perf/urgent fixes

Hi Ingo,

Please consider pulling, the exclude_kernel one is a nasty brown paper
bag one, I'd say :-\

- Arnaldo

Test results at the end of this message, as usual.

The following changes since commit dbf580623d5fee785218d1a47a2bcdf36d85c0e9:

kprobes: Ensure that jprobe probepoints are at function entry (2017-07-08 11:05:35 +0200)

are available in the git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo-4.13-20170710

for you to fetch changes up to 80f62589fa52f530cffc50e78c0b5a2ae572d61e:

perf annotate: Fix broken arrow at row 0 connecting jmp instruction to its target (2017-07-10 16:36:40 -0300)

----------------------------------------------------------------
perf/urgent fixes:

- Fix attr.exclude_kernel setting for default cycles:p (Arnaldo Carvalho de Melo)

- Fix broken arrow at row 0 connecting jmp instruction to its target in the annotate TUI (Jin Yao)

----------------------------------------------------------------
Arnaldo Carvalho de Melo (2):
perf evsel: Fix attr.exclude_kernel setting for default cycles:p perf evsel: State in the default event name if attr.exclude_kernel is set

Jin Yao (1):
perf annotate: Fix broken arrow at row 0 connecting jmp instruction to its target

 tools/perf/ui/browser.c | 2 +-
 tools/perf/util/evsel.c | 8 +++++---
 2 files changed, 6 insertions(+), 4 deletions(-)

Test results:

The first ones are container (docker) based builds of tools/perf with and without libelf support, objtool where it is supported and samples/bpf/, ditto. Where clang is available, it is also used to build perf with/without libelf.

Several are cross builds, the ones with -x-ARCH, and the android one, and those may not have all the features built, due to lack of multi-arch devel packages, available and being used so far on just a few, like debian:experimental-x-{arm64,mipsel}.

The 'perf test' one will perform a variety of tests exercising tools/perf/util/, tools/lib/{bpf,traceevent,etc}, as well as run perf commands with a variety of command line event specifications to then intercept the sys_perf_event syscall to check that the perf_event_attr fields are set up as expected, among a variety of other unit tests.

Then there is the 'make -C tools/perf build-test' ones, that build tools/perf/ with a variety of feature sets, exercising the build with an incomplete set of features as well as with a complete one. It is planned to have it run on each of the containers mentioned above, using some container orchestration infrastructure. Get in contact if interested in helping having this in place.

  # dm
   1 alpine:3.4: Ok
   2 alpine:3.5: Ok
   3 alpine:3.6: Ok
   4 alpine:edge: Ok
   5 android-ndk:r12b-arm: Ok
   6 archlinux:latest: Ok
   7 centos:5: Ok
   8 centos:6: Ok
   9 centos:7: Ok
  10 debian:7: Ok
  11 debian:8: Ok
  12 debian:9: Ok
  13 debian:experimental: Ok
  14 debian:experimental-x-arm64: Ok
  15 debian:experimental-x-mips: Ok
  16 debian:experimental-x-mips64: Ok
  17 debian:experimental-x-mipsel: Ok
  18 fedora:20: Ok
  19 fedora:21: Ok
  20 fedora:22: Ok
  21 fedora:23: Ok
  22 fedora:24: Ok
  23 fedora:24-x-ARC-uClibc: Ok
  24 fedora:25: Ok
  25 fedora:rawhide: Ok
  26 mageia:5: Ok
  27 opensuse:13.2: Ok
  28 opensuse:42.1: Ok
  29 opensuse:42.2: Ok
  30 opensuse:tumbleweed: Ok
  31 ubuntu:12.04.5: Ok
  32 ubuntu:14.04.4: Ok
  33 ubuntu:14.04.4-x-linaro-arm64: Ok
  34 ubuntu:15.10: Ok
  35 ubuntu:16.04: Ok
  36 ubuntu:16.04-x-arm: Ok
  37 ubuntu:16.04-x-arm64: Ok
  38 ubuntu:16.04-x-powerpc: Ok
  39 ubuntu:16.04-x-powerpc64: Ok
  40 ubuntu:16.04-x-powerpc64el: Ok
  41 ubuntu:16.04-x-s390: Ok
  42 ubuntu:16.10: Ok
  43 ubuntu:17.04: Ok
  44 ubuntu:17.10: Ok

