linux-kernel - [PATCH 6/8] sched_ext: Add scx_cgroup_enabled to gate cgroup operations and fix scx_tg

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: <20240923190020.1446325-7-tj@kernel.org>
Date: Mon, 23 Sep 2024 08:59:33 -1000
From: Tejun Heo <tj@...nel.org>
To: void@...ifault.com
Cc: kernel-team@...a.com,
	linux-kernel@...r.kernel.org,
	sched-ext@...a.com,
	aboorvad@...ux.ibm.com,
	Tejun Heo <tj@...nel.org>
Subject: [PATCH 6/8] sched_ext: Add scx_cgroup_enabled to gate cgroup operations and fix scx_tg_online()

If the BPF scheduler does not implement ops.cgroup_init(), scx_tg_online()
didn't set SCX_TG_INITED which meant that ops.cgroup_exit(), even if
implemented, won't be called from scx_tg_offline(). This is because
SCX_HAS_OP(cgroupt_init) is used to test both whether SCX cgroup operations
are enabled and ops.cgroup_init() exists.

Fix it by introducing a separate bool scx_cgroup_enabled to gate cgroup
operations and use SCX_HAS_OP(cgroup_init) only to test whether
ops.cgroup_init() exists. Make all cgroup operations consistently use
scx_cgroup_enabled to test whether cgroup operations are enabled.
scx_cgroup_enabled is added instead of using scx_enabled() to ease planned
locking updates.

Signed-off-by: Tejun Heo <tj@...nel.org>
---
 kernel/sched/ext.c | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index feb7c620f9c6..06dc1011312d 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3689,6 +3689,7 @@ bool scx_can_stop_tick(struct rq *rq)
 #ifdef CONFIG_EXT_GROUP_SCHED
 
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
+static bool scx_cgroup_enabled;
 static bool cgroup_warned_missing_weight;
 static bool cgroup_warned_missing_idle;
 
@@ -3708,8 +3709,7 @@ static void scx_cgroup_warn_missing_weight(struct task_group *tg)
 
 static void scx_cgroup_warn_missing_idle(struct task_group *tg)
 {
-	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
-	    cgroup_warned_missing_idle)
+	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
 		return;
 
 	if (!tg->idle)
@@ -3730,15 +3730,18 @@ int scx_tg_online(struct task_group *tg)
 
 	scx_cgroup_warn_missing_weight(tg);
 
-	if (SCX_HAS_OP(cgroup_init)) {
-		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
+	if (scx_cgroup_enabled) {
+		if (SCX_HAS_OP(cgroup_init)) {
+			struct scx_cgroup_init_args args =
+				{ .weight = tg->scx_weight };
 
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
-				      tg->css.cgroup, &args);
-		if (!ret)
+			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+					      tg->css.cgroup, &args);
+			if (ret)
+				ret = ops_sanitize_err("cgroup_init", ret);
+		}
+		if (ret == 0)
 			tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED;
-		else
-			ret = ops_sanitize_err("cgroup_init", ret);
 	} else {
 		tg->scx_flags |= SCX_TG_ONLINE;
 	}
@@ -3769,7 +3772,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 	/* released in scx_finish/cancel_attach() */
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (!scx_enabled())
+	if (!scx_cgroup_enabled)
 		return 0;
 
 	cgroup_taskset_for_each(p, css, tset) {
@@ -3812,7 +3815,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 
 void scx_move_task(struct task_struct *p)
 {
-	if (!scx_enabled())
+	if (!scx_cgroup_enabled)
 		return;
 
 	/*
@@ -3848,7 +3851,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
 	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
-	if (!scx_enabled())
+	if (!scx_cgroup_enabled)
 		goto out_unlock;
 
 	cgroup_taskset_for_each(p, css, tset) {
@@ -3865,7 +3868,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 {
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (tg->scx_weight != weight) {
+	if (scx_cgroup_enabled && tg->scx_weight != weight) {
 		if (SCX_HAS_OP(cgroup_set_weight))
 			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
 				    tg_cgrp(tg), weight);
@@ -4037,6 +4040,9 @@ static void scx_cgroup_exit(void)
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
+	WARN_ON_ONCE(!scx_cgroup_enabled);
+	scx_cgroup_enabled = false;
+
 	/*
 	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and exit all the inited ones, all online cgroups are exited.
@@ -4112,6 +4118,9 @@ static int scx_cgroup_init(void)
 	}
 	rcu_read_unlock();
 
+	WARN_ON_ONCE(scx_cgroup_enabled);
+	scx_cgroup_enabled = true;
+
 	return 0;
 }
 
-- 
2.46.0