[PATCH 1/6] mm/page_owner: extract skip_buddy_pages() helper to unify buddy page skipping

[PATCH 1/6] mm/page_owner: extract skip_buddy_pages() helper to unify buddy page skipping

[Ye Liu]

Three places in page_owner.c duplicate the same pattern: check if a
page is PageBuddy, read its order via buddy_order_unsafe(), advance
the pfn past the buddy block if the order is valid, and continue.

Consolidate them into a single inline helper skip_buddy_pages().
The function returns true (skip) for any buddy page and advances
@pfn past the block when the order is valid; returns false if the
page is not a buddy page and should be processed normally.

The old init_pages_in_zone() variant used "order > 0" as an extra
guard before advancing pfn, but the continue was unconditional and
(1UL << 0) - 1 == 0, so the behaviour is identical.  The comment
about zone->lock is preserved in the helper's kernel-doc.

No functional change.

Signed-off-by: Ye Liu <ye.liu@linux.dev>
---
 mm/page_owner.c | 52 ++++++++++++++++++++++++-------------------------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 2dddcb6510aa..342549891a8d 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -422,6 +422,29 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old)
 	rcu_read_unlock();
 }
 
+/*
+ * Check if a page is a buddy page and advance @pfn past the entire buddy block.
+ * This safely reads the buddy order without the zone lock, which may cause us
+ * to skip less than the full buddy block, but that is acceptable for page owner
+ * iteration purposes.
+ *
+ * Return: true if the page was skipped (caller should continue its loop),
+ *         false if the page is not a buddy page and should be processed normally.
+ */
+static inline bool skip_buddy_pages(unsigned long *pfn, struct page *page)
+{
+	unsigned long order;
+
+	if (!PageBuddy(page))
+		return false;
+
+	order = buddy_order_unsafe(page);
+	if (order <= MAX_PAGE_ORDER)
+		*pfn += (1UL << order) - 1;
+
+	return true;
+}
+
 void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 				       pg_data_t *pgdat, struct zone *zone)
 {
@@ -461,14 +484,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 			if (page_zone(page) != zone)
 				continue;
 
-			if (PageBuddy(page)) {
-				unsigned long freepage_order;
-
-				freepage_order = buddy_order_unsafe(page);
-				if (freepage_order <= MAX_PAGE_ORDER)
-					pfn += (1UL << freepage_order) - 1;
+			if (skip_buddy_pages(&pfn, page))
 				continue;
-			}
 
 			if (PageReserved(page))
 				continue;
@@ -697,13 +714,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		}
 
 		page = pfn_to_page(pfn);
-		if (PageBuddy(page)) {
-			unsigned long freepage_order = buddy_order_unsafe(page);
-
-			if (freepage_order <= MAX_PAGE_ORDER)
-				pfn += (1UL << freepage_order) - 1;
+		if (skip_buddy_pages(&pfn, page))
 			continue;
-		}
 
 		page_ext = page_ext_get(page);
 		if (unlikely(!page_ext))
@@ -798,20 +810,8 @@ static void init_pages_in_zone(struct zone *zone)
 			if (page_zone(page) != zone)
 				continue;
 
-			/*
-			 * 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)) {
-				unsigned long order = buddy_order_unsafe(page);
-
-				if (order > 0 && order <= MAX_PAGE_ORDER)
-					pfn += (1UL << order) - 1;
+			if (skip_buddy_pages(&pfn, page))
 				continue;
-			}
 
 			if (PageReserved(page))
 				continue;
-- 
2.43.0

Re: [PATCH 1/6] mm/page_owner: extract skip_buddy_pages() helper to unify buddy page skipping

[Andrew Morton]

On Tue, 23 Jun 2026 14:52:26 +0800 Ye Liu <ye.liu@linux.dev> wrote:

> Three places in page_owner.c duplicate the same pattern: check if a
> page is PageBuddy, read its order via buddy_order_unsafe(), advance
> the pfn past the buddy block if the order is valid, and continue.
> 
> Consolidate them into a single inline helper skip_buddy_pages().
> The function returns true (skip) for any buddy page and advances
> @pfn past the block when the order is valid; returns false if the
> page is not a buddy page and should be processed normally.
> 
> The old init_pages_in_zone() variant used "order > 0" as an extra
> guard before advancing pfn, but the continue was unconditional and
> (1UL << 0) - 1 == 0, so the behaviour is identical.  The comment
> about zone->lock is preserved in the helper's kernel-doc.

