[PATCH v2 0/5] mm/page_owner: add debugfs files 'show_handles' and 'show_stacks_handles'

[PATCH v2 0/5] mm/page_owner: add debugfs files 'show_handles' and 'show_stacks_handles'

[Mauricio Faria de Oliveira]

Changelog:
 - v2:
   - Make context/usecase and hashing in userspace more explicit
     and add an example in the cover letter. (Michal Hocko)
   - Use different output files. (Michal Hocko, Vlastimil Babka)
   - Add context struct for plumbing flags from debugfs_create_file()
     down to stack_print(), avoiding more struct {file,seq}_operations
     for the new files.
   - Simplify commit messages.

 - v1:
   https://lore.kernel.org/linux-mm/20250924174023.261125-1-mfo@igalia.com/

Context:

The page_owner debug feature can help understand a particular situation in
in a point in time (e.g., identify biggest memory consumers; verify memory
counters that do not add up).

Another useful usecase is to collect data repeatedly over time, and use it
for profiling, monitoring, and even comparing different kernel versions,
at the stack trace level (e.g., watch for trends, leaks, correlations, and
regressions).

For this usecase, userspace periorically collects the data from page_owner
and organizes it in data structures appropriate for access per-stack trace.

Problem:

The usecase of tracking memory usage per stack trace (or tracking it for
a particular stack trace) requires uniquely identifying each stack trace
(i.e., keys to store their memory usage over periodic data collections).

This has to be done for every stack trace in every sample/data collection,
even if tracking only one stack trace (to identify it among all others).

Therefore, an approach like hashing the stack traces in userspace to create
unique keys/identifiers for them during post-processing can quickly become
expensive, considering the repetition and a growing number of stack traces.

Solution:

Fortunately, the kernel can provide a unique identifier for stack traces
in page_owner, which is the handle number in stackdepot. This eliminates
the need for creating keys (hashing) in userspace during post-processing.

Additionally, with that information, the stack traces themselves are not
needed until the memory usage should be resolved from a handle to a stack
trace (say, to look at the stack traces of a few top consumers). This can
reduce the amount of text emitted/copied by the kernel to userspace, and
save userspace from matching and discarding stack traces when not needed.

Changes:

This patchset adds 2 files to provide information, like 'show_stacks':
 - show_handles: print handle number and number of pages (no stack traces)
 - show_stacks_handles: print handle numbers and stack traces (no pages)

Now, it's possible to periodically collect data with handle numbers (keys)
and without stack traces (lower overhead) from 'show_handles', and later do
a final collection with handles and stack traces from 'show_stacks_handles'
to resolve the handles to their stack traces.

The output format follows the existing 'show_stacks' file, for simplicity,
but it can certainly be changed if a different format is more convenient.

Example:

The number of base pages collected can be stored per-handle number over the
periodic data collections, and finally resolved to stack traces per-handle
number as well with a final collection.

Later, one can, for example, identify the biggest consumers and watch their
trends or correlate increases/decreases with other events in the system,
or watch a particular stack trace(s) of interest during development.

Testing:

Tested on next-20250929.

 - show_stacks:
	
	 register_dummy_stack+0x32/0x70
	 init_page_owner+0x29/0x2f0
	 page_ext_init+0x27c/0x2b0
	 mm_core_init+0xdc/0x110
	nr_base_pages: 47
		
 - show_handles:

	handle: 1
	nr_base_pages: 47

 - show_stacks_handles:

	 register_dummy_stack+0x32/0x70
	 init_page_owner+0x29/0x2f0
	 page_ext_init+0x27c/0x2b0
	 mm_core_init+0xdc/0x110
	handle: 1
	
 - count_threshold:

	# echo 100 >/sys/kernel/debug/page_owner_stacks/count_threshold
	# grep register_dummy_stack show_stacks		# not present
	# grep -B4 '^handle: 1$' show_handles  		# not present 
	# grep -B4 '^handle: 1$' show_stacks_handles	# present
	 register_dummy_stack+0x32/0x70
	 init_page_owner+0x29/0x2f0
	 page_ext_init+0x27c/0x2b0
	 mm_core_init+0xdc/0x110
	handle: 1

Mauricio Faria de Oliveira (5):
  mm/page_owner: introduce struct stack_print_ctx
  mm/page_owner: add struct stack_print_ctx.flags
  mm/page_owner: add debugfs file 'show_handles'
  mm/page_owner: add debugfs file 'show_stacks_handles'
  mm/page_owner: update Documentation with 'show_handles' and
    'show_stacks_handles'

 Documentation/mm/page_owner.rst | 32 ++++++++++++++++-
 mm/page_owner.c                 | 61 +++++++++++++++++++++++++++------
 2 files changed, 81 insertions(+), 12 deletions(-)

-- 
2.48.1

[PATCH v2 1/5] mm/page_owner: introduce struct stack_print_ctx

[Mauricio Faria de Oliveira]

Currently, struct seq_file.private is used as an iterator in stack_list
by stack_start|next(), for stack_print().

