e3edfdec04
the first microbenchmark does
fd=open("/proc/self/comm");
for() {
write(fd, "test");
}
and on 4 cpus in parallel:
writes per sec
base (no tracepoints, no kprobes) 930k
with kprobe at __set_task_comm() 420k
with tracepoint at task:task_rename 730k
For kprobe + full bpf program manully fetches oldcomm, newcomm via bpf_probe_read.
For tracepint bpf program does nothing, since arguments are copied by tracepoint.
2nd microbenchmark does:
fd=open("/dev/urandom");
for() {
read(fd, buf);
}
and on 4 cpus in parallel:
reads per sec
base (no tracepoints, no kprobes) 300k
with kprobe at urandom_read() 279k
with tracepoint at random:urandom_read 290k
bpf progs attached to kprobe and tracepoint are noop.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
42 lines
1.0 KiB
C
42 lines
1.0 KiB
C
/* Copyright (c) 2016 Facebook
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#include <linux/version.h>
|
|
#include <linux/ptrace.h>
|
|
#include <uapi/linux/bpf.h>
|
|
#include "bpf_helpers.h"
|
|
|
|
#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
|
|
|
|
SEC("kprobe/__set_task_comm")
|
|
int prog(struct pt_regs *ctx)
|
|
{
|
|
struct signal_struct *signal;
|
|
struct task_struct *tsk;
|
|
char oldcomm[16] = {};
|
|
char newcomm[16] = {};
|
|
u16 oom_score_adj;
|
|
u32 pid;
|
|
|
|
tsk = (void *)PT_REGS_PARM1(ctx);
|
|
|
|
pid = _(tsk->pid);
|
|
bpf_probe_read(oldcomm, sizeof(oldcomm), &tsk->comm);
|
|
bpf_probe_read(newcomm, sizeof(newcomm), (void *)PT_REGS_PARM2(ctx));
|
|
signal = _(tsk->signal);
|
|
oom_score_adj = _(signal->oom_score_adj);
|
|
return 0;
|
|
}
|
|
|
|
SEC("kprobe/urandom_read")
|
|
int prog2(struct pt_regs *ctx)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
char _license[] SEC("license") = "GPL";
|
|
u32 _version SEC("version") = LINUX_VERSION_CODE;
|