[GIT PULL 00/54] perf/core improvements and fixes

[GIT PULL 00/54] perf/core improvements and fixes

[Arnaldo Carvalho de Melo]

Hi Ingo,

	Please consider pulling,

- Arnaldo

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

The following changes since commit 3f986eefc89c528bf2d398a6dc3637b743a7139e:

  Merge branch 'perf/urgent' into perf/core, to resolve conflict (2018-03-07 09:23:12 +0100)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.17-20180308

for you to fetch changes up to 2427b432e63b4b911100f717c48289195b7a7d62:

  perf tools: Update quipper information (2018-03-08 11:30:54 -0300)

----------------------------------------------------------------
perf/core improvements and fixes:

- Support to display the IPC/Cycle in 'annotate' TUI, for systems
  where this info can be obtained, like Intel's >= Skylake (Jin Yao)

- Support wildcards on PMU name in dynamic PMU events (Agustin Vega-Frias)

- Display pmu name when printing unmerged events in stat (Agustin Vega-Frias)

- Auto-merge PMU events created by prefix or glob match (Agustin Vega-Frias)

- Fix s390 'call' operations target function annotation (Thomas Richter)

- Handle s390 PC relative load and store instruction in the augmented
  'annotate', code, used so far in the TUI modes of 'perf report' and
  'perf annotate' (Thomas Richter)

- Provide libtraceevent with a kernel symbol resolver, so that
  symbols in tracepoint fields can be resolved when showing them in
  tools such as 'perf report' (Wang YanQing)

- Refactor the cgroups code to look more like other code in tools/perf,
  using cgroup__{put,get} for refcount operations instead of its
  open-coded equivalent, breaking larger functions, etc (Arnaldo Carvalho de Melo)

- Implement support for the -G/--cgroup target in 'perf trace', allowing
  strace like tracing (plus other events, backtraces, etc) for cgroups
  (Arnaldo Carvalho de Melo)

- Update thread shortname in 'perf sched map' when the thread's COMM
  changes (Changbin Du)

- refcount 'struct mem_info', for better sharing it over several
  users, avoid duplicating structs and fixing crashes related to
  use after free (Jiri Olsa)

- Display perf.data version, offsets in 'perf report --header' (Jiri Olsa)

- Record the machine's memory topology information in a perf.data
  feature section, to be used by tools such as 'perf c2c' (Jiri Olsa)

- Fix output of forced groups in the header for 'perf report' --stdio
  and --tui (Jiri Olsa)

- Better support llvm, clang, cxx make tests in the build process (Jiri Olsa)

- Streamline the 'struct perf_mmap' methods, storing some info in the
  struct instead of passing it via various methods, shortening its
  signatures (Kan Liang)

- Update the quipper perf.data parser library site information (Stephane Eranian)

- Correct perf's man pages title markers for asciidoctor (Takashi Iwai)

- Intel PT fixes and refactorings paving the way for implementing
  support for AUX area sampling (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

----------------------------------------------------------------
Adrian Hunter (13):
      perf record: Combine some auxtrace initialization into a single function
      perf auxtrace: Add missing parameters from kernel-doc comments
      perf auxtrace: Rename some buffer-queuing functions
      perf auxtrace: Make auxtrace_queues__add_buffer() return buffer_ptr
      perf intel-pt: Fix overlap detection to identify consecutive buffers correctly
      perf intel-pt: Fix sync_switch
      perf intel-pt: Fix error recovery from missing TIP packet
      perf intel-pt: Fix timestamp following overflow
      perf intel-pt/bts: In auxtrace_record__init_intel() evlist is never NULL
      perf intel-pt: Get rid of intel_pt_use_buffer_pid_tid()
      perf intel-pt: Tidy old_buffer handling in intel_pt_get_trace()
      perf intel-pt: Remove a check for sampling mode
      perf intel-pt: Adjust overlap-checking to support sampling mode

Agustin Vega-Frias (3):
      perf pmu: Support wildcards on pmu name in dynamic pmu events
      perf pmu: Display pmu name when printing unmerged events in stat
      perf pmu: Auto-merge PMU events created by prefix or glob match

Arnaldo Carvalho de Melo (11):
      perf cgroup: Remove misplaced __maybe_unused
      perf cgroup: Rename 'struct cgroup_sel' to 'struct cgroup'
      perf cgroup: Introduce cgroup__delete()
      perf cgroup: Rename close_cgroup() to cgroup__put()
      perf cgroup: Introduce cgroup__get()
      perf cgroup: Introduce find_cgroup() method
      perf cgroup: Introduce cgroup__new() out of open coded equivalent
      perf cgroup: Add evlist__findnew_cgroup()
      perf cgroup: Add evlist__add_default_cgroup()
      perf cgroup: Make the cgroup name be const char *
      perf trace: Support setting cgroups as targets

Changbin Du (2):
      perf sched: Move thread::shortname to thread_runtime
      perf sched map: Re-annotate shortname if thread comm changed

Jin Yao (1):
      perf annotate: Support to display the IPC/Cycle in TUI mode

Jiri Olsa (11):
      perf report: Fix the output for stdio events list
      perf report: Display perf.data header info
      perf record: Move machine variable down the function
      perf record: Remove progname from struct record
      perf tools: Add refcnt into struct mem_info
      perf c2c: Use mem_info refcnt logic
      perf tools: Add MEM_TOPOLOGY feature to perf data file
      perf tools: Update tags with .cpp files
      perf build: Add llvm/clang/cxx make tests into FEATURE_TESTS_EXTRA
      perf build: Add llvm/clang make targets to FILES
      perf build: Force llvm/clang test compile output to .make.output

Kan Liang (8):
      perf evlist: Store 'overwrite' in struct perf_mmap
      perf mmap: Store mmap scope in struct perf_mmap()
      perf mmap: Use the stored scope data in perf_mmap__push()
      perf mmap: Use the stored data in perf_mmap__read_event()
      perf mmap: Use stored 'overwrite' in perf_mmap__consume()
      perf mmap: Simplify perf_mmap__consume()
      perf mmap: Simplify perf_mmap__read_event()
      perf mmap: Simplify perf_mmap__read_init()

Stephane Eranian (1):
      perf tools: Update quipper information

Takashi Iwai (1):
      perf tools: Correct title markers for asciidoctor

Thomas Richter (2):
      perf annotate: Fix s390 target function disassembly
      perf annotate: Handle s390 PC relative load and store instruction.

Wang YanQing (1):
      perf report: Provide libtraceevent with a kernel symbol resolver

 tools/build/Makefile.feature                       |   6 +-
 tools/build/feature/Makefile                       |  14 +-
 tools/include/linux/bitmap.h                       |   2 +-
 tools/perf/Documentation/perf-data.txt             |   2 +-
 tools/perf/Documentation/perf-ftrace.txt           |   2 +-
 tools/perf/Documentation/perf-kallsyms.txt         |   2 +-
 tools/perf/Documentation/perf-list.txt             |   8 +-
 tools/perf/Documentation/perf-sched.txt            |   2 +-
 tools/perf/Documentation/perf-script-perl.txt      |   2 +-
 tools/perf/Documentation/perf-stat.txt             |  17 ++
 tools/perf/Documentation/perf-trace.txt            |  25 ++
 tools/perf/Documentation/perf.data-file-format.txt |   7 +-
 tools/perf/Makefile.perf                           |   6 +-
 tools/perf/arch/s390/annotate/instructions.c       | 116 +++++++-
 tools/perf/arch/x86/tests/perf-time-to-tsc.c       |   7 +-
 tools/perf/arch/x86/util/auxtrace.c                |  14 +-
 tools/perf/builtin-annotate.c                      |  88 +++++-
 tools/perf/builtin-c2c.c                           |  24 +-
 tools/perf/builtin-kvm.c                           |   9 +-
 tools/perf/builtin-record.c                        |  45 +--
 tools/perf/builtin-report.c                        |  26 +-
 tools/perf/builtin-sched.c                         | 133 ++++++---
 tools/perf/builtin-stat.c                          |  29 +-
 tools/perf/builtin-top.c                           |   7 +-
 tools/perf/builtin-trace.c                         |  57 +++-
 tools/perf/tests/backward-ring-buffer.c            |   5 +-
 tools/perf/tests/bpf.c                             |   5 +-
 tools/perf/tests/code-reading.c                    |   7 +-
 tools/perf/tests/keep-tracking.c                   |   7 +-
 tools/perf/tests/mmap-basic.c                      |   7 +-
 tools/perf/tests/openat-syscall-tp-fields.c        |   7 +-
 tools/perf/tests/perf-record.c                     |   7 +-
 tools/perf/tests/sw-clock.c                        |   7 +-
 tools/perf/tests/switch-tracking.c                 |   7 +-
 tools/perf/tests/task-exit.c                       |   7 +-
 tools/perf/ui/browsers/hists.c                     |   5 +-
 tools/perf/util/annotate.c                         |   2 +-
 tools/perf/util/auxtrace.c                         |  37 ++-
 tools/perf/util/auxtrace.h                         |   2 +
 tools/perf/util/cgroup.c                           | 111 +++++---
 tools/perf/util/cgroup.h                           |  13 +-
 tools/perf/util/env.h                              |   9 +
 tools/perf/util/evlist.c                           |   8 +-
 tools/perf/util/evsel.c                            |  23 +-
 tools/perf/util/evsel.h                            |   6 +-
 tools/perf/util/header.c                           | 312 ++++++++++++++++++++-
 tools/perf/util/header.h                           |   1 +
 tools/perf/util/hist.c                             |   4 +-
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  |  64 ++---
 .../perf/util/intel-pt-decoder/intel-pt-decoder.h  |   2 +-
 tools/perf/util/intel-pt.c                         | 110 ++++----
 tools/perf/util/machine.c                          |   2 +-
 tools/perf/util/mmap.c                             |  63 ++---
 tools/perf/util/mmap.h                             |  16 +-
 tools/perf/util/parse-events.c                     |  21 +-
 tools/perf/util/parse-events.h                     |   2 +-
 tools/perf/util/parse-events.l                     |   2 +-
 tools/perf/util/parse-events.y                     |  18 +-
 tools/perf/util/python.c                           |   7 +-
 tools/perf/util/symbol.c                           |  22 ++
 tools/perf/util/symbol.h                           |  19 +-
 tools/perf/util/thread.h                           |   1 -
 62 files changed, 1197 insertions(+), 401 deletions(-)

