1 files changed, 612 insertions, 238 deletions

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 0fd9dcf2c5dc..a70245684206 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -1,14 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/debugfs.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/stacktrace.h>
 #include <linux/page_owner.h>
 #include <linux/jump_label.h>
 #include <linux/migrate.h>
 #include <linux/stackdepot.h>
 #include <linux/seq_file.h>
+#include <linux/memcontrol.h>
+#include <linux/sched/clock.h>
 
 #include "internal.h"
 
@@ -19,224 +22,404 @@
 #define PAGE_OWNER_STACK_DEPTH (16)
 
 struct page_owner {
-	unsigned int order;
+	unsigned short order;
+	short last_migrate_reason;
 	gfp_t gfp_mask;
-	int last_migrate_reason;
 	depot_stack_handle_t handle;
+	depot_stack_handle_t free_handle;
+	u64 ts_nsec;
+	u64 free_ts_nsec;
+	char comm[TASK_COMM_LEN];
+	pid_t pid;
+	pid_t tgid;
+	pid_t free_pid;
+	pid_t free_tgid;
 };
 
-static bool page_owner_disabled = true;
+struct stack {
+	struct stack_record *stack_record;
+	struct stack *next;
+};
+static struct stack dummy_stack;
+static struct stack failure_stack;
+static struct stack *stack_list;
+static DEFINE_SPINLOCK(stack_list_lock);
+
+#define STACK_PRINT_FLAG_STACK		0x1
+#define STACK_PRINT_FLAG_PAGES		0x2
+#define STACK_PRINT_FLAG_HANDLE		0x4
+
+struct stack_print_ctx {
+	struct stack *stack;
+	u8 flags;
+};
+
+static bool page_owner_enabled __initdata;
 DEFINE_STATIC_KEY_FALSE(page_owner_inited);
 
 static depot_stack_handle_t dummy_handle;
 static depot_stack_handle_t failure_handle;
+static depot_stack_handle_t early_handle;
 
 static void init_early_allocated_pages(void);
 
-static int early_page_owner_param(char *buf)
+static inline void set_current_in_page_owner(void)
 {
-	if (!buf)
-		return -EINVAL;
+	/*
+	 * Avoid recursion.
+	 *
+	 * We might need to allocate more memory from page_owner code, so make
+	 * sure to signal it in order to avoid recursion.
+	 */
+	current->in_page_owner = 1;
+}
 
-	if (strcmp(buf, "on") == 0)
-		page_owner_disabled = false;
+static inline void unset_current_in_page_owner(void)
+{
+	current->in_page_owner = 0;
+}
 
-	return 0;
+static int __init early_page_owner_param(char *buf)
+{
+	int ret = kstrtobool(buf, &page_owner_enabled);
+
+	if (page_owner_enabled)
+		stack_depot_request_early_init();
+
+	return ret;
 }
 early_param("page_owner", early_page_owner_param);
 
-static bool need_page_owner(void)
+static __init bool need_page_owner(void)
 {
-	if (page_owner_disabled)
-		return false;
-
-	return true;
+	return page_owner_enabled;
 }
 
-static noinline void register_dummy_stack(void)
+static __always_inline depot_stack_handle_t create_dummy_stack(void)
 {
 	unsigned long entries[4];
-	struct stack_trace dummy;
+	unsigned int nr_entries;
 
-	dummy.nr_entries = 0;
-	dummy.max_entries = ARRAY_SIZE(entries);
-	dummy.entries = &entries[0];
-	dummy.skip = 0;
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	return stack_depot_save(entries, nr_entries, GFP_KERNEL);
+}
 
-	save_stack_trace(&dummy);
-	dummy_handle = depot_save_stack(&dummy, GFP_KERNEL);
+static noinline void register_dummy_stack(void)
+{
+	dummy_handle = create_dummy_stack();
 }
 
 static noinline void register_failure_stack(void)
 {
-	unsigned long entries[4];
-	struct stack_trace failure;
-
-	failure.nr_entries = 0;
-	failure.max_entries = ARRAY_SIZE(entries);
-	failure.entries = &entries[0];
-	failure.skip = 0;
+	failure_handle = create_dummy_stack();
+}
 
-	save_stack_trace(&failure);
-	failure_handle = depot_save_stack(&failure, GFP_KERNEL);
+static noinline void register_early_stack(void)
+{
+	early_handle = create_dummy_stack();
 }
 
