Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Roman Gushchin <roman.gushchin@linux.dev>
To:     Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org
Cc:     Dave Chinner <dchinner@redhat.com>, linux-kernel@vger.kernel.org,
        Kent Overstreet <kent.overstreet@gmail.com>,
        Hillf Danton <hdanton@sina.com>,
        Christophe JAILLET <christophe.jaillet@wanadoo.fr>,
        Muchun Song <songmuchun@bytedance.com>,
        Roman Gushchin <roman.gushchin@linux.dev>
Subject: [PATCH v5 6/6] mm: shrinkers: add scan interface for shrinker debugfs
Date:   Tue, 31 May 2022 20:22:27 -0700
Message-Id: <20220601032227.4076670-7-roman.gushchin@linux.dev>
In-Reply-To: <20220601032227.4076670-1-roman.gushchin@linux.dev>
References: <20220601032227.4076670-1-roman.gushchin@linux.dev>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a scan interface which allows to trigger scanning of a particular
shrinker and specify memcg and numa node. It's useful for testing,
debugging and profiling of a specific scan_objects() callback.
Unlike alternatives (creating a real memory pressure and dropping
caches via /proc/sys/vm/drop_caches) this interface allows to interact
with only one shrinker at once. Also, if a shrinker is misreporting
the number of objects (as some do), it doesn't affect scanning.

Signed-off-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Muchun Song <songmuchun@bytedance.com>
---
 .../admin-guide/mm/shrinker_debugfs.rst       | 39 +++++++++-
 mm/shrinker_debug.c                           | 74 +++++++++++++++++++
 2 files changed, 109 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/mm/shrinker_debugfs.rst b/Documentation/admin-guide/mm/shrinker_debugfs.rst
index 1e0e5bdb8179..3887f0b294fe 100644
--- a/Documentation/admin-guide/mm/shrinker_debugfs.rst
+++ b/Documentation/admin-guide/mm/shrinker_debugfs.rst
@@ -5,14 +5,16 @@ Shrinker Debugfs Interface
 ==========================
 
 Shrinker debugfs interface provides a visibility into the kernel memory
-shrinkers subsystem and allows to get information about individual shrinkers.
+shrinkers subsystem and allows to get information about individual shrinkers
+and interact with them.
 
 For each shrinker registered in the system a directory in **<debugfs>/shrinker/**
 is created. The directory's name is composed from the shrinker's name and an
 unique id: e.g. *kfree_rcu-0* or *sb-xfs:vda1-36*.
 
-Each shrinker directory contains the **count** file, which allows to trigger
-the *count_objects()* callback for each memcg and numa node (if applicable).
+Each shrinker directory contains **count** and **scan** files, which allow to
+trigger *count_objects()* and *scan_objects()* callbacks for each memcg and
+numa node (if applicable).
 
 Usage:
 ------
@@ -43,7 +45,7 @@ Usage:
 
     $ cd sb-btrfs\:vda2-24/
     $ ls
-    count
+    count            scan
 
 3. *Count objects*
 
@@ -102,3 +104,32 @@ Usage:
     2877 84 0
     293 1 0
     735 8 0
+
+4. *Scan objects*
+
+  The expected input format::
+
+    <cgroup inode id> <numa id> <number of objects to scan>
+
+  For a non-memcg-aware shrinker or on a system with no memory
+  cgrups **0** should be passed as cgroup id.
+  ::
+
+    $ cd /sys/kernel/debug/shrinker/
+    $ cd sb-btrfs\:vda2-24/
+
+    $ cat count | head -n 5
+    1 212 0
+    21 97 0
+    55 802 5
+    2367 2 0
+    225 13 0
+
+    $ echo "55 0 200" > scan
+
+    $ cat count | head -n 5
+    1 212 0
+    21 96 0
+    55 752 5
+    2367 2 0
+    225 13 0
diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c
index 781ecbd3d608..e25114e0c41c 100644
--- a/mm/shrinker_debug.c
+++ b/mm/shrinker_debug.c
@@ -99,6 +99,78 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v)
 }
 DEFINE_SHOW_ATTRIBUTE(shrinker_debugfs_count);
 
+static int shrinker_debugfs_scan_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+	return nonseekable_open(inode, file);
+}
+
+static ssize_t shrinker_debugfs_scan_write(struct file *file,
+					   const char __user *buf,
+					   size_t size, loff_t *pos)
+{
+	struct shrinker *shrinker = file->private_data;
+	unsigned long nr_to_scan = 0, ino;
+	struct shrink_control sc = {
+		.gfp_mask = GFP_KERNEL,
+	};
+	struct mem_cgroup *memcg = NULL;
+	int nid;
+	char kbuf[72];
+	int read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1);
+	ssize_t ret;
+
+	if (copy_from_user(kbuf, buf, read_len))
+		return -EFAULT;
+	kbuf[read_len] = '\0';
+
+	if (sscanf(kbuf, "%lu %d %lu", &ino, &nid, &nr_to_scan) < 2)
+		return -EINVAL;
+
+	if (nid < 0 || nid >= nr_node_ids)
+		return -EINVAL;
+
+	if (nr_to_scan == 0)
+		return size;
+
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
+		memcg = mem_cgroup_get_from_ino(ino);
+		if (!memcg || IS_ERR(memcg))
+			return -ENOENT;
+
+		if (!mem_cgroup_online(memcg)) {
+			mem_cgroup_put(memcg);
+			return -ENOENT;
+		}
+	} else if (ino != 0) {
+		return -EINVAL;
+	}
+
+	ret = down_read_killable(&shrinker_rwsem);
+	if (ret) {
+		mem_cgroup_put(memcg);
+		return ret;
+	}
+
+	sc.nid = nid;
+	sc.memcg = memcg;
+	sc.nr_to_scan = nr_to_scan;
+	sc.nr_scanned = nr_to_scan;
+
+	shrinker->scan_objects(shrinker, &sc);
+
+	up_read(&shrinker_rwsem);
+	mem_cgroup_put(memcg);
+
+	return size;
+}
+
+static const struct file_operations shrinker_debugfs_scan_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = shrinker_debugfs_scan_open,
+	.write	 = shrinker_debugfs_scan_write,
+};
+
 int shrinker_debugfs_add(struct shrinker *shrinker)
 {
 	struct dentry *entry;
@@ -128,6 +200,8 @@ int shrinker_debugfs_add(struct shrinker *shrinker)
 
 	debugfs_create_file("count", 0220, entry, shrinker,
 			    &shrinker_debugfs_count_fops);
+	debugfs_create_file("scan", 0440, entry, shrinker,
+			    &shrinker_debugfs_scan_fops);
 	return 0;
 }
 
-- 
2.35.3