Test results:

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

The objtool and samples/bpf/ builds are disabled now that I'm switching from
using the sources in a local volume to fetching them from a http server to
build it inside the container, to make it easier to build in a container cluster.
Those will come back later.

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   gcc (Alpine 5.3.0) 5.3.0
   2 alpine:3.5                    : Ok   gcc (Alpine 6.2.1) 6.2.1 20160822
   3 alpine:3.6                    : Ok   gcc (Alpine 6.3.0) 6.3.0
   1 alpine:3.7                    : Ok   gcc (Alpine 6.4.0) 6.4.0
   5 alpine:edge                   : Ok   gcc (Alpine 6.4.0) 6.4.0
   6 amazonlinux:1                 : Ok   gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-11)
   7 amazonlinux:2                 : Ok   gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2)
   8 android-ndk:r12b-arm          : Ok   arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
   9 android-ndk:r15c-arm          : Ok   arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
  10 centos:5                      : Ok   gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55)
  11 centos:6                      : Ok   gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-18)
  12 centos:7                      : Ok   gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-16)
  13 debian:7                      : Ok   gcc (Debian 4.7.2-5) 4.7.2
  14 debian:8                      : Ok   gcc (Debian 4.9.2-10+deb8u1) 4.9.2
  15 debian:9                      : Ok   gcc (Debian 6.3.0-18) 6.3.0 20170516
  16 debian:experimental           : Ok   gcc (Debian 7.2.0-17) 7.2.1 20171205
  17 debian:experimental-x-arm64   : Ok   aarch64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
  18 debian:experimental-x-mips    : Ok   mips-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
  19 debian:experimental-x-mips64  : Ok   mips64-linux-gnuabi64-gcc (Debian 7.2.0-11) 7.2.0
  20 debian:experimental-x-mipsel  : Ok   mipsel-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
  21 fedora:20                     : Ok   gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7)
  22 fedora:21                     : Ok   gcc (GCC) 4.9.2 20150212 (Red Hat 4.9.2-6)
  23 fedora:22                     : Ok   gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6)
  24 fedora:23                     : Ok   gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6)
  25 fedora:24                     : Ok   gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1)
  26 fedora:24-x-ARC-uClibc        : Ok   arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710
  27 fedora:25                     : Ok   gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1)
  28 fedora:26                     : Ok   gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2)
  29 fedora:27                     : Ok   gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2)
  30 fedora:rawhide                : Ok   gcc (GCC) 7.2.1 20170829 (Red Hat 7.2.1-1)
  31 gentoo-stage3-amd64:latest    : Ok   gcc (Gentoo 6.4.0-r1 p1.3) 6.4.0
  32 mageia:5                      : Ok   gcc (GCC) 4.9.2
  33 mageia:6                      : Ok   gcc (Mageia 5.4.0-5.mga6) 5.4.0
  34 opensuse:42.1                 : Ok   gcc (SUSE Linux) 4.8.5
  35 opensuse:42.2                 : Ok   gcc (SUSE Linux) 4.8.5
  36 opensuse:42.3                 : Ok   gcc (SUSE Linux) 4.8.5
  37 opensuse:tumbleweed           : Ok   gcc (SUSE Linux) 7.3.0
  38 oraclelinux:6                 : Ok   gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-18)
  39 oraclelinux:7                 : Ok   gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-16)
  40 ubuntu:12.04.5                : Ok   gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3
  41 ubuntu:14.04.4                : Ok   gcc (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4
  42 ubuntu:14.04.4-x-linaro-arm64 : Ok   aarch64-linux-gnu-gcc (Linaro GCC 5.4-2017.05) 5.4.1 20170404
  43 ubuntu:15.04                  : Ok   gcc (Ubuntu 4.9.2-10ubuntu13) 4.9.2
  44 ubuntu:16.04                  : Ok   gcc (Ubuntu 5.4.0-6ubuntu1~16.04.5) 5.4.0 20160609
  45 ubuntu:16.04-x-arm            : Ok   arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609
  46 ubuntu:16.04-x-arm64          : Ok   aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609
  47 ubuntu:16.04-x-powerpc        : Ok   powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609
  48 ubuntu:16.04-x-powerpc64      : Ok   powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.1) 5.4.0 20160609
  49 ubuntu:16.04-x-powerpc64el    : Ok   powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609
  50 ubuntu:16.04-x-s390           : Ok   s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609
  51 ubuntu:16.10                  : Ok   gcc (Ubuntu 6.2.0-5ubuntu12) 6.2.0 20161005
  52 ubuntu:17.04                  : Ok   gcc (Ubuntu 6.3.0-12ubuntu2) 6.3.0 20170406
  53 ubuntu:17.10                  : Ok   gcc (Ubuntu 7.2.0-8ubuntu3) 7.2.0
  54 ubuntu:18.04                  : Ok   gcc (Ubuntu 7.2.0-16ubuntu1) 7.2.0

  # uname -a
  Linux jouet 4.16.0-rc4 #1 SMP Mon Mar 5 12:18:05 -03 2018 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: Test data source output                               : Ok
   6: Parse event definition strings                        : Ok
   7: Simple expression parser                              : Ok
   8: PERF_RECORD_* events & perf_sample fields             : Ok
   9: Parse perf pmu format                                 : Ok
  10: DSO data read                                         : Ok
  11: DSO data cache                                        : Ok
  12: DSO data reopen                                       : Ok
  13: Roundtrip evsel->name                                 : Ok
  14: Parse sched tracepoints fields                        : Ok
  15: syscalls:sys_enter_openat event fields                : Ok
  16: Setup struct perf_event_attr                          : Ok
  17: Match and link multiple hists                         : Ok
  18: 'import perf' in python                               : Ok
  19: Breakpoint overflow signal handler                    : Ok
  20: Breakpoint overflow sampling                          : Ok
  21: Number of exit events of a simple workload            : Ok
  22: Software clock events period values                   : Ok
  23: Object code reading                                   : FAILED!
  24: Sample parsing                                        : Ok
  25: Use a dummy software event to keep tracking           : Ok
  26: Parse with no sample_id_all bit set                   : Ok
  27: Filter hist entries                                   : Ok
  28: Lookup mmap thread                                    : Ok
  29: Share thread mg                                       : Ok
  30: Sort output of hist entries                           : Ok
  31: Cumulate child hist entries                           : Ok
  32: Track with sched_switch                               : Ok
  33: Filter fds with revents mask in a fdarray             : Ok
  34: Add fd to a fdarray, making it autogrow               : Ok
  35: kmod_path__parse                                      : Ok
  36: Thread map                                            : Ok
  37: LLVM search and compile                               :
  37.1: Basic BPF llvm compile                              : Ok
  37.2: kbuild searching                                    : Ok
  37.3: Compile source for BPF prologue generation          : Ok
  37.4: Compile source for BPF relocation                   : Ok
  38: Session topology                                      : Ok
  39: BPF filter                                            :
  39.1: Basic BPF filtering                                 : Ok
  39.2: BPF pinning                                         : Ok
  39.3: BPF prologue generation                             : Ok
  39.4: BPF relocation checker                              : Ok
  40: Synthesize thread map                                 : Ok
  41: Remove thread map                                     : Ok
  42: Synthesize cpu map                                    : Ok
  43: Synthesize stat config                                : Ok
  44: Synthesize stat                                       : Ok
  45: Synthesize stat round                                 : Ok
  46: Synthesize attr update                                : Ok
  47: Event times                                           : Ok
  48: Read backward ring buffer                             : Ok
  49: Print cpu map                                         : Ok
  50: Probe SDT events                                      : Ok
  51: is_printable_array                                    : Ok
  52: Print bitmap                                          : Ok
  53: perf hooks                                            : Ok
  54: builtin clang support                                 : Skip (not compiled in)
  55: unit_number__scnprintf                                : Ok
  56: x86 rdpmc                                             : Ok
  57: Convert perf time to TSC                              : Ok
  58: DWARF unwind                                          : Ok
  59: x86 instruction decoder - new instructions            : Ok
  60: Use vfs_getname probe to get syscall args filenames   : Ok
  61: probe libc's inet_pton & backtrace it with ping       : Ok
  62: Check open filename arg using perf trace + vfs_getname: Ok
  63: probe libc's inet_pton & backtrace it with ping       : Ok
  64: Add vfs_getname probe to get syscall args filenames   : Ok
  #