-static void init_page_owner(void)
+static __init void init_page_owner(void)
 {
-	if (page_owner_disabled)
+	if (!page_owner_enabled)
 		return;
 
 	register_dummy_stack();
 	register_failure_stack();
-	static_branch_enable(&page_owner_inited);
+	register_early_stack();
 	init_early_allocated_pages();
+	/* Initialize dummy and failure stacks and link them to stack_list */
+	dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle);
+	failure_stack.stack_record = __stack_depot_get_stack_record(failure_handle);
+	if (dummy_stack.stack_record)
+		refcount_set(&dummy_stack.stack_record->count, 1);
+	if (failure_stack.stack_record)
+		refcount_set(&failure_stack.stack_record->count, 1);
+	dummy_stack.next = &failure_stack;
+	stack_list = &dummy_stack;
+	static_branch_enable(&page_owner_inited);
 }
 
 struct page_ext_operations page_owner_ops = {
 	.size = sizeof(struct page_owner),
 	.need = need_page_owner,
 	.init = init_page_owner,
+	.need_shared_flags = true,
 };
 
 static inline struct page_owner *get_page_owner(struct page_ext *page_ext)
 {
-	return (void *)page_ext + page_owner_ops.offset;
+	return page_ext_data(page_ext, &page_owner_ops);
 }
 
-void __reset_page_owner(struct page *page, unsigned int order)
+static noinline depot_stack_handle_t save_stack(gfp_t flags)
 {
-	int i;
-	struct page_ext *page_ext;
+	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
+	depot_stack_handle_t handle;
+	unsigned int nr_entries;
 
-	for (i = 0; i < (1 << order); i++) {
-		page_ext = lookup_page_ext(page + i);
-		if (unlikely(!page_ext))
-			continue;
-		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
-	}
+	if (current->in_page_owner)
+		return dummy_handle;
+
+	set_current_in_page_owner();
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
+	handle = stack_depot_save(entries, nr_entries, flags);
+	if (!handle)
+		handle = failure_handle;
+	unset_current_in_page_owner();
+
+	return handle;
 }
 
-static inline bool check_recursive_alloc(struct stack_trace *trace,
-					unsigned long ip)
+static void add_stack_record_to_list(struct stack_record *stack_record,
+				     gfp_t gfp_mask)
 {
-	int i, count;
+	unsigned long flags;
+	struct stack *stack;
 
-	if (!trace->nr_entries)
-		return false;
+	if (!gfpflags_allow_spinning(gfp_mask))
+		return;
 
-	for (i = 0, count = 0; i < trace->nr_entries; i++) {
-		if (trace->entries[i] == ip && ++count == 2)
-			return true;
+	set_current_in_page_owner();
+	stack = kmalloc(sizeof(*stack), gfp_nested_mask(gfp_mask));
+	if (!stack) {
+		unset_current_in_page_owner();
+		return;
 	}
+	unset_current_in_page_owner();
 
-	return false;
+	stack->stack_record = stack_record;
+	stack->next = NULL;
+
+	spin_lock_irqsave(&stack_list_lock, flags);
+	stack->next = stack_list;
+	/*
+	 * This pairs with smp_load_acquire() from function
+	 * stack_start(). This guarantees that stack_start()
+	 * will see an updated stack_list before starting to
+	 * traverse the list.
+	 */
+	smp_store_release(&stack_list, stack);
+	spin_unlock_irqrestore(&stack_list_lock, flags);
 }
 
-static noinline depot_stack_handle_t save_stack(gfp_t flags)
+static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask,
+				   int nr_base_pages)
 {
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
-	depot_stack_handle_t handle;
+	struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
+	if (!stack_record)
+		return;
 
 	/*
-	 * We need to check recursion here because our request to stackdepot
-	 * could trigger memory allocation to save new entry. New memory
-	 * allocation would reach here and call depot_save_stack() again
-	 * if we don't catch it. There is still not enough memory in stackdepot
-	 * so it would try to allocate memory again and loop forever.
+	 * New stack_record's that do not use STACK_DEPOT_FLAG_GET start
+	 * with REFCOUNT_SATURATED to catch spurious increments of their
+	 * refcount.
+	 * Since we do not use STACK_DEPOT_FLAG_GET API, let us
+	 * set a refcount of 1 ourselves.
 	 */
-	if (check_recursive_alloc(&trace, _RET_IP_))
-		return dummy_handle;
+	if (refcount_read(&stack_record->count) == REFCOUNT_SATURATED) {
+		int old = REFCOUNT_SATURATED;
 
-	handle = depot_save_stack(&trace, flags);
-	if (!handle)
-		handle = failure_handle;
+		if (atomic_try_cmpxchg_relaxed(&stack_record->count.refs, &old, 1))
+			/* Add the new stack_record to our list */
+			add_stack_record_to_list(stack_record, gfp_mask);
+	}
+	refcount_add(nr_base_pages, &stack_record->count);
+}
 