  # uname -a
  Linux jouet 4.12.0-rc6+ #3 SMP Tue Jun 27 15:12:38 -03 2017 x86_64 x86_64 x86_64 GNU/Linux
  # perf test
   1: vmlinux symtab matches kallsyms            : Ok
   2: Detect openat syscall event                : Ok
   3: Detect openat syscall event on all cpus    : Ok
   4: Read samples using the mmap interface      : Ok
   5: Parse event definition strings             : Ok
   6: Simple expression parser                   : Ok
   7: PERF_RECORD_* events & perf_sample fields  : Ok
   8: Parse perf pmu format                      : Ok
   9: DSO data read                              : Ok
  10: DSO data cache                             : Ok
  11: DSO data reopen                            : Ok
  12: Roundtrip evsel->name                      : Ok
  13: Parse sched tracepoints fields             : Ok
  14: syscalls:sys_enter_openat event fields     : Ok
  15: Setup struct perf_event_attr               : Ok
  16: Match and link multiple hists              : Ok
  17: 'import perf' in python                    : Ok
  18: Breakpoint overflow signal handler         : Ok
  19: Breakpoint overflow sampling               : Ok
  20: Number of exit events of a simple workload : Ok
  21: Software clock events period values        : Ok
  22: Object code reading                        : Ok
  23: Sample parsing                             : Ok
  24: Use a dummy software event to keep tracking: Ok
  25: Parse with no sample_id_all bit set        : Ok
  26: Filter hist entries                        : Ok
  27: Lookup mmap thread                         : Ok
  28: Share thread mg                            : Ok
  29: Sort output of hist entries                : Ok
  30: Cumulate child hist entries                : Ok
  31: Track with sched_switch                    : Ok
  32: Filter fds with revents mask in a fdarray  : Ok
  33: Add fd to a fdarray, making it autogrow    : Ok
  34: kmod_path__parse                           : Ok
  35: Thread map                                 : Ok
  36: LLVM search and compile                    :
  36.1: Basic BPF llvm compile                    : Ok
  36.2: kbuild searching                          : Ok
  36.3: Compile source for BPF prologue generation: Ok
  36.4: Compile source for BPF relocation         : Ok
  37: Session topology                           : Ok
  38: BPF filter                                 :
  38.1: Basic BPF filtering                      : Skip
  38.2: BPF pinning                              : Skip
  38.3: BPF prologue generation                  : Skip
  38.4: BPF relocation checker                   : Skip
  39: Synthesize thread map                      : Ok
  40: Remove thread map                          : Ok
  41: Synthesize cpu map                         : Ok
  42: Synthesize stat config                     : Ok
  43: Synthesize stat                            : Ok
  44: Synthesize stat round                      : Ok
  45: Synthesize attr update                     : Ok
  46: Event times                                : Ok
  47: Read backward ring buffer                  : Ok
  48: Print cpu map                              : Ok
  49: Probe SDT events                           : Ok
  50: is_printable_array                         : Ok
  51: Print bitmap                               : Ok
  52: perf hooks                                 : Ok
  53: builtin clang support                      : Skip (not compiled in)
  54: unit_number__scnprintf                     : Ok
  55: x86 rdpmc                                  : Ok
  56: Convert perf time to TSC                   : Ok
  57: DWARF unwind                               : Ok
  58: x86 instruction decoder - new instructions : Ok
  59: Intel cqm nmi context read                 : Skip
  # 
  $ make -C tools/perf build-test
  make: Entering directory '/home/acme/git/linux/tools/perf'
  - tarpkg: ./tests/perf-targz-src-pkg .
              make_no_libelf_O: make NO_LIBELF=1
              make_no_libbpf_O: make NO_LIBBPF=1
   make_install_prefix_slash_O: make install prefix=/tmp/krava/
       make_util_pmu_bison_o_O: make util/pmu-bison.o
                make_install_O: make install
                 make_static_O: make LDFLAGS=-static
         make_with_clangllvm_O: make LIBCLANGLLVM=1
            make_no_demangle_O: make NO_DEMANGLE=1
                make_no_gtk2_O: make NO_GTK2=1
                   make_tags_O: make tags
             make_no_libperl_O: make NO_LIBPERL=1
               make_no_slang_O: make NO_SLANG=1
  make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
                   make_help_O: make help
              make_clean_all_O: make clean all
                make_minimal_O: make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1
        make_with_babeltrace_O: make LIBBABELTRACE=1
             make_no_libnuma_O: make NO_LIBNUMA=1
                   make_pure_O: make
                make_no_newt_O: make NO_NEWT=1
            make_install_bin_O: make install-bin
           make_no_libunwind_O: make NO_LIBUNWIND=1
                    make_doc_O: make doc
           make_no_backtrace_O: make NO_BACKTRACE=1
           make_no_libpython_O: make NO_LIBPYTHON=1
             make_util_map_o_O: make util/map.o
            make_no_libaudit_O: make NO_LIBAUDIT=1
                  make_debug_O: make DEBUG=1
                  make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
             make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
            make_no_auxtrace_O: make NO_AUXTRACE=1
                 make_perf_o_O: make perf.o
           make_no_libbionic_O: make NO_LIBBIONIC=1
         make_install_prefix_O: make install prefix=/tmp/krava
  OK
  make: Leaving directory '/home/acme/git/linux/tools/perf'
  $ 