All looks nice, thanks.

A [0/N] cover letter is nice to have.

AI review identified a few possible pre-existing issues, if you're
interested:
	https://sashiko.dev/#/patchset/20260623065234.31866-2-ye.liu@linux.dev

Re: [PATCH 1/6] mm/page_owner: extract skip_buddy_pages() helper to unify buddy page skipping

[Vlastimil Babka (SUSE)]

On 6/25/26 02:20, Andrew Morton wrote:
> On Tue, 23 Jun 2026 14:52:26 +0800 Ye Liu <ye.liu@linux.dev> wrote:
> 
>> Three places in page_owner.c duplicate the same pattern: check if a
>> page is PageBuddy, read its order via buddy_order_unsafe(), advance
>> the pfn past the buddy block if the order is valid, and continue.
>> 
>> Consolidate them into a single inline helper skip_buddy_pages().
>> The function returns true (skip) for any buddy page and advances
>> @pfn past the block when the order is valid; returns false if the
>> page is not a buddy page and should be processed normally.
>> 
>> The old init_pages_in_zone() variant used "order > 0" as an extra
>> guard before advancing pfn, but the continue was unconditional and
>> (1UL << 0) - 1 == 0, so the behaviour is identical.  The comment
>> about zone->lock is preserved in the helper's kernel-doc.
> 
> All looks nice, thanks.

I got a bunch of "added to mm-hotfixes-unstable branch" mails, but this
seems like cleanups and nothing urgent? Was that intended?

> A [0/N] cover letter is nice to have.

Seems like it exists, but wasn't delivered. Lore shows its message id, but
as missing.

> AI review identified a few possible pre-existing issues, if you're
> interested:
> 	https://sashiko.dev/#/patchset/20260623065234.31866-2-ye.liu@linux.dev
> 

Re: [PATCH 1/6] mm/page_owner: extract skip_buddy_pages() helper to unify buddy page skipping

[Ye Liu]

在 2026/6/25 15:13, Vlastimil Babka (SUSE) 写道:
> On 6/25/26 02:20, Andrew Morton wrote:
>> On Tue, 23 Jun 2026 14:52:26 +0800 Ye Liu <ye.liu@linux.dev> wrote:
>>
>>> Three places in page_owner.c duplicate the same pattern: check if a
>>> page is PageBuddy, read its order via buddy_order_unsafe(), advance
>>> the pfn past the buddy block if the order is valid, and continue.
>>>
>>> Consolidate them into a single inline helper skip_buddy_pages().
>>> The function returns true (skip) for any buddy page and advances
>>> @pfn past the block when the order is valid; returns false if the
>>> page is not a buddy page and should be processed normally.
>>>
>>> The old init_pages_in_zone() variant used "order > 0" as an extra
>>> guard before advancing pfn, but the continue was unconditional and
>>> (1UL << 0) - 1 == 0, so the behaviour is identical.  The comment
>>> about zone->lock is preserved in the helper's kernel-doc.
>>
>> All looks nice, thanks.
> 
> I got a bunch of "added to mm-hotfixes-unstable branch" mails, but this
> seems like cleanups and nothing urgent? Was that intended?
> 
>> A [0/N] cover letter is nice to have.
> 
> Seems like it exists, but wasn't delivered. Lore shows its message id, but
> as missing.