  $ make -C tools/perf build-test
  make: Entering directory '/home/acme/git/perf/tools/perf'
  - tarpkg: ./tests/perf-targz-src-pkg .
            make_no_auxtrace_O: make NO_AUXTRACE=1
              make_no_libelf_O: make NO_LIBELF=1
                    make_doc_O: make doc
                   make_tags_O: make tags
        make_with_babeltrace_O: make LIBBABELTRACE=1
           make_no_backtrace_O: make NO_BACKTRACE=1
           make_no_libpython_O: make NO_LIBPYTHON=1
                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_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
         make_install_prefix_O: make install prefix=/tmp/krava
                   make_pure_O: make
              make_clean_all_O: make clean all
   make_install_prefix_slash_O: make install prefix=/tmp/krava/
         make_with_clangllvm_O: make LIBCLANGLLVM=1
       make_util_pmu_bison_o_O: make util/pmu-bison.o
           make_no_libbionic_O: make NO_LIBBIONIC=1
             make_no_libnuma_O: make NO_LIBNUMA=1
                  make_debug_O: make DEBUG=1
  make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
           make_no_libunwind_O: make NO_LIBUNWIND=1
                make_install_O: make install
                   make_help_O: make help
             make_util_map_o_O: make util/map.o
                  make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
            make_no_demangle_O: make NO_DEMANGLE=1
            make_install_bin_O: make install-bin
                 make_perf_o_O: make perf.o
                make_no_gtk2_O: make NO_GTK2=1
                make_no_newt_O: make NO_NEWT=1
               make_no_slang_O: make NO_SLANG=1
            make_no_libaudit_O: make NO_LIBAUDIT=1
              make_no_libbpf_O: make NO_LIBBPF=1
                 make_static_O: make LDFLAGS=-static
             make_no_libperl_O: make NO_LIBPERL=1
  OK
  make: Leaving directory '/home/acme/git/perf/tools/perf'
  $

[PATCH 01/54] perf cgroup: Remove misplaced __maybe_unused

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

The 'opt' parameter in parse_cgroups() _is_ used. The original patch
used '__used' that was even more confusing :-)

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 023695d96ee0 ("perf tool: Add cgroup support")
Link: https://lkml.kernel.org/n/tip-4jo2puz0empkoou6bbq460tl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 5dd9b5ea314d..2e2aa6c86107 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -153,7 +153,7 @@ void close_cgroup(struct cgroup_sel *cgrp)
 	}
 }
 
-int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
+int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
-- 
2.14.3

[PATCH 02/54] perf cgroup: Rename 'struct cgroup_sel' to 'struct cgroup'

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

That name isn't used, is shorter, lets switch to it.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-e51yphwgvepd1y4f5fjptmjq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 6 +++---
 tools/perf/util/cgroup.h | 5 +++--
 tools/perf/util/evsel.h  | 4 ++--
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 2e2aa6c86107..6ce291f45f2d 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -93,7 +93,7 @@ static int open_cgroup(char *name)
 static int add_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
-	struct cgroup_sel *cgrp = NULL;
+	struct cgroup *cgrp = NULL;
 	int n;
 	/*
 	 * check if cgrp is already defined, if so we reuse it
@@ -144,7 +144,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	return 0;
 }
 
-void close_cgroup(struct cgroup_sel *cgrp)
+void close_cgroup(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
@@ -158,7 +158,7 @@ int parse_cgroups(const struct option *opt, const char *str,
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	struct perf_evsel *counter;
-	struct cgroup_sel *cgrp = NULL;
+	struct cgroup *cgrp = NULL;
 	const char *p, *e, *eos = str + strlen(str);
 	char *s;
 	int ret, i;
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index afafc87e9201..934daa8e4c19 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -6,7 +6,7 @@
 
 struct option;
 
-struct cgroup_sel {
+struct cgroup {
 	char *name;
 	int fd;
 	refcount_t refcnt;
@@ -14,7 +14,8 @@ struct cgroup_sel {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-void close_cgroup(struct cgroup_sel *cgrp);
+void close_cgroup(struct cgroup *cgrp);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a7487c6d1866..92ba001b627f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -30,7 +30,7 @@ struct perf_sample_id {
 	u64			period;
 };
 
-struct cgroup_sel;
+struct cgroup;
 
 /*
  * The 'struct perf_evsel_config_term' is used to pass event
@@ -107,7 +107,7 @@ struct perf_evsel {
 	struct perf_stat_evsel  *stats;
 	void			*priv;
 	u64			db_id;
-	struct cgroup_sel	*cgrp;
+	struct cgroup		*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
 	struct cpu_map		*own_cpus;
-- 
2.14.3

[PATCH 03/54] perf cgroup: Introduce cgroup__delete()

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

Just to make this code look more like other places in tools/perf.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-j3j72vvn2d5j7tenlghdy195@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 6ce291f45f2d..4dd52feb1ae6 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -144,12 +144,17 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	return 0;
 }
 
+static void cgroup__delete(struct cgroup *cgroup)
+{
+	close(cgroup->fd);
+	zfree(&cgroup->name);
+	free(cgroup);
+}
+
 void close_cgroup(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
-		close(cgrp->fd);
-		zfree(&cgrp->name);
-		free(cgrp);
+		cgroup__delete(cgrp);
 	}
 }
 
-- 
2.14.3

[PATCH 04/54] perf cgroup: Rename close_cgroup() to cgroup__put()

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

It is not really closing the cgroup, but instead dropping a reference
count and if it hits zero, then calling delete, which will, among other
cleanup shores, close the cgroup fd.

So it is really dropping a reference to that cgroup, and the method name
for that is "put", so rename close_cgroup() to cgroup__put() to follow
this naming convention.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sccxpnd7bgwc1llgokt6fcey@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 5 ++---
 tools/perf/util/cgroup.h | 3 ++-
 tools/perf/util/evsel.c  | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 4dd52feb1ae6..b078d54d4245 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -135,9 +135,8 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (refcount_dec_and_test(&cgrp->refcnt))
-		free(cgrp);
 
+	cgroup__put(cgrp);
 	return -1;
 found:
 	counter->cgrp = cgrp;
@@ -151,7 +150,7 @@ static void cgroup__delete(struct cgroup *cgroup)
 	free(cgroup);
 }
 
-void close_cgroup(struct cgroup *cgrp)
+void cgroup__put(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
 		cgroup__delete(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 934daa8e4c19..69169fbf8d13 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -14,7 +14,8 @@ struct cgroup {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-void close_cgroup(struct cgroup *cgrp);
+
+void cgroup__put(struct cgroup *cgroup);
 
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b56e1c2ddaee..f1f883bb41a8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1233,7 +1233,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	perf_evsel__free_config_terms(evsel);
-	close_cgroup(evsel->cgrp);
+	cgroup__put(evsel->cgrp);
 	cpu_map__put(evsel->cpus);
 	cpu_map__put(evsel->own_cpus);
 	thread_map__put(evsel->threads);
-- 
2.14.3

[PATCH 05/54] perf cgroup: Introduce cgroup__get()

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

The refcount operation counterpart to cgroup__put(), use it when reusing
a cgroup.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-14ynvrl7y2cz8gyuy5q5v41g@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 16 ++++++++++------
 tools/perf/util/cgroup.h |  1 +
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index b078d54d4245..8ea964461eb7 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -99,15 +99,12 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	 * check if cgrp is already defined, if so we reuse it
 	 */
 	evlist__for_each_entry(evlist, counter) {
-		cgrp = counter->cgrp;
-		if (!cgrp)
+		if (!counter->cgrp)
 			continue;
-		if (!strcmp(cgrp->name, str)) {
-			refcount_inc(&cgrp->refcnt);
+		if (!strcmp(counter->cgrp->name, str)) {
+			cgrp = cgroup__get(counter->cgrp);
 			break;
 		}
-
-		cgrp = NULL;
 	}
 
 	if (!cgrp) {
@@ -157,6 +154,13 @@ void cgroup__put(struct cgroup *cgrp)
 	}
 }
 
+struct cgroup *cgroup__get(struct cgroup *cgroup)
+{
+       if (cgroup)
+		refcount_inc(&cgroup->refcnt);
+       return cgroup;
+}
+
 int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 69169fbf8d13..34a6c11543dc 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -15,6 +15,7 @@ struct cgroup {
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
 
+struct cgroup *cgroup__get(struct cgroup *cgroup);
 void cgroup__put(struct cgroup *cgroup);
 
 int parse_cgroups(const struct option *opt, const char *str, int unset);
-- 
2.14.3

[PATCH 06/54] perf cgroup: Introduce find_cgroup() method

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

To break down complexity in add_cgroup().