From: Arnaldo Carvalho de Melo <[email protected]>

To allow probing the max attr.precise_ip setting for non-root users we unconditionally set attr.exclude_kernel, which makes the detection work but should be done only for !root, fix it.

---
 tools/perf/util/evsel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 87b431886670..f2a1876d268e 100644
@@ -273,7 +273,7 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
+		.exclude_kernel	= geteuid() != 0,
 	};
 	struct perf_evsel *evsel;
 

2.9.4

From: Arnaldo Carvalho de Melo <[email protected]>

When no event is specified perf will use the "cycles" hardware event with the highest precision available in the processor, and excluding kernel events for non-root users, so make that clear in the event name by setting the "u" event modifier, i.e. "cycles:upp".

E.g.:

The default for root:

  # perf record usleep 1
  # perf evlist -v
  cycles:ppp: ..., precise_ip: 3, exclude_kernel: 0, ...
  #

And for !root:

  $ perf record usleep 1
  $ perf evlist -v
  cycles:uppp: ... , precise_ip: 3, exclude_kernel: 1, ...
  $

---
 tools/perf/util/evsel.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index f2a1876d268e..413f74df08de 100644
@@ -298,8 +298,10 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 		goto out;
 
 	/* use asprintf() because free(evsel) assumes name is allocated */
-	if (asprintf(&evsel->name, "cycles%.*s",
-		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
+	if (asprintf(&evsel->name, "cycles%s%s%.*s",
+		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
+		     attr.exclude_kernel ? "u" : "",
+		     attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0)
 		goto error_free;
 out:
 	return evsel;

2.9.4

From: Jin Yao <[email protected]>

When the jump instruction is displayed at the row 0 in annotate view, the arrow is broken. An example:

 16.86 │   ┌──je     82
  0.01 │      movsd  (%rsp),%xmm0
       │      movsd  0x8(%rsp),%xmm4
       │      movsd  0x8(%rsp),%xmm1
       │      movsd  (%rsp),%xmm3
       │      divsd  %xmm4,%xmm0
       │      divsd  %xmm3,%xmm1
       │      movsd  (%rsp),%xmm2
       │      addsd  %xmm1,%xmm0
       │      addsd  %xmm2,%xmm0
       │      movsd  %xmm0,(%rsp)
       │82:   sub    $0x1,%ebx
 83.03 │    ↑ jne    38
       │      add    $0x10,%rsp
       │      xor    %eax,%eax
       │      pop    %rbx
       │    ← retq

The patch increments the row number before checking with 0.

---
 tools/perf/ui/browser.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index a4d3762cd825..83874b0e266c 100644
@@ -704,7 +704,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 		ui_browser__gotorc(browser, row, column + 1);
 		SLsmg_draw_hline(2);
 
-		if (row++ == 0)
+		if (++row == 0)
 			goto out;
 	} else
 		row = 0;

2.9.4

Pulled, thanks a lot Arnaldo!

Ingo