-	return handle;
+static void dec_stack_record_count(depot_stack_handle_t handle,
+				   int nr_base_pages)
+{
+	struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
+
+	if (!stack_record)
+		return;
+
+	if (refcount_sub_and_test(nr_base_pages, &stack_record->count))
+		pr_warn("%s: refcount went to 0 for %u handle\n", __func__,
+			handle);
 }
 
-noinline void __set_page_owner(struct page *page, unsigned int order,
-					gfp_t gfp_mask)
+static inline void __update_page_owner_handle(struct page *page,
+					      depot_stack_handle_t handle,
+					      unsigned short order,
+					      gfp_t gfp_mask,
+					      short last_migrate_reason, u64 ts_nsec,
+					      pid_t pid, pid_t tgid, char *comm)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext_iter iter;
+	struct page_ext *page_ext;
 	struct page_owner *page_owner;
 
-	if (unlikely(!page_ext))
-		return;
+	rcu_read_lock();
+	for_each_page_ext(page, 1 << order, page_ext, iter) {
+		page_owner = get_page_owner(page_ext);
+		page_owner->handle = handle;
+		page_owner->order = order;
+		page_owner->gfp_mask = gfp_mask;
+		page_owner->last_migrate_reason = last_migrate_reason;
+		page_owner->pid = pid;
+		page_owner->tgid = tgid;
+		page_owner->ts_nsec = ts_nsec;
+		strscpy(page_owner->comm, comm,
+			sizeof(page_owner->comm));
+		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
+		__set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+	}
+	rcu_read_unlock();
+}
 
-	page_owner = get_page_owner(page_ext);
-	page_owner->handle = save_stack(gfp_mask);
-	page_owner->order = order;
-	page_owner->gfp_mask = gfp_mask;
-	page_owner->last_migrate_reason = -1;
+static inline void __update_page_owner_free_handle(struct page *page,
+						   depot_stack_handle_t handle,
+						   unsigned short order,
+						   pid_t pid, pid_t tgid,
+						   u64 free_ts_nsec)
+{
+	struct page_ext_iter iter;
+	struct page_ext *page_ext;
+	struct page_owner *page_owner;
 
-	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
+	rcu_read_lock();
+	for_each_page_ext(page, 1 << order, page_ext, iter) {
+		page_owner = get_page_owner(page_ext);
+		/* Only __reset_page_owner() wants to clear the bit */
+		if (handle) {
+			__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+			page_owner->free_handle = handle;
+		}
+		page_owner->free_ts_nsec = free_ts_nsec;
+		page_owner->free_pid = current->pid;
+		page_owner->free_tgid = current->tgid;
+	}
+	rcu_read_unlock();
 }
 
-void __set_page_owner_migrate_reason(struct page *page, int reason)
+void __reset_page_owner(struct page *page, unsigned short order)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext;
+	depot_stack_handle_t handle;
+	depot_stack_handle_t alloc_handle;
 	struct page_owner *page_owner;
+	u64 free_ts_nsec = local_clock();
 
+	page_ext = page_ext_get(page);
 	if (unlikely(!page_ext))
 		return;
 
 	page_owner = get_page_owner(page_ext);
-	page_owner->last_migrate_reason = reason;
+	alloc_handle = page_owner->handle;
+	page_ext_put(page_ext);
+
+	/*
+	 * Do not specify GFP_NOWAIT to make gfpflags_allow_spinning() == false
+	 * to prevent issues in stack_depot_save().
+	 * This is similar to alloc_pages_nolock() gfp flags, but only used
+	 * to signal stack_depot to avoid spin_locks.
+	 */
+	handle = save_stack(__GFP_NOWARN);
+	__update_page_owner_free_handle(page, handle, order, current->pid,
+					current->tgid, free_ts_nsec);
+
+	if (alloc_handle != early_handle)
+		/*
+		 * early_handle is being set as a handle for all those
+		 * early allocated pages. See init_pages_in_zone().
+		 * Since their refcount is not being incremented because
+		 * the machinery is not ready yet, we cannot decrement
+		 * their refcount either.
+		 */
+		dec_stack_record_count(alloc_handle, 1 << order);
 }
 
-void __split_page_owner(struct page *page, unsigned int order)
+noinline void __set_page_owner(struct page *page, unsigned short order,
+					gfp_t gfp_mask)
 {
-	int i;
-	struct page_ext *page_ext = lookup_page_ext(page);
+	u64 ts_nsec = local_clock();
+	depot_stack_handle_t handle;
+
+	handle = save_stack(gfp_mask);
+	__update_page_owner_handle(page, handle, order, gfp_mask, -1,
+				   ts_nsec, current->pid, current->tgid,
+				   current->comm);
+	inc_stack_record_count(handle, gfp_mask, 1 << order);
+}
+
+void __folio_set_owner_migrate_reason(struct folio *folio, int reason)
+{
+	struct page_ext *page_ext = page_ext_get(&folio->page);
 	struct page_owner *page_owner;
 
 	if (unlikely(!page_ext))
 		return;
 
 	page_owner = get_page_owner(page_ext);
-	page_owner->order = 0;
-	for (i = 1; i < (1 << order); i++)
-		__copy_page_owner(page, page + i);
+	page_owner->last_migrate_reason = reason;
+	page_ext_put(page_ext);
 }
 