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-5yqshcf5hm837n7c86u7lhjf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 8ea964461eb7..84dfc34a6d0f 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -90,11 +90,10 @@ static int open_cgroup(char *name)
 	return fd;
 }
 
-static int add_cgroup(struct perf_evlist *evlist, char *str)
+static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
 	struct cgroup *cgrp = NULL;
-	int n;
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
@@ -107,6 +106,15 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 		}
 	}
 
+	return cgrp;
+}
+
+static int add_cgroup(struct perf_evlist *evlist, char *str)
+{
+	struct perf_evsel *counter;
+	struct cgroup *cgrp = evlist__find_cgroup(evlist, str);
+	int n;
+
 	if (!cgrp) {
 		cgrp = zalloc(sizeof(*cgrp));
 		if (!cgrp)
-- 
2.14.3

[PATCH 07/54] perf cgroup: Introduce cgroup__new() out of open coded equivalent

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

To follow the namespacing convention in tools/perf.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jaalyl6bkvvji4r5u8wqw4n4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 84dfc34a6d0f..26a837037797 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -109,6 +109,25 @@ static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
 	return cgrp;
 }
 
+static struct cgroup *cgroup__new(char *name)
+{
+	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
+
+	if (cgroup != NULL) {
+		cgroup->name = name;
+		refcount_set(&cgroup->refcnt, 1);
+
+		cgroup->fd = open_cgroup(name);
+		if (cgroup->fd == -1)
+			goto out_err;
+	}
+
+	return cgroup;
+out_err:
+	free(cgroup);
+	return NULL;
+}
+
 static int add_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
@@ -116,18 +135,9 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	int n;
 
 	if (!cgrp) {
-		cgrp = zalloc(sizeof(*cgrp));
+		cgrp = cgroup__new(str);
 		if (!cgrp)
 			return -1;
-
-		cgrp->name = str;
-		refcount_set(&cgrp->refcnt, 1);
-
-		cgrp->fd = open_cgroup(str);
-		if (cgrp->fd == -1) {
-			free(cgrp);
-			return -1;
-		}
 	}
 
 	/*
-- 
2.14.3

[PATCH 08/54] perf sched: Move thread::shortname to thread_runtime

[Arnaldo Carvalho de Melo]

From: Changbin Du <changbin.du@intel.com>

The thread::shortname only used by sched command, so move it to sched
private structure.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1520307457-23668-2-git-send-email-changbin.du@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-sched.c | 95 +++++++++++++++++++++++++++-------------------
 tools/perf/util/thread.h   |  1 -
 2 files changed, 55 insertions(+), 41 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 83283fedb00f..0a632a6b6228 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -254,6 +254,8 @@ struct thread_runtime {
 	u64 total_delay_time;
 
 	int last_state;
+
+	char shortname[3];
 	u64 migrations;
 };
 
@@ -897,6 +899,37 @@ struct sort_dimension {
 	struct list_head	list;
 };
 
+/*
+ * handle runtime stats saved per thread
+ */
+static struct thread_runtime *thread__init_runtime(struct thread *thread)
+{
+	struct thread_runtime *r;
+
+	r = zalloc(sizeof(struct thread_runtime));
+	if (!r)
+		return NULL;
+
+	init_stats(&r->run_stats);
+	thread__set_priv(thread, r);
+
+	return r;
+}
+
+static struct thread_runtime *thread__get_runtime(struct thread *thread)
+{
+	struct thread_runtime *tr;
+
+	tr = thread__priv(thread);
+	if (tr == NULL) {
+		tr = thread__init_runtime(thread);
+		if (tr == NULL)
+			pr_debug("Failed to malloc memory for runtime data.\n");
+	}
+
+	return tr;
+}
+
 static int
 thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r)
 {
@@ -1480,6 +1513,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 {
 	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	struct thread *sched_in;
+	struct thread_runtime *tr;
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
@@ -1519,22 +1553,28 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	if (sched_in == NULL)
 		return -1;
 
+	tr = thread__get_runtime(sched_in);
+	if (tr == NULL) {
+		thread__put(sched_in);
+		return -1;
+	}
+
 	sched->curr_thread[this_cpu] = thread__get(sched_in);
 
 	printf("  ");
 
 	new_shortname = 0;
-	if (!sched_in->shortname[0]) {
+	if (!tr->shortname[0]) {
 		if (!strcmp(thread__comm_str(sched_in), "swapper")) {
 			/*
 			 * Don't allocate a letter-number for swapper:0
 			 * as a shortname. Instead, we use '.' for it.
 			 */
-			sched_in->shortname[0] = '.';
-			sched_in->shortname[1] = ' ';
+			tr->shortname[0] = '.';
+			tr->shortname[1] = ' ';
 		} else {
-			sched_in->shortname[0] = sched->next_shortname1;
-			sched_in->shortname[1] = sched->next_shortname2;
+			tr->shortname[0] = sched->next_shortname1;
+			tr->shortname[1] = sched->next_shortname2;
 
 			if (sched->next_shortname1 < 'Z') {
 				sched->next_shortname1++;
@@ -1552,6 +1592,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	for (i = 0; i < cpus_nr; i++) {
 		int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
 		struct thread *curr_thread = sched->curr_thread[cpu];
+		struct thread_runtime *curr_tr;
 		const char *pid_color = color;
 		const char *cpu_color = color;
 
@@ -1569,9 +1610,14 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		else
 			color_fprintf(stdout, cpu_color, "*");
 
-		if (sched->curr_thread[cpu])
-			color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname);
-		else
+		if (sched->curr_thread[cpu]) {
+			curr_tr = thread__get_runtime(sched->curr_thread[cpu]);
+			if (curr_tr == NULL) {
+				thread__put(sched_in);
+				return -1;
+			}
+			color_fprintf(stdout, pid_color, "%2s ", curr_tr->shortname);
+		} else
 			color_fprintf(stdout, color, "   ");
 	}
 
@@ -1587,7 +1633,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			pid_color = COLOR_PIDS;
 
 		color_fprintf(stdout, pid_color, "%s => %s:%d",
-		       sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
+		       tr->shortname, thread__comm_str(sched_in), sched_in->tid);
 	}
 
 	if (sched->map.comp && new_cpu)
@@ -2200,37 +2246,6 @@ static void save_idle_callchain(struct idle_thread_runtime *itr,
 	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
 }
 
-/*
- * handle runtime stats saved per thread
- */
-static struct thread_runtime *thread__init_runtime(struct thread *thread)
-{
-	struct thread_runtime *r;
-
-	r = zalloc(sizeof(struct thread_runtime));
-	if (!r)
-		return NULL;
-
-	init_stats(&r->run_stats);
-	thread__set_priv(thread, r);
-
-	return r;
-}
-
-static struct thread_runtime *thread__get_runtime(struct thread *thread)
-{
-	struct thread_runtime *tr;
-
-	tr = thread__priv(thread);
-	if (tr == NULL) {
-		tr = thread__init_runtime(thread);
-		if (tr == NULL)
-			pr_debug("Failed to malloc memory for runtime data.\n");
-	}
-
-	return tr;
-}
-
 static struct thread *timehist_get_thread(struct perf_sched *sched,
 					  struct perf_sample *sample,
 					  struct machine *machine,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 40cfa36c022a..14d44c3235b8 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -26,7 +26,6 @@ struct thread {
 	pid_t			ppid;
 	int			cpu;
 	refcount_t		refcnt;
-	char			shortname[3];
 	bool			comm_set;
 	int			comm_len;
 	bool			dead; /* if set thread has exited */
-- 
2.14.3

[PATCH 09/54] perf sched map: Re-annotate shortname if thread comm changed

[Arnaldo Carvalho de Melo]

From: Changbin Du <changbin.du@intel.com>

This is to show the real name of thread that created via fork-exec.  See
below example for shortname *A0*.