Create a context struct for this, in order to add another field next.

No behavior change intended.

P.S.: page_owner_stack_open() is expanded with separate statements for
variable definition and return just in preparation for the next patch.

Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>
---
 mm/page_owner.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index c3ca21132c2c..c1a7d7afe945 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -45,6 +45,10 @@ static struct stack failure_stack;
 static struct stack *stack_list;
 static DEFINE_SPINLOCK(stack_list_lock);
 
+struct stack_print_ctx {
+	struct stack *stack;
+};
+
 static bool page_owner_enabled __initdata;
 DEFINE_STATIC_KEY_FALSE(page_owner_inited);
 
@@ -856,6 +860,7 @@ static const struct file_operations proc_page_owner_operations = {
 static void *stack_start(struct seq_file *m, loff_t *ppos)
 {
 	struct stack *stack;
+	struct stack_print_ctx *ctx = m->private;
 
 	if (*ppos == -1UL)
 		return NULL;
@@ -867,9 +872,9 @@ static void *stack_start(struct seq_file *m, loff_t *ppos)
 		 * value of stack_list.
 		 */
 		stack = smp_load_acquire(&stack_list);
-		m->private = stack;
+		ctx->stack = stack;
 	} else {
-		stack = m->private;
+		stack = ctx->stack;
 	}
 
 	return stack;
@@ -878,10 +883,11 @@ static void *stack_start(struct seq_file *m, loff_t *ppos)
 static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
 {
 	struct stack *stack = v;
+	struct stack_print_ctx *ctx = m->private;
 
 	stack = stack->next;
 	*ppos = stack ? *ppos + 1 : -1UL;
-	m->private = stack;
+	ctx->stack = stack;
 
 	return stack;
 }
@@ -926,7 +932,10 @@ static const struct seq_operations page_owner_stack_op = {
 
 static int page_owner_stack_open(struct inode *inode, struct file *file)
 {
-	return seq_open_private(file, &page_owner_stack_op, 0);
+	int ret = seq_open_private(file, &page_owner_stack_op,
+				   sizeof(struct stack_print_ctx));
+
+	return ret;
 }
 
 static const struct file_operations page_owner_stack_operations = {
-- 
2.48.1

Re: [PATCH v2 1/5] mm/page_owner: introduce struct stack_print_ctx

[Oscar Salvador]

On Wed, Oct 01, 2025 at 02:56:07PM -0300, Mauricio Faria de Oliveira wrote:
> Currently, struct seq_file.private is used as an iterator in stack_list
> by stack_start|next(), for stack_print().
> 
> Create a context struct for this, in order to add another field next.
> 
> No behavior change intended.
> 
> P.S.: page_owner_stack_open() is expanded with separate statements for
> variable definition and return just in preparation for the next patch.
> 
> Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>

Reviewed-by: Oscar Salvador <osalvador@suse.de>

 

-- 
Oscar Salvador
SUSE Labs

[PATCH v2 2/5] mm/page_owner: add struct stack_print_ctx.flags

[Mauricio Faria de Oliveira]

Add the flags field to stack_print_ctx, and define two flags for current
behavior (printing stack traces and their number of base pages).

The plumbing of flags is debugfs_create_file(data) -> inode.i_private ->
page_owner_stack_open() -> stack_print_ctx.flags -> stack_print().

No behavior change intended.

Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>
---
 mm/page_owner.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index c1a7d7afe945..e983ac21a4db 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -45,8 +45,12 @@ 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
+
 struct stack_print_ctx {
 	struct stack *stack;
+	u8 flags;
 };
 
 static bool page_owner_enabled __initdata;
@@ -901,20 +905,24 @@ static int stack_print(struct seq_file *m, void *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_entries = stack_record->size;
-	entries = stack_record->entries;
 	nr_base_pages = refcount_read(&stack_record->count) - 1;
 
 	if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold)
 		return 0;
 
-	for (i = 0; i < nr_entries; i++)
-		seq_printf(m, " %pS\n", (void *)entries[i]);
-	seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages);
+	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_PAGES)
+		seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages);
 
 	return 0;
 }
@@ -935,6 +943,13 @@ 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;
 }
 
@@ -973,7 +988,9 @@ static int __init pageowner_init(void)
 	debugfs_create_file("page_owner", 0400, NULL, NULL,
 			    &proc_page_owner_operations);
 	dir = debugfs_create_dir("page_owner_stacks", NULL);
-	debugfs_create_file("show_stacks", 0400, dir, NULL,
+	debugfs_create_file("show_stacks", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_STACK |
+				     STACK_PRINT_FLAG_PAGES),
 			    &page_owner_stack_operations);
 	debugfs_create_file("count_threshold", 0600, dir, NULL,
 			    &proc_page_owner_threshold);
-- 
2.48.1

Re: [PATCH v2 2/5] mm/page_owner: add struct stack_print_ctx.flags

[Oscar Salvador]

On Wed, Oct 01, 2025 at 02:56:08PM -0300, Mauricio Faria de Oliveira wrote:
> Add the flags field to stack_print_ctx, and define two flags for current
> behavior (printing stack traces and their number of base pages).
> 
> The plumbing of flags is debugfs_create_file(data) -> inode.i_private ->
> page_owner_stack_open() -> stack_print_ctx.flags -> stack_print().
> 
> No behavior change intended.
> 
> Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>

Reviewed-by: Oscar Salvador <osalvador@suse.de>

 

-- 
Oscar Salvador
SUSE Labs

[PATCH v2 3/5] mm/page_owner: add debugfs file 'show_handles'

[Mauricio Faria de Oliveira]

Add the flag STACK_PRINT_FLAG_HANDLE to print a stack's handle number
from stackdepot, and add the file 'show_handles' to show just handles
and their number of pages.

This is similar to 'show_stacks', with handles instead of stack traces.

Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>
---
 mm/page_owner.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index e983ac21a4db..5d488fce0e3d 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -47,6 +47,7 @@ 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;
@@ -921,6 +922,8 @@ static int stack_print(struct seq_file *m, void *v)
 		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\n", nr_base_pages);
 
@@ -992,6 +995,10 @@ static int __init pageowner_init(void)
 			    (void *)(STACK_PRINT_FLAG_STACK |
 				     STACK_PRINT_FLAG_PAGES),
 			    &page_owner_stack_operations);
+	debugfs_create_file("show_handles", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_HANDLE |
+				     STACK_PRINT_FLAG_PAGES),
+			    &page_owner_stack_operations);
 	debugfs_create_file("count_threshold", 0600, dir, NULL,
 			    &proc_page_owner_threshold);
 
-- 
2.48.1

Re: [PATCH v2 3/5] mm/page_owner: add debugfs file 'show_handles'

[Oscar Salvador]

On Wed, Oct 01, 2025 at 02:56:09PM -0300, Mauricio Faria de Oliveira wrote:
> Add the flag STACK_PRINT_FLAG_HANDLE to print a stack's handle number
> from stackdepot, and add the file 'show_handles' to show just handles
> and their number of pages.
> 
> This is similar to 'show_stacks', with handles instead of stack traces.
> 
> Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>

Reviewed-by: Oscar Salvador <osalvador@suse.de>

 

-- 
Oscar Salvador
SUSE Labs

[PATCH v2 4/5] mm/page_owner: add debugfs file 'show_stacks_handles'

[Mauricio Faria de Oliveira]

Add the file 'show_stacks_handles' to show just stack traces and their
handles, in order to resolve stack traces and handles (i.e., to identify
the stack traces for handles in previous reads from 'show_handles').

All stacks/handles must show up, regardless of their number of pages, that
might have become zero or no longer make 'count_threshold', but made it in
previous reads from 'show_handles' -- and need to be resolved later.

P.S.: now, print the extra newline independently of the number of pages.

Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>
---
 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 5d488fce0e3d..0e5c7bb3e4e8 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -913,7 +913,8 @@ static int stack_print(struct seq_file *m, void *v)
 
 	nr_base_pages = refcount_read(&stack_record->count) - 1;
 
-	if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold)
+	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) {
@@ -925,7 +926,8 @@ static int stack_print(struct seq_file *m, void *v)
 	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\n", nr_base_pages);
+		seq_printf(m, "nr_base_pages: %d\n", nr_base_pages);
+	seq_putc(m, '\n');
 
 	return 0;
 }
@@ -999,6 +1001,10 @@ static int __init pageowner_init(void)
 			    (void *)(STACK_PRINT_FLAG_HANDLE |
 				     STACK_PRINT_FLAG_PAGES),
 			    &page_owner_stack_operations);
+	debugfs_create_file("show_stacks_handles", 0400, dir,
+			    (void *)(STACK_PRINT_FLAG_STACK |
+				     STACK_PRINT_FLAG_HANDLE),
+			    &page_owner_stack_operations);
 	debugfs_create_file("count_threshold", 0600, dir, NULL,
 			    &proc_page_owner_threshold);
 
-- 
2.48.1

[PATCH v2 5/5] mm/page_owner: update Documentation with 'show_handles' and 'show_stacks_handles'

[Mauricio Faria de Oliveira]

Describe and provide examples for 'show_handles' and 'show_stacks_handles'.

Signed-off-by: Mauricio Faria de Oliveira <mfo@igalia.com>
---
 Documentation/mm/page_owner.rst | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst
index 3a45a20fc05a..6b12f3b007ec 100644
--- a/Documentation/mm/page_owner.rst
+++ b/Documentation/mm/page_owner.rst
@@ -27,7 +27,10 @@ enabled. Other usages are more than welcome.
 It can also be used to show all the stacks and their current number of
 allocated base pages, which gives us a quick overview of where the memory
 is going without the need to screen through all the pages and match the
-allocation and free operation.
+allocation and free operation. It's also possible to show only a numeric
+identifier of all the stacks (without stack traces) and their number of
+allocated base pages (faster to read and parse, eg, for monitoring) that
+can be matched with stacks later (show_handles and show_stacks_handles).
 
 page owner is disabled by default. So, if you'd like to use it, you need
 to add "page_owner=on" to your boot cmdline. If the kernel is built
@@ -116,6 +119,33 @@ Usage
 	nr_base_pages: 20824
 	...
 
+	cat /sys/kernel/debug/page_owner_stacks/show_handles > handles_7000.txt
+	cat handles_7000.txt
+	handle: 42
+	nr_base_pages: 20824
+	...
+
+	cat /sys/kernel/debug/page_owner_stacks/show_stacks_handles > stacks_handles.txt
+	cat stacks_handles.txt
+	 post_alloc_hook+0x177/0x1a0
+	 get_page_from_freelist+0xd01/0xd80
+	 __alloc_pages+0x39e/0x7e0
+	 alloc_pages_mpol+0x22e/0x490
+	 folio_alloc+0xd5/0x110
+	 filemap_alloc_folio+0x78/0x230
+	 page_cache_ra_order+0x287/0x6f0
+	 filemap_get_pages+0x517/0x1160
+	 filemap_read+0x304/0x9f0
+	 xfs_file_buffered_read+0xe6/0x1d0 [xfs]
+	 xfs_file_read_iter+0x1f0/0x380 [xfs]
+	 __kernel_read+0x3b9/0x730
+	 kernel_read_file+0x309/0x4d0
+	 __do_sys_finit_module+0x381/0x730
+	 do_syscall_64+0x8d/0x150
+	 entry_SYSCALL_64_after_hwframe+0x62/0x6a
+	handle: 42
+	...
+
 	cat /sys/kernel/debug/page_owner > page_owner_full.txt
 	./page_owner_sort page_owner_full.txt sorted_page_owner.txt
 
-- 
2.48.1

Re: [PATCH v2 0/5] mm/page_owner: add debugfs files 'show_handles' and 'show_stacks_handles'

[Andrew Morton]

On Wed,  1 Oct 2025 14:56:06 -0300 Mauricio Faria de Oliveira <mfo@igalia.com> wrote:

> Fortunately, the kernel can provide a unique identifier for stack traces
> in page_owner, which is the handle number in stackdepot. This eliminates
> the need for creating keys (hashing) in userspace during post-processing.

Looks nice, thanks.

I'm surprised that our in-tree userspace tooling for page_owner seems
rather weak.  Nobody has touched tools/mm/page_owner_sort.c in two
years.