Commits · 3df33eff2ba96be4f1535db4f672013d756dc9b1 · Kirill Smelkov / linux

09 Aug, 2016 5 commits

perf stat: Avoid skew when reading events · 3df33eff

Mark Rutland authored Aug 09, 2016

When we don't have a tracee (i.e. we're attaching to a task or CPU),
counters can still be running after our workload finishes, and can still
be running as we read their values. As we read events one-by-one, there
can be arbitrary skew between values of events, even within a group.
This means that ratios within an event group are not reliable.

This skew can be seen if measuring a group of identical events, e.g:

# perf stat -a -C0 -e '{cycles,cycles}' sleep 1

To avoid this, we must stop groups from counting before we read the
values of any constituent events. This patch adds and makes use of a new
disable_counters() helper, which disables group leaders (and thus each
group as a whole). This mirrors the use of enable_counters() for
starting event groups in the absence of a tracee.

Closing a group leader splits the group, and without a disabled group
leader the newly split events will begin counting. Thus to ensure counts
are reliable we must defer closing group leaders until all counts have
been read. To do so this patch removes the event closing logic from the
read_counters() helper, explicitly closes the events using
perf_evlist__close(), which also aids legibility.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1470747869-3567-1-git-send-email-mark.rutland@arm.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3df33eff

perf probe: Fix module name matching · cb3f3378

Konstantin Khlebnikov authored Aug 05, 2016

If module is "module" then dso->short_name is "[module]". Substring
comparing is't enough: "raid10" matches to "[raid1]". This patch also
checks terminating zero in module name.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: http://lkml.kernel.org/r/147039975648.715620.12985971832789032159.stgit@buzzSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

cb3f3378

perf probe: Adjust map->reloc offset when finding kernel symbol from map · 8e34189b

Masami Hiramatsu authored Aug 06, 2016

Adjust map->reloc offset for the unmapped address when finding
alternative symbol address from map, because KASLR can relocate the
kernel symbol address.

The same adjustment has been done when finding appropriate kernel symbol
address from map which was introduced by commit f90acac7 ("perf
probe: Find given address from offline dwarf")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu@linaro.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20160806192948.e366f3fbc4b194de600f8326@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

8e34189b

perf hists: Trim libtraceevent trace_seq buffers · 887fa86d

Arnaldo Carvalho de Melo authored Aug 05, 2016

When we use libtraceevent to format trace event fields into printable
strings to use in hist entries it is important to trim it from the
default 4 KiB it starts with to what is really used, to reduce the
memory footprint, so use realloc(seq.buffer, seq.len + 1) when returning
the seq.buffer formatted with the fields contents.
Reported-and-Tested-by: Wang Nan <wangnan0@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-t3hl7uxmilrkigzmc90rlhk2@git.kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

887fa86d

perf script: Add 'bpf-output' field to usage message · bcdc09af

Brendan Gregg authored Aug 03, 2016

This adds the 'bpf-output' field to the perf script usage message, and docs.
Signed-off-by: Brendan Gregg <bgregg@netflix.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1470192469-11910-4-git-send-email-bgregg@netflix.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

bcdc09af

04 Aug, 2016 1 commit

Merge tag 'perf-core-for-mingo-20160803' of... · f282f7a0

Ingo Molnar authored Aug 04, 2016

Merge tag 'perf-core-for-mingo-20160803' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

New features:

- Add --sample-cpu to 'perf record', to explicitely ask for sampling
  the CPU (Jiri Olsa)

Fixes:

- Fix processing of multi byte chunks in objdump output, fixing
  disassemble processing for annotation on at least ARM64 (Jan Stancek)

- Use SyS_epoll_wait in a BPF 'perf test' entry instead of sys_epoll_wait, that
  is not present in the DWARF info in vmlinux files (Arnaldo Carvalho de Melo)

- Add -wno-shadow when processing files using perl headers, fixing
  the build on Fedora Rawhide and Arch Linux (Namhyung Kim)

Infrastructure changes:

- Annotate prep work to better catch and report errors related to
  using objdump to disassemble DSOs (Arnaldo Carvalho de Melo)

- Add 'alloc', 'scnprintf' and 'and' methods for bitmap processing (Jiri Olsa)

- Add nested output resorting callback in hists processing (Jiri Olsa)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

f282f7a0

03 Aug, 2016 1 commit

perf tests bpf: Use SyS_epoll_wait alias · c369e0a1

Arnaldo Carvalho de Melo authored Aug 02, 2016

Something made the sys_epoll_wait() function alias not to be found in
the vmlinux DWARF info, being found only in /proc/kallsyms, which made
the BPF perf tests to fail:

  [root@jouet ~]# perf test BPF
  37: Test BPF filter                                          :
  37.1: Test basic BPF filtering                               : FAILED!
  37.2: Test BPF prologue generation                           : Skip
  37.3: Test BPF relocation checker                            : Skip
  [root@jouet ~]#

Using -v we can see it is failing to find DWARF info for the probed function,
sys_epoll_wait, which we can find in /proc/kallsyms but not in vmlinux with
CONFIG_DEBUG_INFO:

  [root@jouet ~]# grep -w sys_epoll_wait /proc/kallsyms
  ffffffffbd295b50 T sys_epoll_wait
  [root@jouet ~]#

  [root@jouet ~]# readelf -wi /lib/modules/4.7.0+/build/vmlinux | grep -w sys_epoll_wait
  [root@jouet ~]#

If we try to use perf probe:

[root@jouet ~]# perf probe sys_epoll_wait
Failed to find debug information for address ffffffffbd295b50
Probe point 'sys_epoll_wait' not found.
  Error: Failed to add events.
[root@jouet ~]#

It all works if we use SyS_epoll_wait, that is just an alias to the probed
function:

  [root@jouet ~]# grep -i sys_epoll_wait /proc/kallsyms
  ffffffffbd295b50 T SyS_epoll_wait
  ffffffffbd295b50 T sys_epoll_wait
  [root@jouet ~]#

So use it:

  [root@jouet ~]# perf test BPF
  37: Test BPF filter                                          :
  37.1: Test basic BPF filtering                               : Ok
  37.2: Test BPF prologue generation                           : Ok
  37.3: Test BPF relocation checker                            : Ok
  [root@jouet ~]#

Further info:

  [root@jouet ~]# gcc --version
  gcc (GCC) 6.1.1 20160621 (Red Hat 6.1.1-3)
  [acme@jouet linux]$ cat /etc/fedora-release
  Fedora release 24 (Twenty Four)

Investigation as to why it fails is still underway, but it was always
going from sys_epoll_wait to SyS_epoll_wait when looking up the DWARF
info in vmlinux, and this is what is breaking now.

Switching to use SyS_epoll_wait allows this test to proceed and test the
BPF code it was designed for, so lets have this in to allow passing this
test while we fix the root cause.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-7hekjp0bodwjbb419sl2b55h@git.kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

c369e0a1

02 Aug, 2016 11 commits

perf tests: objdump output can contain multi byte chunks · b2d0dbf0

Jan Stancek authored Jan 12, 2016

objdump's raw insn output can vary across architectures on the number of
bytes per chunk (bpc) displayed and their endianness.

The code-reading test relied on reading objdump output as 1 bpc. Kaixu
Xia reported test failure on ARM64, where objdump displays 4 bpc:

  70c48:        f90027bf         str        xzr, [x29,#72]
  70c4c:        91224000         add        x0, x0, #0x890
  70c50:        f90023a0         str        x0, [x29,#64]

This patch adds support to read raw insn output for any bpc length.
In case of 2+ bpc it also guesses objdump's display endian.
Reported-and-Tested-by: Kaixu Xia <xiakaixu@huawei.com>
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/07f0f7bcbda78deb423298708ef9b6a54d6b92bd.1452592712.git.jstancek@redhat.com
[ Fix up pr_fmt() call to use %zd for size_t variables, fixing the build on Ubuntu cross-compiling to armhf and ppc64 ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>