$ sudo ./perf sched map
              *A0   80393.050639 secs A0 => perf:22368
          *.   A0   80393.050748 secs .  => swapper:0
           .  *.    80393.050887 secs
      *B0  .   .    80393.052735 secs B0 => rcu_sched:8
      *.   .   .    80393.052743 secs
       .  *C0  .    80393.056264 secs C0 => kworker/2:1H:287
       .  *A0  .    80393.056270 secs
       .  *D0  .    80393.056769 secs D0 => ksoftirqd/2:22
-      .  *A0  .    80393.056804 secs
+      .  *A0  .    80393.056804 secs A0 => pi:22368
       .  *.   .    80393.056854 secs
      *B0  .   .    80393.060727 secs
      ...

Signed-off-by: Changbin Du <changbin.du@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1520307457-23668-3-git-send-email-changbin.du@intel.com
[ Optimally pack struct thread_runtime when adding the new bool member ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-sched.c | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0a632a6b6228..4dfdee668b0c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -256,6 +256,8 @@ struct thread_runtime {
 	int last_state;
 
 	char shortname[3];
+	bool comm_changed;
+
 	u64 migrations;
 };
 
@@ -1626,7 +1628,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 	timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
 	color_fprintf(stdout, color, "  %12s secs ", stimestamp);
-	if (new_shortname || (verbose > 0 && sched_in->tid)) {
+	if (new_shortname || tr->comm_changed || (verbose > 0 && sched_in->tid)) {
 		const char *pid_color = color;
 
 		if (thread__has_color(sched_in))
@@ -1634,6 +1636,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 		color_fprintf(stdout, pid_color, "%s => %s:%d",
 		       tr->shortname, thread__comm_str(sched_in), sched_in->tid);
+		tr->comm_changed = false;
 	}
 
 	if (sched->map.comp && new_cpu)
@@ -1737,6 +1740,37 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	return err;
 }
 
+static int perf_sched__process_comm(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	struct thread *thread;
+	struct thread_runtime *tr;
+	int err;
+
+	err = perf_event__process_comm(tool, event, sample, machine);
+	if (err)
+		return err;
+
+	thread = machine__find_thread(machine, sample->pid, sample->tid);
+	if (!thread) {
+		pr_err("Internal error: can't find thread\n");
+		return -1;
+	}
+
+	tr = thread__get_runtime(thread);
+	if (tr == NULL) {
+		thread__put(thread);
+		return -1;
+	}
+
+	tr->comm_changed = true;
+	thread__put(thread);
+
+	return 0;
+}
+
 static int perf_sched__read_events(struct perf_sched *sched)
 {
 	const struct perf_evsel_str_handler handlers[] = {
@@ -3306,7 +3340,7 @@ int cmd_sched(int argc, const char **argv)
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
-			.comm		 = perf_event__process_comm,
+			.comm		 = perf_sched__process_comm,
 			.namespaces	 = perf_event__process_namespaces,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
-- 
2.14.3

[PATCH 10/54] perf record: Combine some auxtrace initialization into a single function

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

In preparation for adding AUX area sampling support, combine some
auxtrace initialization into a single function.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520327598-1317-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 12230ddb6506..14d82f0fe5cc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -274,6 +274,24 @@ static void record__read_auxtrace_snapshot(struct record *rec)
 	}
 }
 
+static int record__auxtrace_init(struct record *rec)
+{
+	int err;
+
+	if (!rec->itr) {
+		rec->itr = auxtrace_record__init(rec->evlist, &err);
+		if (err)
+			return err;
+	}
+
+	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+					      rec->opts.auxtrace_snapshot_opts);
+	if (err)
+		return err;
+
+	return auxtrace_parse_filters(rec->evlist);
+}
+
 #else
 
 static inline
@@ -294,6 +312,11 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
 	return 0;
 }
 
+static int record__auxtrace_init(struct record *rec __maybe_unused)
+{
+	return 0;
+}
+
 #endif
 
 static int record__mmap_evlist(struct record *rec,
@@ -1727,17 +1750,6 @@ int cmd_record(int argc, const char **argv)
 		alarm(rec->switch_output.time);
 	}
 
-	if (!rec->itr) {
-		rec->itr = auxtrace_record__init(rec->evlist, &err);
-		if (err)
-			goto out;
-	}
-
-	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
-					      rec->opts.auxtrace_snapshot_opts);
-	if (err)
-		goto out;
-
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().
@@ -1746,7 +1758,7 @@ int cmd_record(int argc, const char **argv)
 
 	symbol__init(NULL);
 
-	err = auxtrace_parse_filters(rec->evlist);
+	err = record__auxtrace_init(rec);
 	if (err)
 		goto out;
 
-- 
2.14.3

[PATCH 11/54] perf cgroup: Add evlist__findnew_cgroup()

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

Similar to machine__findnew_thread(), etc, i.e. try to find, get a
refcount if found and return it, otherwise return a new cgroup object.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-im1omevlihhyneiic4nl3g24@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 17 ++++++++++-------
 tools/perf/util/cgroup.h |  4 ++++
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 26a837037797..6fd33ffc2488 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -128,18 +128,21 @@ static struct cgroup *cgroup__new(char *name)
 	return NULL;
 }
 
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name)
+{
+	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
+
+	return cgroup ?: cgroup__new(name);
+}
+
 static int add_cgroup(struct perf_evlist *evlist, char *str)
 {
 	struct perf_evsel *counter;
-	struct cgroup *cgrp = evlist__find_cgroup(evlist, str);
+	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);
 	int n;
 
-	if (!cgrp) {
-		cgrp = cgroup__new(str);
-		if (!cgrp)
-			return -1;
-	}
-
+	if (!cgrp)
+		return -1;
 	/*
 	 * find corresponding event
 	 * if add cgroup N, then need to find event N
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 34a6c11543dc..0e377e6340dd 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -18,6 +18,10 @@ extern int nr_cgroups; /* number of explicit cgroups defined */
 struct cgroup *cgroup__get(struct cgroup *cgroup);
 void cgroup__put(struct cgroup *cgroup);
 
+struct perf_evlist;
+
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */
-- 
2.14.3

[PATCH 12/54] perf cgroup: Add evlist__add_default_cgroup()

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

So that tools like 'perf trace' can allow the user to set a cgroup
to be used for all the evsels still without a crgroup setup by
parse_cgroups(), such as the one to use for the syscalls, vfs_getname
and other events involved in strace like syscall tracing.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zf9jjsbj661r3lk6qb7g8j70@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 14 ++++++++++++++
 tools/perf/util/cgroup.h |  2 ++
 2 files changed, 16 insertions(+)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 6fd33ffc2488..d8cd0e601c56 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -182,6 +182,20 @@ struct cgroup *cgroup__get(struct cgroup *cgroup)
        return cgroup;
 }
 
+static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup)
+{
+	if (evsel->cgrp == NULL)
+		evsel->cgrp = cgroup__get(cgroup);
+}
+
+void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		evsel__set_default_cgroup(evsel, cgroup);
+}
+
 int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 0e377e6340dd..b213f5e9a3ed 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -22,6 +22,8 @@ struct perf_evlist;
 
 struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name);
 
+void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */
-- 
2.14.3

[PATCH 13/54] perf cgroup: Make the cgroup name be const char *

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

The usual thing is for a constructor to allocate space for its members,
not to require that the caller pass a pre-allocated 'name' and then, at
its destructor, to free something not allocated by it.

Fix it by making cgroup__new() to receive a const char pointer, then
allocate cgroup->name that then can continue to be freed at
cgroup__delete(), balancing the alloc/free operations inside the cgroup
struct methods.

This eases calling evlist__findnew_cgroup() from the custom 'perf trace'
cgroup parser, that will only call parse_cgroups() when the '-G cgroup'
is passed on the command line after '-e event' entries, when it'll
behave just like 'perf stat' and 'perf record', i.e. the previous
parse_cgroup() users that mandate that -G only can come after a -e.

