Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   Oscar Salvador <osalvador@suse.de>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        Michal Hocko <mhocko@suse.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Waiman Long <longman@redhat.com>,
        Suren Baghdasaryan <surenb@google.com>,
        Marco Elver <elver@google.com>,
        Andrey Konovalov <andreyknvl@gmail.com>,
        Eric Dumazet <edumazet@google.com>,
        Alexander Potapenko <glider@google.com>,
        Oscar Salvador <osalvador@suse.de>
Subject: [PATCH v6 4/4] mm,page_owner: Filter out stacks by a threshold counter
Date:   Mon, 20 Nov 2023 09:43:00 +0100
Message-Id: <20231120084300.4368-5-osalvador@suse.de>
In-Reply-To: <20231120084300.4368-1-osalvador@suse.de>
References: <20231120084300.4368-1-osalvador@suse.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We want to be able to filter out the output based on a certain
threshold, so we can leave out stacks with a low counter of
outstanding allocations.

We can control the threshold value by a new file called
'page_owner_threshold', which is 0 by default.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 mm/page_owner.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 509c11e506db..6ee345dafd01 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -41,6 +41,8 @@ static depot_stack_handle_t dummy_handle;
 static depot_stack_handle_t failure_handle;
 static depot_stack_handle_t early_handle;
 
+static unsigned long page_owner_stack_threshold;
+
 static void init_early_allocated_pages(void);
 
 static int __init early_page_owner_param(char *buf)
@@ -763,6 +765,9 @@ static int stack_print(struct seq_file *m, void *v)
 	int ret = 0;
 	struct stack_record *stack = (struct stack_record *)v;
 
+	if (refcount_read(&stack->count) < page_owner_stack_threshold)
+		return 0;
+
 	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
 	ret += stack_depot_get_stack_info(stack, buf);
@@ -804,6 +809,21 @@ const struct file_operations page_owner_stack_operations = {
 	.release        = seq_release,
 };
 
+int page_owner_threshold_get(void *data, u64 *val)
+{
+	*val = page_owner_stack_threshold;
+	return 0;
+}
+
+int page_owner_threshold_set(void *data, u64 val)
+{
+	page_owner_stack_threshold = val;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(proc_page_owner_threshold, &page_owner_threshold_get,
+			&page_owner_threshold_set, "%llu");
+
 static int __init pageowner_init(void)
 {
 	if (!static_branch_unlikely(&page_owner_inited)) {
@@ -815,6 +835,8 @@ static int __init pageowner_init(void)
 			    &proc_page_owner_operations);
 	debugfs_create_file("page_owner_stacks", 0400, NULL, NULL,
 			    &page_owner_stack_operations);
+	debugfs_create_file("page_owner_threshold", 0600, NULL, NULL,
+			    &proc_page_owner_threshold);
 
 	return 0;
 }
-- 
2.42.0