3 files changed, 258 insertions, 0 deletions

diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
new file mode 100644
index 000000000..26004f0c5
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (c) 2020 Facebook */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_tracing.h>
+#include "pid_iter.h"
+
+/* keep in sync with the definition in main.h */
+enum bpf_obj_type {
+	BPF_OBJ_UNKNOWN,
+	BPF_OBJ_PROG,
+	BPF_OBJ_MAP,
+	BPF_OBJ_LINK,
+	BPF_OBJ_BTF,
+};
+
+struct bpf_perf_link___local {
+	struct bpf_link link;
+	struct file *perf_file;
+} __attribute__((preserve_access_index));
+
+struct perf_event___local {
+	u64 bpf_cookie;
+} __attribute__((preserve_access_index));
+
+enum bpf_link_type___local {
+	BPF_LINK_TYPE_PERF_EVENT___local = 7,
+};
+
+extern const void bpf_link_fops __ksym;
+extern const void bpf_map_fops __ksym;
+extern const void bpf_prog_fops __ksym;
+extern const void btf_fops __ksym;
+
+const volatile enum bpf_obj_type obj_type = BPF_OBJ_UNKNOWN;
+
+static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type)
+{
+	switch (type) {
+	case BPF_OBJ_PROG:
+		return BPF_CORE_READ((struct bpf_prog *)ent, aux, id);
+	case BPF_OBJ_MAP:
+		return BPF_CORE_READ((struct bpf_map *)ent, id);
+	case BPF_OBJ_BTF:
+		return BPF_CORE_READ((struct btf *)ent, id);
+	case BPF_OBJ_LINK:
+		return BPF_CORE_READ((struct bpf_link *)ent, id);
+	default:
+		return 0;
+	}
+}
+
+/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */
+static __u64 get_bpf_cookie(struct bpf_link *link)
+{
+	struct bpf_perf_link___local *perf_link;
+	struct perf_event___local *event;
+
+	perf_link = container_of(link, struct bpf_perf_link___local, link);
+	event = BPF_CORE_READ(perf_link, perf_file, private_data);
+	return BPF_CORE_READ(event, bpf_cookie);
+}
+
+SEC("iter/task_file")
+int iter(struct bpf_iter__task_file *ctx)
+{
+	struct file *file = ctx->file;
+	struct task_struct *task = ctx->task;
+	struct pid_iter_entry e;
+	const void *fops;
+
+	if (!file || !task)
+		return 0;
+
+	switch (obj_type) {
+	case BPF_OBJ_PROG:
+		fops = &bpf_prog_fops;
+		break;
+	case BPF_OBJ_MAP:
+		fops = &bpf_map_fops;
+		break;
+	case BPF_OBJ_BTF:
+		fops = &btf_fops;
+		break;
+	case BPF_OBJ_LINK:
+		fops = &bpf_link_fops;
+		break;
+	default:
+		return 0;
+	}
+
+	if (file->f_op != fops)
+		return 0;
+
+	__builtin_memset(&e, 0, sizeof(e));
+	e.pid = task->tgid;
+	e.id = get_obj_id(file->private_data, obj_type);
+
+	if (obj_type == BPF_OBJ_LINK &&
+	    bpf_core_enum_value_exists(enum bpf_link_type___local,
+				       BPF_LINK_TYPE_PERF_EVENT___local)) {
+		struct bpf_link *link = (struct bpf_link *) file->private_data;
+
+		if (link->type == bpf_core_enum_value(enum bpf_link_type___local,
+						      BPF_LINK_TYPE_PERF_EVENT___local)) {
+			e.has_bpf_cookie = true;
+			e.bpf_cookie = get_bpf_cookie(link);
+		}
+	}
+
+	bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm),
+				  task->group_leader->comm);
+	bpf_seq_write(ctx->meta->seq, &e, sizeof(e));
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h
new file mode 100644
index 000000000..bbb570d4c
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/pid_iter.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2020 Facebook */
+#ifndef __PID_ITER_H
+#define __PID_ITER_H
+
+struct pid_iter_entry {
+	__u32 id;
+	int pid;
+	__u64 bpf_cookie;
+	bool has_bpf_cookie;
+	char comm[16];
+};
+
+#endif
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
new file mode 100644
index 000000000..2f80edc68
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2020 Facebook
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct bpf_perf_event_value___local {
+	__u64 counter;
+	__u64 enabled;
+	__u64 running;
+} __attribute__((preserve_access_index));
+
+/* map of perf event fds, num_cpu * num_metric entries */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(int));
+} events SEC(".maps");
+
+/* readings at fentry */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value___local));
+} fentry_readings SEC(".maps");
+
+/* accumulated readings */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value___local));
+} accum_readings SEC(".maps");
+
+/* sample counts, one per cpu */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+} counts SEC(".maps");
+
+const volatile __u32 num_cpu = 1;
+const volatile __u32 num_metric = 1;
+#define MAX_NUM_MATRICS 4
+
+SEC("fentry/XXX")
+int BPF_PROG(fentry_XXX)
+{
+	struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS];
+	u32 key = bpf_get_smp_processor_id();
+	u32 i;
+
+	/* look up before reading, to reduce error */
+	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+		u32 flag = i;
+
+		ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag);
+		if (!ptrs[i])
+			return 0;
+	}
+
+	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+		struct bpf_perf_event_value___local reading;
+		int err;
+
+		err = bpf_perf_event_read_value(&events, key, (void *)&reading,
+						sizeof(reading));
+		if (err)
+			return 0;
+		*(ptrs[i]) = reading;
+		key += num_cpu;
+	}
+
+	return 0;
+}
+
+static inline void
+fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after)
+{
+	struct bpf_perf_event_value___local *before, diff;
+
+	before = bpf_map_lookup_elem(&fentry_readings, &id);
+	/* only account samples with a valid fentry_reading */
+	if (before && before->counter) {
+		struct bpf_perf_event_value___local *accum;
+
+		diff.counter = after->counter - before->counter;
+		diff.enabled = after->enabled - before->enabled;
+		diff.running = after->running - before->running;
+
+		accum = bpf_map_lookup_elem(&accum_readings, &id);
+		if (accum) {
+			accum->counter += diff.counter;
+			accum->enabled += diff.enabled;
+			accum->running += diff.running;
+		}
+	}
+}
+
+SEC("fexit/XXX")
+int BPF_PROG(fexit_XXX)
+{
+	struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS];
+	u32 cpu = bpf_get_smp_processor_id();
+	u32 i, zero = 0;
+	int err;
+	u64 *count;
+
+	/* read all events before updating the maps, to reduce error */
+	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+		err = bpf_perf_event_read_value(&events, cpu + i * num_cpu,
+						(void *)(readings + i),
+						sizeof(*readings));
+		if (err)
+			return 0;
+	}
+	count = bpf_map_lookup_elem(&counts, &zero);
+	if (count) {
+		*count += 1;
+		for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++)
+			fexit_update_maps(i, &readings[i]);
+	}
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";