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>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-4leugnuyqi10t98990o3xi1t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cgroup.c | 24 ++++++++++++++----------
 tools/perf/util/cgroup.h |  2 +-
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index d8cd0e601c56..78408f5c4bad 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -71,7 +71,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 	return -1;
 }
 
-static int open_cgroup(char *name)
+static int open_cgroup(const char *name)
 {
 	char path[PATH_MAX + 1];
 	char mnt[PATH_MAX + 1];
@@ -90,7 +90,7 @@ static int open_cgroup(char *name)
 	return fd;
 }
 
-static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
+static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str)
 {
 	struct perf_evsel *counter;
 	struct cgroup *cgrp = NULL;
@@ -109,33 +109,38 @@ static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, char *str)
 	return cgrp;
 }
 
-static struct cgroup *cgroup__new(char *name)
+static struct cgroup *cgroup__new(const char *name)
 {
 	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
 
 	if (cgroup != NULL) {
-		cgroup->name = name;
 		refcount_set(&cgroup->refcnt, 1);
 
+		cgroup->name = strdup(name);
+		if (!cgroup->name)
+			goto out_err;
 		cgroup->fd = open_cgroup(name);
 		if (cgroup->fd == -1)
-			goto out_err;
+			goto out_free_name;
 	}
 
 	return cgroup;
+
+out_free_name:
+	free(cgroup->name);
 out_err:
 	free(cgroup);
 	return NULL;
 }
 
-struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name)
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name)
 {
 	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
 
 	return cgroup ?: cgroup__new(name);
 }
 
-static int add_cgroup(struct perf_evlist *evlist, char *str)
+static int add_cgroup(struct perf_evlist *evlist, const char *str)
 {
 	struct perf_evsel *counter;
 	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);
@@ -222,10 +227,9 @@ int parse_cgroups(const struct option *opt, const char *str,
 			if (!s)
 				return -1;
 			ret = add_cgroup(evlist, s);
-			if (ret) {
-				free(s);
+			free(s);
+			if (ret)
 				return -1;
-			}
 		}
 		/* nr_cgroups is increased een for empty cgroups */
 		nr_cgroups++;
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index b213f5e9a3ed..f033a80c1b14 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -20,7 +20,7 @@ void cgroup__put(struct cgroup *cgroup);
 
 struct perf_evlist;
 
-struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, char *name);
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name);
 
 void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup);
 
-- 
2.14.3

[PATCH 14/54] perf trace: Support setting cgroups as targets

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.

Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:

  # ls -la /sys/fs/cgroup/perf_event/ | grep drw
  drwxr-xr-x. 14 root root 360 Mar  6 12:04 ..
  drwxr-xr-x.  3 root root   0 Mar  6 15:05 machine.slice
  #

So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:

  # perf trace --duration 100 -G machine.slice
     0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
   250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
   500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
   750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
  1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
  1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
  1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
  1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
   902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
  1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
  2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C  #

If we look inside that cgroup hierarchy we get:

  # ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
  drwxr-xr-x. 3 root root 0 Mar  6 15:05 .
  drwxr-xr-x. 2 root root 0 Mar  6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
  #

There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:

  # perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5

   Summary of events:

     qemu-system-x86 (23667), 143858 events, 24.2%

     syscall            calls    total       min       avg       max      stddev
                                 (msec)    (msec)    (msec)    (msec)        (%)
     --------------- -------- --------- --------- --------- ---------     ------
     ppoll              28492  4348.631     0.000     0.153    11.616      1.05%
     futex              19661   140.801     0.001     0.007     2.993      3.20%
     read               18440    68.084     0.001     0.004     1.653      4.33%
     ioctl               5387    24.768     0.002     0.005     0.134      1.62%

     CPU 0/KVM (23744), 449455 events, 75.8%

     syscall            calls    total       min       avg       max      stddev
                               (msec)    (msec)    (msec)    (msec)        (%)
     --------------- -------- --------- --------- --------- ---------     ------
     ioctl             148364  3401.812     0.000     0.023    11.801      1.15%
     futex              36131   404.127     0.001     0.011     7.377      2.63%
     writev             29452   339.688     0.003     0.012     1.740      1.36%
     write              11315    45.992     0.001     0.004     0.105      1.10%

  #

See the documentation about how to set more than one cgroup for
different events in the same command line.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-trace.txt | 25 +++++++++++++++++
 tools/perf/builtin-trace.c              | 50 +++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 33a88e984e66..5a7035c5c523 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -63,6 +63,31 @@ filter out the startup phase of the program, which is often very different.
 --uid=::
         Record events in threads owned by uid. Name or number.
 
+-G::
+--cgroup::
+	Record events in threads in a cgroup.
+
+	Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then
+	remove the /sys/fs/cgroup/perf_event/ part and try:
+
+		perf trace -G A -e sched:*switch
+
+	Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
+	_and_ sched:sched_switch to the 'A' cgroup, while:
+
+		perf trace -e sched:*switch -G A
+
+	will only set the sched:sched_switch event to the 'A' cgroup, all the
+	other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
+	a cgroup (on the root cgroup, sys wide, etc).
+
+	Multiple cgroups:
+
+		perf trace -G A -e sched:*switch -G B
+
+	the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
+	to the 'B' cgroup.
+
 --filter-pids=::
 	Filter out events for these pids and for 'trace' itself (comma separated list).
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 1a93debc1e8d..5b81060a8117 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -19,6 +19,7 @@
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
 #include "builtin.h"
+#include "util/cgroup.h"
 #include "util/color.h"
 #include "util/debug.h"
 #include "util/env.h"
@@ -83,6 +84,7 @@ struct trace {
 	struct perf_evlist	*evlist;
 	struct machine		*host;
 	struct thread		*current;
+	struct cgroup		*cgroup;
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
@@ -2370,6 +2372,34 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 				   trace__sched_stat_runtime))
 		goto out_error_sched_stat_runtime;
 
+	/*
+	 * If a global cgroup was set, apply it to all the events without an
+	 * explicit cgroup. I.e.:
+	 *
+	 * 	trace -G A -e sched:*switch
+	 *
+	 * Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
+	 * _and_ sched:sched_switch to the 'A' cgroup, while:
+	 *
+	 * trace -e sched:*switch -G A
+	 *
+	 * will only set the sched:sched_switch event to the 'A' cgroup, all the
+	 * other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
+	 * a cgroup (on the root cgroup, sys wide, etc).
+	 *
+	 * Multiple cgroups:
+	 *
+	 * trace -G A -e sched:*switch -G B
+	 *
+	 * the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
+	 * to the 'B' cgroup.
+	 *
+	 * evlist__set_default_cgroup() grabs a reference of the passed cgroup
+	 * only for the evsels still without a cgroup, i.e. evsel->cgroup == NULL.
+	 */
+	if (trace->cgroup)
+		evlist__set_default_cgroup(trace->evlist, trace->cgroup);
+
 	err = perf_evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
@@ -2540,6 +2570,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	trace__symbols__exit(trace);
 
 	perf_evlist__delete(evlist);
+	cgroup__put(trace->cgroup);
 	trace->evlist = NULL;
 	trace->live = false;
 	return err;
@@ -2979,6 +3010,18 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 	return err;
 }
 
+static int trace__parse_cgroups(const struct option *opt, const char *str, int unset)
+{
+	struct trace *trace = opt->value;
+
+	if (!list_empty(&trace->evlist->entries))
+		return parse_cgroups(opt, str, unset);
+
+	trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
+
+	return 0;
+}
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -3069,6 +3112,8 @@ int cmd_trace(int argc, const char **argv)
 			"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
 	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
+		     trace__parse_cgroups),
 	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
 		     "ms to wait before starting measurement after program "
 		     "start"),
@@ -3095,6 +3140,11 @@ int cmd_trace(int argc, const char **argv)
 	argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
 				 trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) {
+		usage_with_options_msg(trace_usage, trace_options,
+				       "cgroup monitoring only available in system-wide mode");
+	}
+
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
-- 
2.14.3

[PATCH 15/54] perf auxtrace: Add missing parameters from kernel-doc comments

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Add missing parameters from kernel-doc comments.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520327598-1317-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/auxtrace.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 453c148d2158..e731f55da072 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -130,6 +130,7 @@ struct auxtrace_index {
 /**
  * struct auxtrace - session callbacks to allow AUX area data decoding.
  * @process_event: lets the decoder see all session events
+ * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event
  * @flush_events: process any remaining data
  * @free_events: free resources associated with event processing
  * @free: free resources associated with the session
@@ -301,6 +302,7 @@ struct auxtrace_mmap_params {
  * @parse_snapshot_options: parse snapshot options
  * @reference: provide a 64-bit reference number for auxtrace_event
  * @read_finish: called after reading from an auxtrace mmap
+ * @alignment: alignment (if any) for AUX area data
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
-- 
2.14.3

[PATCH 16/54] perf auxtrace: Rename some buffer-queuing functions

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Rename some buffer-queuing functions in preparation for supporting AUX area
sampling buffers.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520327598-1317-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/auxtrace.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 6470ea2aa25e..6ea840ec5b7f 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -233,9 +233,9 @@ static void *auxtrace_copy_data(u64 size, struct perf_session *session)
 	return p;
 }
 
-static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
-				       unsigned int idx,
-				       struct auxtrace_buffer *buffer)
+static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
+					 unsigned int idx,
+					 struct auxtrace_buffer *buffer)
 {
 	struct auxtrace_queue *queue;
 	int err;
@@ -286,7 +286,7 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 			return -ENOMEM;
 		b->size = BUFFER_LIMIT_FOR_32_BIT;
 		b->consecutive = consecutive;
-		err = auxtrace_queues__add_buffer(queues, idx, b);
+		err = auxtrace_queues__queue_buffer(queues, idx, b);
 		if (err) {
 			auxtrace_buffer__free(b);
 			return err;
@@ -302,10 +302,10 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 	return 0;
 }
 