-void __copy_page_owner(struct page *oldpage, struct page *newpage)
+void __split_page_owner(struct page *page, int old_order, int new_order)
 {
-	struct page_ext *old_ext = lookup_page_ext(oldpage);
-	struct page_ext *new_ext = lookup_page_ext(newpage);
-	struct page_owner *old_page_owner, *new_page_owner;
+	struct page_ext_iter iter;
+	struct page_ext *page_ext;
+	struct page_owner *page_owner;
 
-	if (unlikely(!old_ext || !new_ext))
+	rcu_read_lock();
+	for_each_page_ext(page, 1 << old_order, page_ext, iter) {
+		page_owner = get_page_owner(page_ext);
+		page_owner->order = new_order;
+	}
+	rcu_read_unlock();
+}
+
+void __folio_copy_owner(struct folio *newfolio, struct folio *old)
+{
+	struct page_ext *page_ext;
+	struct page_ext_iter iter;
+	struct page_owner *old_page_owner;
+	struct page_owner *new_page_owner;
+	depot_stack_handle_t migrate_handle;
+
+	page_ext = page_ext_get(&old->page);
+	if (unlikely(!page_ext))
 		return;
 
-	old_page_owner = get_page_owner(old_ext);
-	new_page_owner = get_page_owner(new_ext);
-	new_page_owner->order = old_page_owner->order;
-	new_page_owner->gfp_mask = old_page_owner->gfp_mask;
-	new_page_owner->last_migrate_reason =
-		old_page_owner->last_migrate_reason;
-	new_page_owner->handle = old_page_owner->handle;
+	old_page_owner = get_page_owner(page_ext);
+	page_ext_put(page_ext);
 
+	page_ext = page_ext_get(&newfolio->page);
+	if (unlikely(!page_ext))
+		return;
+
+	new_page_owner = get_page_owner(page_ext);
+	page_ext_put(page_ext);
+
+	migrate_handle = new_page_owner->handle;
+	__update_page_owner_handle(&newfolio->page, old_page_owner->handle,
+				   old_page_owner->order, old_page_owner->gfp_mask,
+				   old_page_owner->last_migrate_reason,
+				   old_page_owner->ts_nsec, old_page_owner->pid,
+				   old_page_owner->tgid, old_page_owner->comm);
 	/*
-	 * We don't clear the bit on the oldpage as it's going to be freed
-	 * after migration. Until then, the info can be useful in case of
-	 * a bug, and the overal stats will be off a bit only temporarily.
-	 * Also, migrate_misplaced_transhuge_page() can still fail the
-	 * migration and then we want the oldpage to retain the info. But
-	 * in that case we also don't need to explicitly clear the info from
-	 * the new page, which will be freed.
+	 * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio
+	 * will be freed after migration. Keep them until then as they may be
+	 * useful.
 	 */
-	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
+	__update_page_owner_free_handle(&newfolio->page, 0, old_page_owner->order,
+					old_page_owner->free_pid,
+					old_page_owner->free_tgid,
+					old_page_owner->free_ts_nsec);
+	/*
+	 * We linked the original stack to the new folio, we need to do the same
+	 * for the new one and the old folio otherwise there will be an imbalance
+	 * when subtracting those pages from the stack.
+	 */
+	rcu_read_lock();
+	for_each_page_ext(&old->page, 1 << new_page_owner->order, page_ext, iter) {
+		old_page_owner = get_page_owner(page_ext);
+		old_page_owner->handle = migrate_handle;
+	}
+	rcu_read_unlock();
 }
 
 void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -245,8 +428,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	struct page *page;
 	struct page_ext *page_ext;
 	struct page_owner *page_owner;
-	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
-	unsigned long end_pfn = pfn + zone->spanned_pages;
+	unsigned long pfn, block_end_pfn;
+	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long count[MIGRATE_TYPES] = { 0, };
 	int pageblock_mt, page_mt;
 	int i;
@@ -260,21 +443,19 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	 * not matter as the mixed block count will still be correct
 	 */
 	for (; pfn < end_pfn; ) {
-		if (!pfn_valid(pfn)) {
+		page = pfn_to_online_page(pfn);
+		if (!page) {
 			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
 			continue;
 		}
 