Apologies, I accidentally sent the cover letter only to my own address.
I'll ensure it goes to the mailing list in future submissions.         
Thanks for pointing it out.                                            


Subject: [PATCH 0/6] mm/page_owner: misc cleanups                      
                                                                       
Hi,                                                                    
                                                                       
This series collects a few cleanups for mm/page_owner.c that have been 
accumulated while reading through the file.  There is no functional    
change -- the goal is to make the code easier to read and maintain.    
                                                                       
Patch 1 consolidates three identical PageBuddy skip blocks into a      
single skip_buddy_pages() helper, eliminating the duplication and      
keeping the lockless-read comment in one place.                        
                                                                       
Patch 2 replaces the -1 magic number used for "never migrated" with    
a local MIGRATE_REASON_NONE define, making the intent explicit at      
every use site.                                                        
                                                                       
Patch 3 hoists the CONFIG_MEMCG guard out of print_page_owner_memcg()'s
body so that the real implementation and the empty stub are two clearly
separate definitions, the common kernel idiom.                         
                                                                       
Patch 4 adds a missing \n to the count_threshold debugfs attribute     
format string so that cat(1) output is properly terminated.            
                                                                       
Patch 5 moves free_ts_nsec from the allocation summary line to the     
free section in __dump_page_owner(), grouping it with free_pid and     
free_tgid where it logically belongs.  This also makes the dump        
output consistent with print_page_owner().                             
                                                                       
Patch 6 drops the redundant page_owner_ prefix from file-scoped static 
symbols (stack_fops, threshold_fops, etc.).  Since they cannot collide 
across translation units, the prefix carries no information.           
                                                                       
The series is based on v6.17-rc1 and has been compile-tested with and  
without CONFIG_MEMCG.                                                  
                                                                       
Ye Liu (6):                                                            
  mm/page_owner: extract skip_buddy_pages() helper to unify buddy page 
    skipping                                                           
  mm/page_owner: use MIGRATE_REASON_NONE instead of -1 for             
    last_migrate_reason                                                
  mm/page_owner: hoist CONFIG_MEMCG to function level for              
    print_page_owner_memcg()                                           
  mm/page_owner: add missing newline to count_threshold format string  
  mm/page_owner: move free_ts_nsec output to free section in           
    __dump_page_owner()                                                
  mm/page_owner: drop redundant page_owner prefix from static symbols  
                                                                       
 mm/page_owner.c | 121 +++++++++++++++++++++++++++---------------------
 1 file changed, 67 insertions(+), 54 deletions(-)                     


> 
>> AI review identified a few possible pre-existing issues, if you're
>> interested:
>> 	https://sashiko.dev/#/patchset/20260623065234.31866-2-ye.liu@linux.dev
>>
> 

-- 
Thanks,
Ye Liu

[PATCH 2/6] mm/page_owner: use MIGRATE_REASON_NONE instead of -1 for last_migrate_reason

[Ye Liu]

The last_migrate_reason field uses -1 as a sentinel value to mean "no
migration has happened".  Replace the four bare -1 occurrences with a
local MIGRATE_REASON_NONE define so the intent is explicit and the
magic number is eliminated.

No functional change.

Signed-off-by: Ye Liu <ye.liu@linux.dev>
---
 mm/page_owner.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 342549891a8d..ebafa9d7ff07 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -21,6 +21,13 @@
  */
 #define PAGE_OWNER_STACK_DEPTH (16)
 
+/*
+ * Used to indicate that a page has never been migrated, as the valid
+ * migrate_reason values are non-negative enum members (MR_* in
+ * include/linux/migrate_mode.h).
+ */
+#define MIGRATE_REASON_NONE (-1)
+
 struct page_owner {
 	unsigned short order;
 	short last_migrate_reason;
@@ -339,7 +346,7 @@ noinline void __set_page_owner(struct page *page, unsigned short order,
 	depot_stack_handle_t handle;
 
 	handle = save_stack(gfp_mask);
-	__update_page_owner_handle(page, handle, order, gfp_mask, -1,
+	__update_page_owner_handle(page, handle, order, gfp_mask, MIGRATE_REASON_NONE,
 				   ts_nsec, current->pid, current->tgid,
 				   current->comm);
 	inc_stack_record_count(handle, gfp_mask, 1 << order);
@@ -596,7 +603,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	if (ret >= count)
 		goto err;
 
-	if (page_owner->last_migrate_reason != -1) {
+	if (page_owner->last_migrate_reason != MIGRATE_REASON_NONE) {
 		ret += scnprintf(kbuf + ret, count - ret,
 			"Page has been migrated, last migrate reason: %s\n",
 			migrate_reason_names[page_owner->last_migrate_reason]);
@@ -667,7 +674,7 @@ void __dump_page_owner(const struct page *page)
 		stack_depot_print(handle);
 	}
 