-static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
-					     struct perf_session *session,
-					     unsigned int idx,
-					     struct auxtrace_buffer *buffer)
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+				       struct perf_session *session,
+				       unsigned int idx,
+				       struct auxtrace_buffer *buffer)
 {
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
@@ -324,7 +324,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
 			return err;
 	}
 
-	return auxtrace_queues__add_buffer(queues, idx, buffer);
+	return auxtrace_queues__queue_buffer(queues, idx, buffer);
 }
 
 static bool filter_cpu(struct perf_session *session, int cpu)
@@ -359,7 +359,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	buffer->size = event->auxtrace.size;
 	idx = event->auxtrace.idx;
 
-	err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+	err = auxtrace_queues__add_buffer(queues, session, idx, buffer);
 	if (err)
 		goto out_err;
 
-- 
2.14.3

[PATCH 17/54] perf auxtrace: Make auxtrace_queues__add_buffer() return buffer_ptr

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

In preparation for supporting AUX area sampling buffers,
auxtrace_queues__add_buffer() needs to be more generic. To that end, make
it return buffer_ptr instead of the caller.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520327598-1317-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/auxtrace.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 6ea840ec5b7f..fb357a00dd86 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -305,8 +305,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 				       struct perf_session *session,
 				       unsigned int idx,
-				       struct auxtrace_buffer *buffer)
+				       struct auxtrace_buffer *buffer,
+				       struct auxtrace_buffer **buffer_ptr)
 {
+	int err;
+
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
 			       session->one_mmap_addr;
@@ -317,14 +320,20 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 		buffer->data_needs_freeing = true;
 	} else if (BITS_PER_LONG == 32 &&
 		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
-		int err;
-
 		err = auxtrace_queues__split_buffer(queues, idx, buffer);
 		if (err)
 			return err;
 	}
 
-	return auxtrace_queues__queue_buffer(queues, idx, buffer);
+	err = auxtrace_queues__queue_buffer(queues, idx, buffer);
+	if (err)
+		return err;
+
+	/* FIXME: Doesn't work for split buffer */
+	if (buffer_ptr)
+		*buffer_ptr = buffer;
+
+	return 0;
 }
 
 static bool filter_cpu(struct perf_session *session, int cpu)
@@ -359,13 +368,11 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	buffer->size = event->auxtrace.size;
 	idx = event->auxtrace.idx;
 
-	err = auxtrace_queues__add_buffer(queues, session, idx, buffer);
+	err = auxtrace_queues__add_buffer(queues, session, idx, buffer,
+					  buffer_ptr);
 	if (err)
 		goto out_err;
 
-	if (buffer_ptr)
-		*buffer_ptr = buffer;
-
 	return 0;
 
 out_err:
-- 
2.14.3

[PATCH 18/54] perf tools: Correct title markers for asciidoctor

[Arnaldo Carvalho de Melo]

From: Takashi Iwai <tiwai@suse.de>

I've tested to process the perf man pages with asciidoctor that is
picker than asciidoc, and it revealed minor syntax errors in some
documents.  Namely, the title markers aren't aligned with the previous
line, hence asciidoctor didn't recognize as titles.

This patch corrects these markers to be processed properly.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307105441.28512-1-tiwai@suse.de
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-data.txt        | 2 +-
 tools/perf/Documentation/perf-ftrace.txt      | 2 +-
 tools/perf/Documentation/perf-kallsyms.txt    | 2 +-
 tools/perf/Documentation/perf-sched.txt       | 2 +-
 tools/perf/Documentation/perf-script-perl.txt | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index 90bb4aabe4f8..c87180764829 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -1,5 +1,5 @@
 perf-data(1)
-==============
+============
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 721a447f046e..b80c84307dc9 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -1,5 +1,5 @@
 perf-ftrace(1)
-=============
+==============
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
index cf9f4040ea5c..f3c620951f6e 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -1,5 +1,5 @@
 perf-kallsyms(1)
-==============
+================
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index c7e50f263887..bb33601a823b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -1,5 +1,5 @@
 perf-sched(1)
-==============
+=============
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index 142606c0ec9c..5a1f68122f50 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -1,5 +1,5 @@
 perf-script-perl(1)
-==================
+===================
 
 NAME
 ----
-- 
2.14.3

[PATCH 19/54] perf pmu: Support wildcards on pmu name in dynamic pmu events

[Arnaldo Carvalho de Melo]

From: Agustin Vega-Frias <agustinv@codeaurora.org>

Starting on v4.12 event parsing code for dynamic pmu events already
supports prefix-based matching of multiple pmus when creating dynamic
events. E.g., in a system with the following dynamic pmus:

    mypmu_0
    mypmu_1
    mypmu_2
    mypmu_4

passing mypmu/<config>/ as an event spec will result in the creation of
the event in all of the pmus. This change expands this matching through
the use of fnmatch so glob-like expressions can be used to create events
in multiple pmus. E.g., in the system described above if a user only
wants to create the event in mypmu_0 and mypmu_1, mypmu_[01]/<config>/
can be passed.

Signed-off-by: Agustin Vega-Frias <agustinv@codeaurora.org>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Timur Tabi <timur@codeaurora.org>
Change-Id: Icb25653fc5d5239c20f3bffdfdf4ab4c9c9bb20b
Link: http://lkml.kernel.org/r/1520454947-16977-1-git-send-email-agustinv@codeaurora.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-list.txt |  8 +++++++-
 tools/perf/Documentation/perf-stat.txt | 13 +++++++++++++
 tools/perf/util/parse-events.l         |  2 +-
 tools/perf/util/parse-events.y         | 14 ++++++++++++--
 4 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index e2a897ae3596..2549c34a7895 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -141,7 +141,13 @@ on the first memory controller on socket 0 of a Intel Xeon system
 
 Each memory controller has its own PMU.  Measuring the complete system
 bandwidth would require specifying all imc PMUs (see perf list output),
-and adding the values together.
+and adding the values together. To simplify creation of multiple events,
+prefix and glob matching is supported in the PMU name, and the prefix
+'uncore_' is also ignored when performing the match. So the command above
+can be expanded to all memory controllers by using the syntaxes:
+
+  perf stat -C 0 -a imc/cas_count_read/,imc/cas_count_write/ -I 1000 ...
+  perf stat -C 0 -a *imc*/cas_count_read/,*imc*/cas_count_write/ -I 1000 ...
 
 This example measures the combined core power every second
 
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 2b38e222016a..628026dbedc5 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -49,6 +49,13 @@ report::
 	  parameters are defined by corresponding entries in
 	  /sys/bus/event_source/devices/<pmu>/format/*
 
+	Note that the last two syntaxes support prefix and glob matching in
+	the PMU name to simplify creation of events accross multiple instances
+	of the same type of PMU in large systems (e.g. memory controller PMUs).
+	Multiple PMU instances are typical for uncore PMUs, so the prefix
+	'uncore_' is also ignored when performing this match.
+
+
 -i::
 --no-inherit::
         child tasks do not inherit counters
@@ -260,6 +267,12 @@ taskset.
 --no-merge::
 Do not merge results from same PMUs.
 
+When multiple events are created from a single event alias, stat will,
+by default, aggregate the event counts and show the result in a single
+row. This option disables that behavior and shows the individual events
+and counts. Aliases are listed immediately after the Kernel PMU events
+by perf list.
+
 --smi-cost::
 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 655ecff636a8..a1a01b1ac8b8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -175,7 +175,7 @@ bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index e81a20ea8d7d..dedf184b5bed 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -8,6 +8,7 @@
 
 #define YYDEBUG 1
 
+#include <fnmatch.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/types.h>
@@ -234,6 +235,10 @@ PE_NAME opt_event_config
 	if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
+		char *pattern;
+
+		if (asprintf(&pattern, "%s*", $1) < 0)
+			YYABORT;
 
 		while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 			char *name = pmu->name;
@@ -241,14 +246,19 @@ PE_NAME opt_event_config
 			if (!strncmp(name, "uncore_", 7) &&
 			    strncmp($1, "uncore_", 7))
 				name += 7;
-			if (!strncmp($1, name, strlen($1))) {
-				if (parse_events_copy_term_list(orig_terms, &terms))
+			if (!fnmatch(pattern, name, 0)) {
+				if (parse_events_copy_term_list(orig_terms, &terms)) {
+					free(pattern);
 					YYABORT;
+				}
 				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
 					ok++;
 				parse_events_terms__delete(terms);
 			}
 		}
+
+		free(pattern);
+
 		if (!ok)
 			YYABORT;
 	}
-- 
2.14.3

[PATCH 20/54] perf pmu: Display pmu name when printing unmerged events in stat

[Arnaldo Carvalho de Melo]

From: Agustin Vega-Frias <agustinv@codeaurora.org>

To simplify creation of events accross multiple instances of the same
type of PMU stat supports two methods for creating multiple events from
a single event specification:

1. A prefix or glob can be used in the PMU name.
2. Aliases, which are listed immediately after the Kernel PMU events
   by perf list, are used.