-		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+		block_end_pfn = pageblock_end_pfn(pfn);
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		page = pfn_to_page(pfn);
 		pageblock_mt = get_pageblock_migratetype(page);
 
 		for (; pfn < block_end_pfn; pfn++) {
-			if (!pfn_valid_within(pfn))
-				continue;
-
+			/* The pageblock is online, no need to recheck. */
 			page = pfn_to_page(pfn);
 
 			if (page_zone(page) != zone)
@@ -283,8 +464,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 			if (PageBuddy(page)) {
 				unsigned long freepage_order;
 
-				freepage_order = page_order_unsafe(page);
-				if (freepage_order < MAX_ORDER)
+				freepage_order = buddy_order_unsafe(page);
+				if (freepage_order <= MAX_PAGE_ORDER)
 					pfn += (1UL << freepage_order) - 1;
 				continue;
 			}
@@ -292,16 +473,15 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 			if (PageReserved(page))
 				continue;
 
-			page_ext = lookup_page_ext(page);
+			page_ext = page_ext_get(page);
 			if (unlikely(!page_ext))
 				continue;
 
-			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
-				continue;
+			if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
+				goto ext_put_continue;
 
 			page_owner = get_page_owner(page_ext);
-			page_mt = gfpflags_to_migratetype(
-					page_owner->gfp_mask);
+			page_mt = gfp_migratetype(page_owner->gfp_mask);
 			if (pageblock_mt != page_mt) {
 				if (is_migrate_cma(pageblock_mt))
 					count[MIGRATE_MOVABLE]++;
@@ -309,9 +489,12 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 					count[pageblock_mt]++;
 
 				pfn = block_end_pfn;
+				page_ext_put(page_ext);
 				break;
 			}
 			pfn += (1UL << page_owner->order) - 1;
+ext_put_continue:
+			page_ext_put(page_ext);
 		}
 	}
 
@@ -322,61 +505,88 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	seq_putc(m, '\n');
 }
 
+/*
+ * Looking for memcg information and print it out
+ */
+static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
+					 struct page *page)
+{
+#ifdef CONFIG_MEMCG
+	unsigned long memcg_data;
+	struct mem_cgroup *memcg;
+	bool online;
+	char name[80];
+
+	rcu_read_lock();
+	memcg_data = READ_ONCE(page->memcg_data);
+	if (!memcg_data || PageTail(page))
+		goto out_unlock;
+
+	if (memcg_data & MEMCG_DATA_OBJEXTS)
+		ret += scnprintf(kbuf + ret, count - ret,
+				"Slab cache page\n");
+
+	memcg = page_memcg_check(page);
+	if (!memcg)
+		goto out_unlock;
+
+	online = (memcg->css.flags & CSS_ONLINE);
+	cgroup_name(memcg->css.cgroup, name, sizeof(name));
+	ret += scnprintf(kbuf + ret, count - ret,
+			"Charged %sto %smemcg %s\n",
+			PageMemcgKmem(page) ? "(via objcg) " : "",
+			online ? "" : "offline ",
+			name);
+out_unlock:
+	rcu_read_unlock();
+#endif /* CONFIG_MEMCG */
+
+	return ret;
+}
+
 static ssize_t
 print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		struct page *page, struct page_owner *page_owner,
 		depot_stack_handle_t handle)
 {
-	int ret;
-	int pageblock_mt, page_mt;
+	int ret, pageblock_mt, page_mt;
 	char *kbuf;
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
 
+	count = min_t(size_t, count, PAGE_SIZE);
 	kbuf = kmalloc(count, GFP_KERNEL);
 	if (!kbuf)
 		return -ENOMEM;
 
-	ret = snprintf(kbuf, count,
-			"Page allocated via order %u, mask %#x(%pGg)\n",
+	ret = scnprintf(kbuf, count,
+			"Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns\n",
 			page_owner->order, page_owner->gfp_mask,
-			&page_owner->gfp_mask);
-
-	if (ret >= count)
-		goto err;
+			&page_owner->gfp_mask, page_owner->pid,
+			page_owner->tgid, page_owner->comm,
+			page_owner->ts_nsec);
 
 	/* Print information relevant to grouping pages by mobility */
 	pageblock_mt = get_pageblock_migratetype(page);
-	page_mt  = gfpflags_to_migratetype(page_owner->gfp_mask);
-	ret += snprintf(kbuf + ret, count - ret,
-			"PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n",
+	page_mt  = gfp_migratetype(page_owner->gfp_mask);
+	ret += scnprintf(kbuf + ret, count - ret,
+			"PFN 0x%lx type %s Block %lu type %s Flags %pGp\n",
 			pfn,
 			migratetype_names[page_mt],
 			pfn >> pageblock_order,
 			migratetype_names[pageblock_mt],
-			page->flags, &page->flags);
-
-	if (ret >= count)
-		goto err;
+			&page->flags);
 
