Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Chuyi Zhou <zhouchuyi@bytedance.com>
To:     hannes@cmpxchg.org, mhocko@kernel.org, roman.gushchin@linux.dev,
        ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
        muchun.song@linux.dev
Cc:     bpf@vger.kernel.org, linux-kernel@vger.kernel.org,
        wuyun.abel@bytedance.com, robin.lu@bytedance.com,
        Chuyi Zhou <zhouchuyi@bytedance.com>
Subject: [RFC PATCH 1/2] mm, oom: Introduce bpf_select_task
Date:   Fri,  4 Aug 2023 17:38:03 +0800
Message-Id: <20230804093804.47039-2-zhouchuyi@bytedance.com>
In-Reply-To: <20230804093804.47039-1-zhouchuyi@bytedance.com>
References: <20230804093804.47039-1-zhouchuyi@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This patch adds a new hook bpf_select_task in oom_evaluate_task. It
takes oc and current iterating task as parameters and returns a result
indicating which one is selected by bpf program.

Although bpf_select_task is used to bypass the default method, there are
some existing rules should be obeyed. Specifically, we skip these
"unkillable" tasks(e.g., kthread, MMF_OOM_SKIP, in_vfork()).So we do not
consider tasks with lowest score returned by oom_badness except it was
caused by OOM_SCORE_ADJ_MIN.

If we attach a prog to the hook, the interface is enabled only when we have
successfully chosen at least one valid candidate in previous iteraion. This
is to avoid that we find nothing if bpf program rejects all tasks.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
---
 mm/oom_kill.c | 57 ++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 50 insertions(+), 7 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 612b5597d3af..aec4c55ed49a 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -18,6 +18,7 @@
  *  kernel subsystems and hints as to where to find out what things do.
  */
 
+#include <linux/bpf.h>
 #include <linux/oom.h>
 #include <linux/mm.h>
 #include <linux/err.h>
@@ -210,6 +211,16 @@ long oom_badness(struct task_struct *p, unsigned long totalpages)
 	if (!p)
 		return LONG_MIN;
 
+	/*
+	 * If task is allocating a lot of memory and has been marked to be
+	 * killed first if it triggers an oom, then set points to LONG_MAX.
+	 * It will be selected unless we keep oc->chosen through bpf interface.
+	 */
+	if (oom_task_origin(p)) {
+		task_unlock(p);
+		return LONG_MAX;
+	}
+
 	/*
 	 * Do not even consider tasks which are explicitly marked oom
 	 * unkillable or have been already oom reaped or the are in
@@ -305,8 +316,30 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
 	return CONSTRAINT_NONE;
 }
 
+enum bpf_select_ret {
+	BPF_SELECT_DISABLE,
+	BPF_SELECT_TASK,
+	BPF_SELECT_CHOSEN,
+};
+
+__weak noinline int bpf_select_task(struct oom_control *oc,
+				struct task_struct *task, long badness_points)
+{
+	return BPF_SELECT_DISABLE;
+}
+
+BTF_SET8_START(oom_bpf_fmodret_ids)
+BTF_ID_FLAGS(func, bpf_select_task)
+BTF_SET8_END(oom_bpf_fmodret_ids)
+
+static const struct btf_kfunc_id_set oom_bpf_fmodret_set = {
+	.owner = THIS_MODULE,
+	.set   = &oom_bpf_fmodret_ids,
+};
+
 static int oom_evaluate_task(struct task_struct *task, void *arg)
 {
+	enum bpf_select_ret bpf_ret = BPF_SELECT_DISABLE;
 	struct oom_control *oc = arg;
 	long points;
 
@@ -329,17 +362,23 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 		goto abort;
 	}
 
+	points = oom_badness(task, oc->totalpages);
+
 	/*
-	 * If task is allocating a lot of memory and has been marked to be
-	 * killed first if it triggers an oom, then select it.
+	 * Do not consider tasks with lowest score value except it was caused
+	 * by OOM_SCORE_ADJ_MIN. Give these tasks a chance to be selected by
+	 * bpf interface.
 	 */
-	if (oom_task_origin(task)) {
-		points = LONG_MAX;
+	if (points == LONG_MIN && task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN)
+		goto next;
+
+	if (oc->chosen)
+		bpf_ret = bpf_select_task(oc, task, points);
+
+	if (bpf_ret == BPF_SELECT_TASK)
 		goto select;
-	}
 
-	points = oom_badness(task, oc->totalpages);
-	if (points == LONG_MIN || points < oc->chosen_points)
+	if (bpf_ret == BPF_SELECT_CHOSEN || points == LONG_MIN || points < oc->chosen_points)
 		goto next;
 
 select:
@@ -732,10 +771,14 @@ static struct ctl_table vm_oom_kill_table[] = {
 
 static int __init oom_init(void)
 {
+	int err;
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
 #ifdef CONFIG_SYSCTL
 	register_sysctl_init("vm", vm_oom_kill_table);
 #endif
+	err = register_btf_fmodret_id_set(&oom_bpf_fmodret_set);
+	if (err)
+		pr_warn("error while registering oom fmodret entrypoints: %d", err);
 	return 0;
 }
 subsys_initcall(oom_init)
-- 
2.20.1