-	if (page_owner->last_migrate_reason != -1)
+	if (page_owner->last_migrate_reason != MIGRATE_REASON_NONE)
 		pr_alert("page has been migrated, last migrate reason: %s\n",
 			migrate_reason_names[page_owner->last_migrate_reason]);
 	page_ext_put(page_ext);
@@ -826,7 +833,7 @@ static void init_pages_in_zone(struct zone *zone)
 
 			/* Found early allocated page */
 			__update_page_owner_handle(page, early_handle, 0, 0,
-						   -1, local_clock(), current->pid,
+						   MIGRATE_REASON_NONE, local_clock(), current->pid,
 						   current->tgid, current->comm);
 			count++;
 ext_put_continue:
-- 
2.43.0

[PATCH 3/6] mm/page_owner: hoist CONFIG_MEMCG to function level for print_page_owner_memcg()

[Ye Liu]

The print_page_owner_memcg() function has CONFIG_MEMCG guarding its
entire body via #ifdef inside the function, which leaves a no-op
{ return ret; } when the config is disabled.  Hoist the #ifdef to the
top level so the real implementation and the empty stub are two clearly
separated definitions.

No functional change.

Signed-off-by: Ye Liu <ye.liu@linux.dev>
---
 mm/page_owner.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index ebafa9d7ff07..5d8773c90cd9 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -529,13 +529,13 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	seq_putc(m, '\n');
 }
 
+#ifdef CONFIG_MEMCG
 /*
  * 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;
@@ -563,10 +563,16 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
 			name);
 out_unlock:
 	rcu_read_unlock();
-#endif /* CONFIG_MEMCG */
 
 	return ret;
 }
+#else
+static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
+					 struct page *page)
+{
+	return ret;
+}
+#endif
 
 static ssize_t
 print_page_owner(char __user *buf, size_t count, unsigned long pfn,
-- 
2.43.0

[PATCH 4/6] mm/page_owner: add missing newline to count_threshold format string

[Ye Liu]

The DEFINE_SIMPLE_ATTRIBUTE format string for page_owner_threshold_fops
is missing a trailing \n.  simple_attr_read() uses scnprintf() with the
format string, which does not append a newline, so reading
/sys/kernel/debug/page_owner_stacks/count_threshold produces output
without a terminating newline.  Add the missing \n to match the
standard debugfs attribute convention.

Signed-off-by: Ye Liu <ye.liu@linux.dev>
---
 mm/page_owner.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 5d8773c90cd9..958151ccb587 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -981,7 +981,7 @@ static int page_owner_threshold_set(void *data, u64 val)
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(page_owner_threshold_fops, &page_owner_threshold_get,
-			&page_owner_threshold_set, "%llu");
+			&page_owner_threshold_set, "%llu\n");
 
 
 static int __init pageowner_init(void)
-- 
2.43.0

[PATCH 5/6] mm/page_owner: move free_ts_nsec output to free section in __dump_page_owner()

[Ye Liu]

The free_ts_nsec field is a free-event timestamp, but it was printed
in the allocation summary line alongside ts_nsec (allocation time).
Move it to the free section where it logically belongs, together with
free_pid and free_tgid.  This also makes __dump_page_owner() consistent
with print_page_owner(), which only prints ts_nsec in the allocation
summary.

The output now groups all free-related information (pid, tgid,
timestamp, stack trace) in one place.

No functional change except output formatting.