-	depot_fetch_stack(handle, &trace);
-	ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
+	ret += stack_depot_snprint(handle, kbuf + ret, count - ret, 0);
 	if (ret >= count)
 		goto err;
 
 	if (page_owner->last_migrate_reason != -1) {
-		ret += snprintf(kbuf + ret, count - ret,
+		ret += scnprintf(kbuf + ret, count - ret,
 			"Page has been migrated, last migrate reason: %s\n",
 			migrate_reason_names[page_owner->last_migrate_reason]);
-		if (ret >= count)
-			goto err;
 	}
 
+	ret = print_page_owner_memcg(kbuf, count, ret, page);
+
 	ret += snprintf(kbuf + ret, count - ret, "\n");
 	if (ret >= count)
 		goto err;
@@ -392,17 +602,10 @@ err:
 	return -ENOMEM;
 }
 
-void __dump_page_owner(struct page *page)
+void __dump_page_owner(const struct page *page)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = page_ext_get((void *)page);
 	struct page_owner *page_owner;
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
 	depot_stack_handle_t handle;
 	gfp_t gfp_mask;
 	int mt;
@@ -414,27 +617,43 @@ void __dump_page_owner(struct page *page)
 
 	page_owner = get_page_owner(page_ext);
 	gfp_mask = page_owner->gfp_mask;
-	mt = gfpflags_to_migratetype(gfp_mask);
+	mt = gfp_migratetype(gfp_mask);
 
 	if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
-		pr_alert("page_owner info is not active (free page?)\n");
+		pr_alert("page_owner info is not present (never set?)\n");
+		page_ext_put(page_ext);
 		return;
 	}
 
+	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");
+
+	pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu, free_ts %llu\n",
+		 page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask,
+		 page_owner->pid, page_owner->tgid, page_owner->comm,
+		 page_owner->ts_nsec, page_owner->free_ts_nsec);
+
 	handle = READ_ONCE(page_owner->handle);
+	if (!handle)
+		pr_alert("page_owner allocation stack trace missing\n");
+	else
+		stack_depot_print(handle);
+
+	handle = READ_ONCE(page_owner->free_handle);
 	if (!handle) {
-		pr_alert("page_owner info is not active (free page?)\n");
-		return;
+		pr_alert("page_owner free stack trace missing\n");
+	} else {
+		pr_alert("page last free pid %d tgid %d stack trace:\n",
+			  page_owner->free_pid, page_owner->free_tgid);
+		stack_depot_print(handle);
 	}
 
-	depot_fetch_stack(handle, &trace);
-	pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
-		 page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
-	print_stack_trace(&trace, 0);
-
 	if (page_owner->last_migrate_reason != -1)
 		pr_alert("page has been migrated, last migrate reason: %s\n",
 			migrate_reason_names[page_owner->last_migrate_reason]);
+	page_ext_put(page_ext);
 }
 
 static ssize_t
@@ -450,17 +669,25 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		return -EINVAL;
 
 	page = NULL;
-	pfn = min_low_pfn + *ppos;
-
+	if (*ppos == 0)
+		pfn = min_low_pfn;
+	else
+		pfn = *ppos;
 	/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
 	while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
 		pfn++;
 
-	drain_all_pages(NULL);
-
 	/* Find an allocated page */
 	for (; pfn < max_pfn; pfn++) {
 		/*
+		 * This temporary page_owner is required so
+		 * that we can avoid the context switches while holding
+		 * the rcu lock and copying the page owner information to
+		 * user through copy_to_user() or GFP_KERNEL allocations.
+		 */
+		struct page_owner page_owner_tmp;
+
+		/*
 		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
 		 * validate the area as existing, skip it if not
 		 */
@@ -469,20 +696,16 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 			continue;
 		}
 
-		/* Check for holes within a MAX_ORDER area */
-		if (!pfn_valid_within(pfn))
-			continue;
-
 		page = pfn_to_page(pfn);
 		if (PageBuddy(page)) {
-			unsigned long freepage_order = page_order_unsafe(page);
+			unsigned long freepage_order = buddy_order_unsafe(page);
 
-			if (freepage_order < MAX_ORDER)
+			if (freepage_order <= MAX_PAGE_ORDER)
 				pfn += (1UL << freepage_order) - 1;
 			continue;
 		}
 
-		page_ext = lookup_page_ext(page);
+		page_ext = page_ext_get(page);
 		if (unlikely(!page_ext))
 			continue;
 
@@ -491,38 +714,66 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		 * because we don't hold the zone lock.
 		 */
 		if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
-			continue;
+			goto ext_put_continue;
+
+		/*
+		 * 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_ALLOCATED, &page_ext->flags))
+			goto ext_put_continue;
 
 		page_owner = get_page_owner(page_ext);
 
