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;
Date:   Fri, 25 Feb 2022 15:43:35 -0800
In-Reply-To: <20220225234339.2386398-1-haoluo@google.com>
Message-Id: <20220225234339.2386398-6-haoluo@google.com>
Mime-Version: 1.0
References: <20220225234339.2386398-1-haoluo@google.com>
Subject: [PATCH bpf-next v1 5/9] cgroup: Sleepable cgroup tracepoints.
From:   Hao Luo <haoluo@google.com>
To:     Alexei Starovoitov <ast@kernel.org>,
        Andrii Nakryiko <andrii@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>
Cc:     Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
        Yonghong Song <yhs@fb.com>, KP Singh <kpsingh@kernel.org>,
        Shakeel Butt <shakeelb@google.com>,
        Joe Burton <jevburton.kernel@gmail.com>,
        Tejun Heo <tj@kernel.org>, joshdon@google.com, sdf@google.com,
        bpf@vger.kernel.org, linux-kernel@vger.kernel.org,
        Hao Luo <haoluo@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Add two new sleepable tracepoints in cgroup: cgroup_mkdir_s and
cgroup_rmdir_s. The suffix _s means they are in a sleepable context.
These two tracepoints don't need full cgroup paths, they don't have
to live in atomic context. These two tracepoints are also called without
holding cgroup_mutex.

They can be used for bpf to monitor cgroup creation and deletion. Bpf
sleepable programs can attach to these two tracepoints and create
corresponding directories in bpffs. The created directories don't need
the cgroup paths, cgroup id is sufficient to identify the cgroup. Once
the bpffs directories have been created, the bpf prog can further pin
bpf objects inside the directories and allow users to read the pinned
objects.

This serves a way to extend the fixed cgroup interface.

Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Hao Luo <haoluo@google.com>
---
 include/trace/events/cgroup.h | 45 +++++++++++++++++++++++++++++++++++
 kernel/cgroup/cgroup.c        |  5 ++++
 2 files changed, 50 insertions(+)

diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
index dd7d7c9efecd..4483a7d6c43a 100644
--- a/include/trace/events/cgroup.h
+++ b/include/trace/events/cgroup.h
@@ -204,6 +204,51 @@ DEFINE_EVENT(cgroup_event, cgroup_notify_frozen,
 	TP_ARGS(cgrp, path, val)
 );
 
+/*
+ * The following tracepoints are supposed to be called in a sleepable context.
+ */
+DECLARE_EVENT_CLASS(cgroup_sleepable_tp,
+
+	TP_PROTO(struct cgroup *cgrp),
+
+	TP_ARGS(cgrp),
+
+	TP_STRUCT__entry(
+		__field(	int,		root			)
+		__field(	int,		level			)
+		__field(	u64,		id			)
+	),
+
+	TP_fast_assign(
+		__entry->root = cgrp->root->hierarchy_id;
+		__entry->id = cgroup_id(cgrp);
+		__entry->level = cgrp->level;
+	),
+
+	TP_printk("root=%d id=%llu level=%d",
+		  __entry->root, __entry->id, __entry->level)
+);
+
+#ifdef DEFINE_EVENT_SLEEPABLE
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)		\
+	DEFINE_EVENT_SLEEPABLE(template, call, PARAMS(proto), PARAMS(args))
+#endif
+
+DEFINE_EVENT(cgroup_sleepable_tp, cgroup_mkdir_s,
+
+	TP_PROTO(struct cgroup *cgrp),
+
+	TP_ARGS(cgrp)
+);
+
+DEFINE_EVENT(cgroup_sleepable_tp, cgroup_rmdir_s,
+
+	TP_PROTO(struct cgroup *cgrp),
+
+	TP_ARGS(cgrp)
+);
+
 #endif /* _TRACE_CGROUP_H */
 
 /* This part must be outside protection */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9d05c3ca2d5e..f14ab00d9ef5 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5535,6 +5535,8 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 	cgroup_destroy_locked(cgrp);
 out_unlock:
 	cgroup_kn_unlock(parent_kn);
+	if (!ret)
+		trace_cgroup_mkdir_s(cgrp);
 	return ret;
 }
 
@@ -5725,6 +5727,9 @@ int cgroup_rmdir(struct kernfs_node *kn)
 		TRACE_CGROUP_PATH(rmdir, cgrp);
 
 	cgroup_kn_unlock(kn);
+
+	if (!ret)
+		trace_cgroup_rmdir_s(cgrp);
 	return ret;
 }
 
-- 
2.35.1.574.g5d30c73bfb-goog