5 files changed, 385 insertions, 0 deletions
diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore
new file mode 100644
index 000000000000..90a456a2a72f
--- /dev/null
+++ b/tools/bpf/runqslower/.gitignore
@@ -0,0 +1 @@
+/.output
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
new file mode 100644
index 000000000000..0c021352beed
--- /dev/null
+++ b/tools/bpf/runqslower/Makefile
@@ -0,0 +1,84 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+OUTPUT := .output
+CLANG ?= clang
+LLC ?= llc
+LLVM_STRIP ?= llvm-strip
+DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+LIBBPF_SRC := $(abspath ../../lib/bpf)
+BPFOBJ := $(OUTPUT)/libbpf.a
+BPF_INCLUDE := $(OUTPUT)
+INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib)
+CFLAGS := -g -Wall
+
+# Try to detect best kernel BTF source
+KERNEL_REL := $(shell uname -r)
+VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL)
+VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword			       \
+					  $(wildcard $(VMLINUX_BTF_PATHS))))
+
+abs_out := $(abspath $(OUTPUT))
+ifeq ($(V),1)
+Q =
+msg =
+else
+Q = @
+msg = @printf '  %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
+endif
+
+.DELETE_ON_ERROR:
+
+.PHONY: all clean runqslower
+all: runqslower
+
+runqslower: $(OUTPUT)/runqslower
+
+clean:
+	$(call msg,CLEAN)
+	$(Q)rm -rf $(OUTPUT) runqslower
+
+$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
+	$(call msg,BINARY,$@)
+	$(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@
+
+$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h	      \
+			$(OUTPUT)/runqslower.bpf.o
+
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+
+$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
+	$(call msg,GEN-SKEL,$@)
+	$(Q)$(BPFTOOL) gen skeleton $< > $@
+
+$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
+	$(call msg,BPF,$@)
+	$(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES)			      \
+		 -c $(filter %.c,$^) -o $@ &&				      \
+	$(LLVM_STRIP) -g $@
+
+$(OUTPUT)/%.o: %.c | $(OUTPUT)
+	$(call msg,CC,$@)
+	$(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $(OUTPUT)
+
+$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL)
+	$(call msg,GEN,$@)
+	$(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \
+		echo "Couldn't find kernel BTF; set VMLINUX_BTF to"	       \
+			"specify its location." >&2;			       \
+		exit 1;\
+	fi
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
+
+$(BPFOBJ): | $(OUTPUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)			       \
+		    OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+
+$(DEFAULT_BPFTOOL):
+	$(Q)$(MAKE) $(submake_extras) -C ../bpftool			      \
+		    prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
new file mode 100644
index 000000000000..48a39f72fadf
--- /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/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";
diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c
new file mode 100644
index 000000000000..d89715844952
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+#include <argp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <time.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "runqslower.h"
+#include "runqslower.skel.h"
+
+struct env {
+	pid_t pid;
+	__u64 min_us;
+	bool verbose;
+} env = {
+	.min_us = 10000,
+};
+
+const char *argp_program_version = "runqslower 0.1";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"runqslower    Trace long process scheduling delays.\n"
+"              For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n"
+"\n"
+"This script traces high scheduling delays between tasks being\n"
+"ready to run and them running on CPU after that.\n"
+"\n"
+"USAGE: runqslower [-p PID] [min_us]\n"
+"\n"
+"EXAMPLES:\n"
+"    runqslower         # trace run queue latency higher than 10000 us (default)\n"
+"    runqslower 1000    # trace run queue latency higher than 1000 us\n"
+"    runqslower -p 123  # trace pid 123 only\n";
+
+static const struct argp_option opts[] = {
+	{ "pid", 'p', "PID", 0, "Process PID to trace"},
+	{ "verbose", 'v', NULL, 0, "Verbose debug output" },
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	static int pos_args;
+	int pid;
+	long long min_us;
+
+	switch (key) {
+	case 'v':
+		env.verbose = true;
+		break;
+	case 'p':
+		errno = 0;
+		pid = strtol(arg, NULL, 10);
+		if (errno || pid <= 0) {
+			fprintf(stderr, "Invalid PID: %s\n", arg);
+			argp_usage(state);
+		}
+		env.pid = pid;
+		break;
+	case ARGP_KEY_ARG:
+		if (pos_args++) {
+			fprintf(stderr,
+				"Unrecognized positional argument: %s\n", arg);
+			argp_usage(state);
+		}
+		errno = 0;
+		min_us = strtoll(arg, NULL, 10);
+		if (errno || min_us <= 0) {
+			fprintf(stderr, "Invalid delay (in us): %s\n", arg);
+			argp_usage(state);
+		}
+		env.min_us = min_us;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+int libbpf_print_fn(enum libbpf_print_level level,
+		    const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+	struct rlimit rlim_new = {
+		.rlim_cur	= RLIM_INFINITY,
+		.rlim_max	= RLIM_INFINITY,
+	};
+
+	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
+{
+	const struct event *e = data;
+	struct tm *tm;
+	char ts[32];
+	time_t t;
+
+	time(&t);
+	tm = localtime(&t);
+	strftime(ts, sizeof(ts), "%H:%M:%S", tm);
+	printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us);
+}
+
+void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt)
+{
+	printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu);
+}
+
+int main(int argc, char **argv)
+{
+	static const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+	};
+	struct perf_buffer_opts pb_opts;
+	struct perf_buffer *pb = NULL;
+	struct runqslower_bpf *obj;
+	int err;
+
+	err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+	if (err)
+		return err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	err = bump_memlock_rlimit();
+	if (err) {
+		fprintf(stderr, "failed to increase rlimit: %d", err);
+		return 1;
+	}
+
+	obj = runqslower_bpf__open();
+	if (!obj) {
+		fprintf(stderr, "failed to open and/or load BPF object\n");
+		return 1;
+	}
+
+	/* initialize global data (filtering options) */
+	obj->rodata->targ_pid = env.pid;
+	obj->rodata->min_us = env.min_us;
+
+	err = runqslower_bpf__load(obj);
+	if (err) {
+		fprintf(stderr, "failed to load BPF object: %d\n", err);
+		goto cleanup;
+	}
+
+	err = runqslower_bpf__attach(obj);
+	if (err) {
+		fprintf(stderr, "failed to attach BPF programs\n");
+		goto cleanup;
+	}
+
+	printf("Tracing run queue latency higher than %llu us\n", env.min_us);
+	printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)");
+
+	pb_opts.sample_cb = handle_event;
+	pb_opts.lost_cb = handle_lost_events;
+	pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts);
+	err = libbpf_get_error(pb);
+	if (err) {
+		pb = NULL;
+		fprintf(stderr, "failed to open perf buffer: %d\n", err);
+		goto cleanup;
+	}
+
+	while ((err = perf_buffer__poll(pb, 100)) >= 0)
+		;
+	printf("Error polling perf buffer: %d\n", err);
+
+cleanup:
+	perf_buffer__free(pb);
+	runqslower_bpf__destroy(obj);
+
+	return err != 0;
+}
diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h
new file mode 100644
index 000000000000..9db225425e5f
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __RUNQSLOWER_H
+#define __RUNQSLOWER_H
+
+#define TASK_COMM_LEN 16
+
+struct event {
+	char task[TASK_COMM_LEN];
+	__u64 delta_us;
+	pid_t pid;
+};
+
+#endif /* __RUNQSLOWER_H */