 		/*
+		 * Don't print "tail" pages of high-order allocations as that
+		 * would inflate the stats.
+		 */
+		if (!IS_ALIGNED(pfn, 1 << page_owner->order))
+			goto ext_put_continue;
+
+		/*
 		 * Access to page_ext->handle isn't synchronous so we should
 		 * be careful to access it.
 		 */
 		handle = READ_ONCE(page_owner->handle);
 		if (!handle)
-			continue;
+			goto ext_put_continue;
 
 		/* Record the next PFN to read in the file offset */
-		*ppos = (pfn - min_low_pfn) + 1;
+		*ppos = pfn + 1;
 
+		page_owner_tmp = *page_owner;
+		page_ext_put(page_ext);
 		return print_page_owner(buf, count, pfn, page,
-				page_owner, handle);
+				&page_owner_tmp, handle);
+ext_put_continue:
+		page_ext_put(page_ext);
 	}
 
 	return 0;
 }
 
-static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
+static loff_t lseek_page_owner(struct file *file, loff_t offset, int orig)
 {
-	struct page *page;
-	struct page_ext *page_ext;
-	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
-	unsigned long end_pfn = pfn + zone->spanned_pages;
-	unsigned long count = 0;
+	switch (orig) {
+	case SEEK_SET:
+		file->f_pos = offset;
+		break;
+	case SEEK_CUR:
+		file->f_pos += offset;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return file->f_pos;
+}
 
-	/* Scan block by block. First and last block may be incomplete */
-	pfn = zone->zone_start_pfn;
+static void init_pages_in_zone(struct zone *zone)
+{
+	unsigned long pfn = zone->zone_start_pfn;
+	unsigned long end_pfn = zone_end_pfn(zone);
+	unsigned long count = 0;
 
 	/*
 	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
@@ -530,98 +781,221 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 	 * not matter as the mixed block count will still be correct
 	 */
 	for (; pfn < end_pfn; ) {
+		unsigned long block_end_pfn;
+
 		if (!pfn_valid(pfn)) {
 			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
 			continue;
 		}
 
-		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+		block_end_pfn = pageblock_end_pfn(pfn);
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		page = pfn_to_page(pfn);
-
 		for (; pfn < block_end_pfn; pfn++) {
-			if (!pfn_valid_within(pfn))
-				continue;
-
-			page = pfn_to_page(pfn);
+			struct page *page = pfn_to_page(pfn);
+			struct page_ext *page_ext;
 
 			if (page_zone(page) != zone)
 				continue;
 
 			/*
-			 * We are safe to check buddy flag and order, because
-			 * this is init stage and only single thread runs.
+			 * To avoid having to grab zone->lock, be a little
+			 * careful when reading buddy page order. The only
+			 * danger is that we skip too much and potentially miss
+			 * some early allocated pages, which is better than
+			 * heavy lock contention.
 			 */
 			if (PageBuddy(page)) {
-				pfn += (1UL << page_order(page)) - 1;
+				unsigned long order = buddy_order_unsafe(page);
+
+				if (order > 0 && order <= MAX_PAGE_ORDER)
+					pfn += (1UL << order) - 1;
 				continue;
 			}
 
 			if (PageReserved(page))
 				continue;
 
-			page_ext = lookup_page_ext(page);
+			page_ext = page_ext_get(page);
 			if (unlikely(!page_ext))
 				continue;
 
-			/* Maybe overraping zone */
+			/* Maybe overlapping zone */
 			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
-				continue;
+				goto ext_put_continue;
 
 			/* Found early allocated page */
-			set_page_owner(page, 0, 0);
+			__update_page_owner_handle(page, early_handle, 0, 0,
+						   -1, local_clock(), current->pid,
+						   current->tgid, current->comm);
 			count++;
+ext_put_continue:
+			page_ext_put(page_ext);
 		}
+		cond_resched();
 	}
 
 	pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
-		pgdat->node_id, zone->name, count);
+		zone->zone_pgdat->node_id, zone->name, count);
 }
 
-static void init_zones_in_node(pg_data_t *pgdat)
+static void init_early_allocated_pages(void)
 {
 	struct zone *zone;
-	struct zone *node_zones = pgdat->node_zones;
-	unsigned long flags;
 
-	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
-		if (!populated_zone(zone))
-			continue;
+	for_each_populated_zone(zone)
+		init_pages_in_zone(zone);
+}
+
+static const struct file_operations page_owner_fops = {
+	.read		= read_page_owner,
+	.llseek		= lseek_page_owner,
+};
+
+static void *stack_start(struct seq_file *m, loff_t *ppos)
+{
+	struct stack *stack;
+	struct stack_print_ctx *ctx = m->private;
 
