tools/bpf: Add runqslower tool to tools/bpf

Convert one of BCC tools (runqslower [0]) to BPF CO-RE + libbpf. It matches
its BCC-based counterpart 1-to-1, supporting all the same parameters and
functionality.

runqslower tool utilizes BPF skeleton, auto-generated from BPF object file,
as well as memory-mapped interface to global (read-only, in this case) data.
Its Makefile also ensures auto-generation of "relocatable" vmlinux.h, which is
necessary for BTF-typed raw tracepoints with direct memory access.

  [0] https://github.com/iovisor/bcc/blob/11bf5d02c895df9646c117c713082eb192825293/tools/runqslower.py

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200113073143.1779940-6-andriin@fb.com

1 files changed, 100 insertions, 0 deletions

diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
new file mode 100644
index 000000000000..623cce4d37f5
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include "vmlinux.h"
+#include <bpf_helpers.h>
+#include "runqslower.h"
+
+#define TASK_RUNNING 0
+
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
+const volatile __u64 min_us = 0;
+const volatile pid_t targ_pid = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 10240);
+	__type(key, u32);
+	__type(value, u64);
+} start SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u32));
+} events SEC(".maps");
+
+/* record enqueue timestamp */
+__always_inline
+static int trace_enqueue(u32 tgid, u32 pid)
+{
+	u64 ts;
+
+	if (!pid || (targ_pid && targ_pid != pid))
+		return 0;
+
+	ts = bpf_ktime_get_ns();
+	bpf_map_update_elem(&start, &pid, &ts, 0);
+	return 0;
+}
+
+SEC("tp_btf/sched_wakeup")
+int handle__sched_wakeup(u64 *ctx)
+{
+	/* TP_PROTO(struct task_struct *p) */
+	struct task_struct *p = (void *)ctx[0];
+
+	return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_wakeup_new")
+int handle__sched_wakeup_new(u64 *ctx)
+{
+	/* TP_PROTO(struct task_struct *p) */
+	struct task_struct *p = (void *)ctx[0];
+
+	return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_switch")
+int handle__sched_switch(u64 *ctx)
+{
+	/* TP_PROTO(bool preempt, struct task_struct *prev,
+	 *	    struct task_struct *next)
+	 */
+	struct task_struct *prev = (struct task_struct *)ctx[1];
+	struct task_struct *next = (struct task_struct *)ctx[2];
+	struct event event = {};
+	u64 *tsp, delta_us;
+	long state;
+	u32 pid;
+
+	/* ivcsw: treat like an enqueue event and store timestamp */
+	if (prev->state == TASK_RUNNING)
+		trace_enqueue(prev->tgid, prev->pid);
+
+	pid = next->pid;
+
+	/* fetch timestamp and calculate delta */
+	tsp = bpf_map_lookup_elem(&start, &pid);
+	if (!tsp)
+		return 0;   /* missed enqueue */
+
+	delta_us = (bpf_ktime_get_ns() - *tsp) / 1000;
+	if (min_us && delta_us <= min_us)
+		return 0;
+
+	event.pid = pid;
+	event.delta_us = delta_us;
+	bpf_get_current_comm(&event.task, sizeof(event.task));
+
+	/* output */
+	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
+			      &event, sizeof(event));
+
+	bpf_map_delete_elem(&start, &pid);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";