linux-kernel - [PATCH v2 2/3] sched_ext: Provide scx_bpf_remote

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250804112743.711816-3-christian.loehle@arm.com>
Date: Mon,  4 Aug 2025 12:27:42 +0100
From: Christian Loehle <christian.loehle@....com>
To: tj@...nel.org,
	arighi@...dia.com,
	void@...ifault.com
Cc: linux-kernel@...r.kernel.org,
	sched-ext@...ts.linux.dev,
	changwoo@...lia.com,
	hodgesd@...a.com,
	mingo@...hat.com,
	peterz@...radead.org,
	Christian Loehle <christian.loehle@....com>
Subject: [PATCH v2 2/3] sched_ext: Provide scx_bpf_remote_curr()

Provide scx_bpf_remote_curr() as a way for scx schedulers to
check the curr task of a remote rq, without assuming its lock
is held.

Many scx schedulers make use of scx_bpf_cpu_rq() to check a
remote curr (e.g. to see if it should be preempted). This is
problematic because scx_bpf_cpu_rq() provides access to all
fields of struct rq, most of which aren't safe to use without
holding the associated rq lock.

Signed-off-by: Christian Loehle <christian.loehle@....com>
---
 kernel/sched/ext.c                       | 24 ++++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  1 +
 2 files changed, 25 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 3ea3f0f18030..1d9d9cbed0aa 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7426,6 +7426,29 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
 	return cpu_rq(cpu);
 }

+struct task_struct *bpf_task_acquire(struct task_struct *p);
+
+/**
+ * scx_bpf_remote_curr - Fetch the curr of a rq without acquiring its rq lock
+ * @cpu: CPU of the rq
+ *
+ * Increments the refcount of the task_struct which needs to be released later.
+ */
+__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)
+{
+	struct task_struct *p;
+
+	if (!kf_cpu_valid(cpu, NULL))
+		return NULL;
+
+	rcu_read_lock();
+	p = cpu_rq(cpu)->curr;
+	if (p)
+		p = bpf_task_acquire(p);
+	rcu_read_unlock();
+	return p;
+}
+
 /**
  * scx_bpf_task_cgroup - Return the sched cgroup of a task
  * @p: task of interest
@@ -7590,6 +7613,7 @@ BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
 BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_cpu_rq, KF_RET_NULL)
+BTF_ID_FLAGS(func, scx_bpf_remote_curr, KF_RET_NULL | KF_ACQUIRE)
 #ifdef CONFIG_CGROUP_SCHED
 BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE)
 #endif
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index d4e21558e982..e5d4ef124532 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -91,6 +91,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
 bool scx_bpf_task_running(const struct task_struct *p) __ksym;
 s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
 struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
+struct task_struct *scx_bpf_remote_curr(s32 cpu) __ksym;
 struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak;
 u64 scx_bpf_now(void) __ksym __weak;
 void scx_bpf_events(struct scx_event_stats *events, size_t events__sz) __ksym __weak;
--
2.34.1