Signed-off-by: Ye Liu <ye.liu@linux.dev>
---
 mm/page_owner.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 958151ccb587..eaccff355cb4 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -660,10 +660,10 @@ void __dump_page_owner(const struct page *page)
 	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",
+	pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, tgid %d (%s), 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);
+		 page_owner->ts_nsec);
 
 	handle = READ_ONCE(page_owner->handle);
 	if (!handle)
@@ -675,8 +675,9 @@ void __dump_page_owner(const struct page *page)
 	if (!handle) {
 		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);
+		pr_alert("page last free pid %d tgid %d ts %llu stack trace:\n",
+			  page_owner->free_pid, page_owner->free_tgid,
+			  page_owner->free_ts_nsec);
 		stack_depot_print(handle);
 	}
 
-- 
2.43.0

[PATCH 6/6] mm/page_owner: drop redundant page_owner prefix from static symbols

[Ye Liu]

All of these symbols are file-scoped (static) in page_owner.c, so the
page_owner_ prefix is pure noise.  Rename them to shorter, still-clear
names:

  page_owner_stack_op      -> stack_op
  page_owner_stack_open    -> stack_open
  page_owner_stack_fops    -> stack_fops
  page_owner_pages_threshold -> pages_threshold
  page_owner_threshold_get -> threshold_get
  page_owner_threshold_set -> threshold_set
  page_owner_threshold_fops -> threshold_fops

No functional change.

Signed-off-by: Ye Liu <ye.liu@linux.dev>
---
 mm/page_owner.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index eaccff355cb4..ec9600025127 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -901,7 +901,7 @@ static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
 	return stack;
 }
 
-static unsigned long page_owner_pages_threshold;
+static unsigned long pages_threshold;
 
 static int stack_print(struct seq_file *m, void *v)
 {
@@ -918,7 +918,7 @@ static int stack_print(struct seq_file *m, void *v)
 	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))
+	    (nr_base_pages < 1 || nr_base_pages < pages_threshold))
 		return 0;
 
 	if (ctx->flags & STACK_PRINT_FLAG_STACK) {
@@ -940,16 +940,16 @@ static void stack_stop(struct seq_file *m, void *v)
 {
 }
 
-static const struct seq_operations page_owner_stack_op = {
+static const struct seq_operations 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)
+static int stack_open(struct inode *inode, struct file *file)
 {
-	int ret = seq_open_private(file, &page_owner_stack_op,
+	int ret = seq_open_private(file, &stack_op,
 				   sizeof(struct stack_print_ctx));
 
 	if (!ret) {
@@ -962,28 +962,27 @@ static int page_owner_stack_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-static const struct file_operations page_owner_stack_fops = {
-	.open		= page_owner_stack_open,
+static const struct file_operations stack_fops = {
+	.open		= stack_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
 
-static int page_owner_threshold_get(void *data, u64 *val)
+static int threshold_get(void *data, u64 *val)
 {
-	*val = READ_ONCE(page_owner_pages_threshold);
+	*val = READ_ONCE(pages_threshold);
 	return 0;
 }
 
-static int page_owner_threshold_set(void *data, u64 val)
+static int threshold_set(void *data, u64 val)
 {
-	WRITE_ONCE(page_owner_pages_threshold, val);
+	WRITE_ONCE(pages_threshold, val);
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(page_owner_threshold_fops, &page_owner_threshold_get,
-			&page_owner_threshold_set, "%llu\n");
-
+DEFINE_SIMPLE_ATTRIBUTE(threshold_fops, &threshold_get,
+			&threshold_set, "%llu\n");
 
 static int __init pageowner_init(void)
 {
@@ -999,17 +998,17 @@ static int __init pageowner_init(void)
 	debugfs_create_file("show_stacks", 0400, dir,
 			    (void *)(STACK_PRINT_FLAG_STACK |
 				     STACK_PRINT_FLAG_PAGES),
-			     &page_owner_stack_fops);
+			     &stack_fops);
 	debugfs_create_file("show_handles", 0400, dir,
 			    (void *)(STACK_PRINT_FLAG_HANDLE |
 				     STACK_PRINT_FLAG_PAGES),
-			    &page_owner_stack_fops);
+			    &stack_fops);
 	debugfs_create_file("show_stacks_handles", 0400, dir,
 			    (void *)(STACK_PRINT_FLAG_STACK |
 				     STACK_PRINT_FLAG_HANDLE),
-			    &page_owner_stack_fops);
+			    &stack_fops);
 	debugfs_create_file("count_threshold", 0600, dir, NULL,
-			    &page_owner_threshold_fops);
+			    &threshold_fops);
 	return 0;
 }
 late_initcall(pageowner_init)
-- 
2.43.0