hold off
+	 * slab_mem_going_offline_callback) here because slab's memory hot
+	 * unplug code doesn't destroy the kmem_cache->node[] data.
+	 */
+
 #ifdef CONFIG_SLUB_DEBUG
 	if (flags & SO_ALL) {
 		struct kmem_cache_node *n;
@@ -4887,7 +4907,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 			x += sprintf(buf + x, " N%d=%lu",
 					node, nodes[node]);
 #endif
-	put_online_mems();
 	kfree(nodes);
 	return x + sprintf(buf + x, "\n");
 }