Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
Sender: Namhyung Kim <namhyung@gmail.com>
From:   Namhyung Kim <namhyung@kernel.org>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@kernel.org>
Cc:     Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Andi Kleen <ak@linux.intel.com>,
        Ian Rogers <irogers@google.com>,
        Song Liu <songliubraving@fb.com>, Hao Luo <haoluo@google.com>,
        bpf@vger.kernel.org, linux-perf-users@vger.kernel.org,
        Blake Jones <blakejones@google.com>
Subject: [PATCH 4/4] perf record: Handle argument change in sched_switch
Date:   Thu, 21 Apr 2022 22:34:01 -0700
Message-Id: <20220422053401.208207-5-namhyung@kernel.org>
In-Reply-To: <20220422053401.208207-1-namhyung@kernel.org>
References: <20220422053401.208207-1-namhyung@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Recently sched_switch tracepoint added a new argument for prev_state,
but it's hard to handle the change in a BPF program.  Instead, we can
check the function prototype in BTF before loading the program.

Thus I make two copies of the tracepoint handler and select one based
on the BTF info.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf_off_cpu.c          | 32 +++++++++++++++
 tools/perf/util/bpf_skel/off_cpu.bpf.c | 55 ++++++++++++++++++++------
 2 files changed, 76 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 89f36229041d..38aeb13d3d25 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -86,6 +86,37 @@ static void off_cpu_finish(void *arg __maybe_unused)
 	off_cpu_bpf__destroy(skel);
 }
 
+/* recent kernel added prev_state arg, so it needs to call the proper function */
+static void check_sched_switch_args(void)
+{
+	const struct btf *btf = bpf_object__btf(skel->obj);
+	const struct btf_type *t1, *t2, *t3;
+	u32 type_id;
+
+	type_id = btf__find_by_name_kind(btf, "bpf_trace_sched_switch",
+					 BTF_KIND_TYPEDEF);
+	if ((s32)type_id < 0)
+		goto old_format;
+
+	t1 = btf__type_by_id(btf, type_id);
+	if (t1 == NULL)
+		goto old_format;
+
+	t2 = btf__type_by_id(btf, t1->type);
+	if (t2 == NULL || !btf_is_ptr(t2))
+		goto old_format;
+
+	t3 = btf__type_by_id(btf, t2->type);
+	if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 4) {
+		/* new format: disable old functions */
+		bpf_program__set_autoload(skel->progs.on_switch3, false);
+		return;
+	}
+
+old_format:
+	bpf_program__set_autoload(skel->progs.on_switch4, false);
+}
+
 int off_cpu_prepare(struct evlist *evlist, struct target *target)
 {
 	int err, fd, i;
@@ -114,6 +145,7 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target)
 	}
 
 	set_max_rlimit();
+	check_sched_switch_args();
 
 	err = off_cpu_bpf__load(skel);
 	if (err) {
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 27425fe361e2..e11e198af86f 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -121,22 +121,13 @@ static inline int can_record(struct task_struct *t, int state)
 	return 1;
 }
 
-SEC("tp_btf/sched_switch")
-int on_switch(u64 *ctx)
+static int on_switch(u64 *ctx, struct task_struct *prev,
+		     struct task_struct *next, int state)
 {
 	__u64 ts;
-	int state;
 	__u32 pid, stack_id;
-	struct task_struct *prev, *next;
 	struct tstamp_data elem, *pelem;
 
-	if (!enabled)
-		return 0;
-
-	prev = (struct task_struct *)ctx[1];
-	next = (struct task_struct *)ctx[2];
-	state = get_task_state(prev);
-
 	ts = bpf_ktime_get_ns();
 
 	if (!can_record(prev, state))
@@ -178,4 +169,46 @@ int on_switch(u64 *ctx)
 	return 0;
 }
 
+SEC("tp_btf/sched_switch")
+int on_switch3(u64 *ctx)
+{
+	struct task_struct *prev, *next;
+	int state;
+
+	if (!enabled)
+		return 0;
+
+	/*
+	 * TP_PROTO(bool preempt, struct task_struct *prev,
+	 *          struct task_struct *next)
+	 */
+	prev = (struct task_struct *)ctx[1];
+	next = (struct task_struct *)ctx[2];
+
+	state = get_task_state(prev);
+
+	return on_switch(ctx, prev, next, state);
+}
+
+SEC("tp_btf/sched_switch")
+int on_switch4(u64 *ctx)
+{
+	struct task_struct *prev, *next;
+	int prev_state;
+
+	if (!enabled)
+		return 0;
+
+	/*
+	 * TP_PROTO(bool preempt, int prev_state,
+	 *          struct task_struct *prev,
+	 *          struct task_struct *next)
+	 */
+	prev = (struct task_struct *)ctx[2];
+	next = (struct task_struct *)ctx[3];
+	prev_state = (int)ctx[1];
+
+	return on_switch(ctx, prev, next, prev_state);
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
-- 
2.36.0.rc2.479.g8af0fa9b8e-goog