lkml.org 
[lkml]   [2018]   [Jul]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v2] perf build: Fix installation directory for bpf
Em Tue, Jul 31, 2018 at 09:32:54AM +0200, Thomas Richter escreveu:
> Output after using command ./perf test -Fv 40:
> echo '...[bpf-program-source]...' | /usr/bin/clang ... \
> -I/root/lib/perf/include/bpf ...
> ^^^^^^^^^^^^
> ...
> [root@p23lp27 perf]# ./perf test -F 40
> 40: BPF filter :
> 40.1: Basic BPF filtering : Ok
> 40.2: BPF pinning : Ok
> 40.3: BPF prologue generation : Ok
> 40.4: BPF relocation checker : Ok
> [root@p23lp27 perf]#

So, testing it:

[root@jouet perf]# cat tools/perf/examples/bpf/5sec.c
// SPDX-License-Identifier: GPL-2.0
/*
Description:

. Disable strace like syscall tracing (--no-syscalls), or try tracing
just some (-e *sleep).

. Attach a filter function to a kernel function, returning when it should
be considered, i.e. appear on the output.

. Run it system wide, so that any sleep of >= 5 seconds and < than 6
seconds gets caught.

. Ask for callgraphs using DWARF info, so that userspace can be unwound

. While this is running, run something like "sleep 5s".

. If we decide to add tv_nsec as well, then it becomes:

int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)

I.e. add where it comes from (rqtp->tv_nsec) and where it will be
accessible in the function body (nsec)

# perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
hrtimer_nanosleep ([kernel.kallsyms])
__x64_sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
__GI___nanosleep (/usr/lib64/libc-2.26.so)
rpl_nanosleep (/usr/bin/sleep)
xnanosleep (/usr/bin/sleep)
main (/usr/bin/sleep)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/sleep)
^C#

Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
*/

#include <bpf.h>

int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
{
return sec == 5;
}

license(GPL);
[root@jouet perf]# perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c
0.000 perf_bpf_probe:hrtimer_nanosleep:(ffffffff9911efe0) tv_sec=5
3145.238 perf_bpf_probe:hrtimer_nanosleep:(ffffffff9911efe0) tv_sec=5
^C[root@jouet perf]#

After it works just the same, thanks, applying.

I need to get the above testing process hooked up in 'perf test', so
that besides adding that -I/root/lib/perf/include/bpf we actually _try_
to include something from there from the /root/lib/perf/examples/bpf/
bpf example scripts.

- Arnaldo

\
 
 \ /
  Last update: 2018-07-31 15:21    [W:0.156 / U:0.376 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site