-		spin_lock_irqsave(&zone->lock, flags);
-		init_pages_in_zone(pgdat, zone);
-		spin_unlock_irqrestore(&zone->lock, flags);
+	if (*ppos == -1UL)
+		return NULL;
+
+	if (!*ppos) {
+		/*
+		 * This pairs with smp_store_release() from function
+		 * add_stack_record_to_list(), so we get a consistent
+		 * value of stack_list.
+		 */
+		stack = smp_load_acquire(&stack_list);
+		ctx->stack = stack;
+	} else {
+		stack = ctx->stack;
 	}
+
+	return stack;
 }
 
-static void init_early_allocated_pages(void)
+static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
 {
-	pg_data_t *pgdat;
+	struct stack *stack = v;
+	struct stack_print_ctx *ctx = m->private;
 
-	drain_all_pages(NULL);
-	for_each_online_pgdat(pgdat)
-		init_zones_in_node(pgdat);
+	stack = stack->next;
+	*ppos = stack ? *ppos + 1 : -1UL;
+	ctx->stack = stack;
+
+	return stack;
 }
 
-static const struct file_operations proc_page_owner_operations = {
-	.read		= read_page_owner,
+static unsigned long page_owner_pages_threshold;
+
+static int stack_print(struct seq_file *m, void *v)
+{
+	int i, nr_base_pages;
+	struct stack *stack = v;
+	unsigned long *entries;
+	unsigned long nr_entries;
+	struct stack_record *stack_record = stack->stack_record;
+	struct stack_print_ctx *ctx = m->private;
+
+	if (!stack->stack_record)
+		return 0;
+
+	nr_base_pages = refcount_read(&stack_record->count) - 1;
+
+	if (ctx->flags & STACK_PRINT_FLAG_PAGES &&
+	    (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold))
+		return 0;
+
+	if (ctx->flags & STACK_PRINT_FLAG_STACK) {
+		nr_entries = stack_record->size;
+		entries = stack_record->entries;
+		for (i = 0; i < nr_entries; i++)
+			seq_printf(m, " %pS\n", (void *)entries[i]);
+	}
+	if (ctx->flags & STACK_PRINT_FLAG_HANDLE)
+		seq_printf(m, "handle: %d\n", stack_record->handle.handle);
+	if (ctx->flags & STACK_PRINT_FLAG_PAGES)
+		seq_printf(m, "nr_base_pages: %d\n", nr_base_pages);
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static void stack_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations page_owner_stack_op = {
+	.start	= stack_start,
+	.next	= stack_next,
+	.stop	= stack_stop,
+	.show	= stack_print
 };
 
+static int page_owner_stack_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open_private(file, &page_owner_stack_op,
+				   sizeof(struct stack_print_ctx));
+
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		struct stack_print_ctx *ctx = m->private;
+
+		ctx->flags = (uintptr_t) inode->i_private;
+	}
+
+	return ret;
+}
+
+static const struct file_operations page_owner_stack_fops = {
+	.open		= page_owner_stack_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int page_owner_threshold_get(void *data, u64 *val)
+{
+	*val = READ_ONCE(page_owner_pages_threshold);
+	return 0;
+}
+
+static int page_owner_threshold_set(void *data, u64 val)
+{
+	WRITE_ONCE(page_owner_pages_threshold, val);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(page_owner_threshold_fops, &page_owner_threshold_get,
+			&page_owner_threshold_set, "%llu");
+
+
 static int __init pageowner_init(void)
 {
-	struct dentry *dentry;
+	struct dentry *dir;
 
 	if (!static_branch_unlikely(&page_owner_inited)) {
 		pr_info("page_owner is disabled\n");
 		return 0;
 	}
 
-	dentry = debugfs_create_file("page_owner", S_IRUSR, NULL,
-			NULL, &proc_page_owner_operations);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-
+	debugfs_create_file("page_owner", 0400, NULL, NULL, &page_owner_fops);
+	dir = debugfs_create_dir("page_owner_stacks", NULL);
+	debugfs_create_file("show_stacks", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_STACK |
+				     STACK_PRINT_FLAG_PAGES),
+			     &page_owner_stack_fops);
+	debugfs_create_file("show_handles", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_HANDLE |
+				     STACK_PRINT_FLAG_PAGES),
+			    &page_owner_stack_fops);
+	debugfs_create_file("show_stacks_handles", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_STACK |
+				     STACK_PRINT_FLAG_HANDLE),
+			    &page_owner_stack_fops);
+	debugfs_create_file("count_threshold", 0600, dir, NULL,
+			    &page_owner_threshold_fops);
 	return 0;
 }
 late_initcall(pageowner_init)