When the --no-merge option is passed and these events are displayed
individually the PMU name is lost and it's not possible to see which
count corresponds to which pmu:

    $ perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    67      l3cache/read-miss/
                    67      l3cache/read-miss/
                    63      l3cache/read-miss/
                    60      l3cache/read-miss/

           0.001675706 seconds time elapsed

    $ perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    12      l3cache_read_miss
                    17      l3cache_read_miss
                    10      l3cache_read_miss
                     8      l3cache_read_miss

           0.001661305 seconds time elapsed

This change adds the original pmu name to the event. For dynamic pmu
events the pmu name is restored in the event name:

    $ perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    63      l3cache_0_3/read-miss/
                    74      l3cache_0_1/read-miss/
                    64      l3cache_0_2/read-miss/
                    74      l3cache_0_0/read-miss/

           0.001675706 seconds time elapsed

For alias events the name is added after the event name:

    $ perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    10      l3cache_read_miss [l3cache_0_3]
                    12      l3cache_read_miss [l3cache_0_1]
                    10      l3cache_read_miss [l3cache_0_2]
                    17      l3cache_read_miss [l3cache_0_0]

           0.001661305 seconds time elapsed

Signed-off-by: Agustin Vega-Frias <agustinv@codeaurora.org>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Timur Tabi <timur@codeaurora.org>
Cc: linux-arm-kernel@lists.infradead.org
Change-Id: I8056b9eda74bda33e95065056167ad96e97cb1fb
Link: http://lkml.kernel.org/r/1520345084-42646-3-git-send-email-agustinv@codeaurora.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c      | 29 ++++++++++++++++++++++++++++-
 tools/perf/util/evsel.c        |  1 +
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c |  8 +++++++-
 4 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3a022b3e5c02..0fa9ea3a6d92 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1251,6 +1251,31 @@ static void aggr_update_shadow(void)
 	}
 }
 
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+}
+
 static void collect_all_aliases(struct perf_evsel *counter,
 			    void (*cb)(struct perf_evsel *counter, void *data,
 				       bool first),
@@ -1279,7 +1304,9 @@ static bool collect_data(struct perf_evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(counter, data, true);
-	if (!no_merge && counter->auto_merge_stats)
+	if (no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
 		collect_all_aliases(counter, cb, data);
 	return true;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f1f883bb41a8..e937894654b2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->metric_name   = NULL;
 	evsel->metric_events = NULL;
 	evsel->collect_stat  = false;
+	evsel->pmu_name      = NULL;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 92ba001b627f..55ae1cda7396 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -142,6 +142,7 @@ struct perf_evsel {
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
 	bool			weak_group;
+	const char		*pmu_name;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 34589c427e52..bafc91edcb44 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
-		return evsel ? 0 : -ENOMEM;
+		if (evsel) {
+			evsel->pmu_name = name;
+			return 0;
+		} else {
+			return -ENOMEM;
+		}
 	}
 
 	if (perf_pmu__check_alias(pmu, head_config, &info))
@@ -1276,6 +1281,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->snapshot = info.snapshot;
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
+		evsel->pmu_name = name;
 	}
 
 	return evsel ? 0 : -ENOMEM;
-- 
2.14.3

[PATCH 21/54] perf pmu: Auto-merge PMU events created by prefix or glob match

[Arnaldo Carvalho de Melo]

From: Agustin Vega-Frias <agustinv@codeaurora.org>

Auto-merge for these events was disabled when auto-merging of non-alias
events was disabled in commit 63ce844 (perf stat: Only auto-merge events
that are PMU aliases).

Non-merging of legacy events is preserved:

    $ perf stat -ag -e cache-misses,cache-misses sleep 1

     Performance counter stats for 'system wide':

                86,323      cache-misses
                86,323      cache-misses

           1.002623307 seconds time elapsed

But prefix or glob matching auto-merges the events created:

    $ perf stat -a -e l3cache/read-miss/ sleep 1

     Performance counter stats for 'system wide':

                   328      l3cache/read-miss/

           1.002627008 seconds time elapsed

    $ perf stat -a -e l3cache_0_[01]/read-miss/ sleep 1

     Performance counter stats for 'system wide':

                   172      l3cache/read-miss/

           1.002627008 seconds time elapsed

As with events created with aliases, auto-merging can be suppressed with
the --no-merge option:

    $ perf stat -a -e l3cache/read-miss/ --no-merge sleep 1

     Performance counter stats for 'system wide':

                    67      l3cache/read-miss/
                    67      l3cache/read-miss/
                    63      l3cache/read-miss/
                    60      l3cache/read-miss/

           1.002622192 seconds time elapsed

Signed-off-by: Agustin Vega-Frias <agustinv@codeaurora.org>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Timur Tabi <timur@codeaurora.org>
Cc: linux-arm-kernel@lists.infradead.org
Change-Id: I0a47eed54c05e1982ca964d743b37f50f60c508c
Link: http://lkml.kernel.org/r/1520345084-42646-4-git-send-email-agustinv@codeaurora.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-stat.txt | 14 +++++++++-----
 tools/perf/util/parse-events.c         | 13 +++----------
 tools/perf/util/parse-events.h         |  2 +-
 tools/perf/util/parse-events.y         |  4 ++--
 4 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 628026dbedc5..f15b306be183 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -267,11 +267,15 @@ taskset.
 --no-merge::
 Do not merge results from same PMUs.
 
-When multiple events are created from a single event alias, stat will,
-by default, aggregate the event counts and show the result in a single
-row. This option disables that behavior and shows the individual events
-and counts. Aliases are listed immediately after the Kernel PMU events
-by perf list.
+When multiple events are created from a single event specification,
+stat will, by default, aggregate the event counts and show the result
+in a single row. This option disables that behavior and shows
+the individual events and counts.
+
+Multiple events are created from a single event specification when:
+1. Prefix or glob matching is used for the PMU name.
+2. Aliases, which are listed immediately after the Kernel PMU events
+   by perf list, are used.
 
 --smi-cost::
 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bafc91edcb44..4e80ca320399 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1217,7 +1217,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			 get_config_name(head_config), &config_terms);
 }
 
-static int __parse_events_add_pmu(struct parse_events_state *parse_state,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config, bool auto_merge_stats)
 {
@@ -1287,13 +1287,6 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	return evsel ? 0 : -ENOMEM;
 }
 
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
-			 struct list_head *head_config)
-{
-	return __parse_events_add_pmu(parse_state, list, name, head_config, false);
-}
-
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str, struct list_head **listp)
 {
@@ -1323,8 +1316,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 					return -1;
 				list_add_tail(&term->list, head);
 
-				if (!__parse_events_add_pmu(parse_state, list,
-							    pmu->name, head, true)) {
+				if (!parse_events_add_pmu(parse_state, list,
+							  pmu->name, head, true)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					ok++;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 88108cd11b4c..5015cfd58277 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -167,7 +167,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config);
+			 struct list_head *head_config, bool auto_merge_stats);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index dedf184b5bed..7afeb80cc39e 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -232,7 +232,7 @@ PE_NAME opt_event_config
 		YYABORT;
 
 	ALLOC_LIST(list);
-	if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
+	if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
 		char *pattern;
@@ -251,7 +251,7 @@ PE_NAME opt_event_config
 					free(pattern);
 					YYABORT;
 				}
-				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
+				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true))
 					ok++;
 				parse_events_terms__delete(terms);
 			}
-- 
2.14.3

[PATCH 22/54] perf evlist: Store 'overwrite' in struct perf_mmap

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

It has been determined that the map is for overwrite mode
(evlist->overwrite_mmap) or non-overwrite mode (evlist->mmap) when
calling perf_evlist__alloc_mmap().

Store the information in struct perf_mmap, which will be used later to
simplify the perf_mmap__read*() interfaces.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 8 +++++---
 tools/perf/util/mmap.h   | 1 +
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 41a4666f1519..a59281d64368 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -722,7 +722,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 	zfree(&evlist->overwrite_mmap);
 }
 
-static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist,
+						 bool overwrite)
 {
 	int i;
 	struct perf_mmap *map;
@@ -736,6 +737,7 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		map[i].fd = -1;
+		map[i].overwrite = overwrite;
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last
@@ -779,7 +781,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 			maps = evlist->overwrite_mmap;
 
 			if (!maps) {
-				maps = perf_evlist__alloc_mmap(evlist);
+				maps = perf_evlist__alloc_mmap(evlist, true);
 				if (!maps)
 					return -1;
 				evlist->overwrite_mmap = maps;
@@ -1029,7 +1031,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	struct mmap_params mp;
 
 	if (!evlist->mmap)
-		evlist->mmap = perf_evlist__alloc_mmap(evlist);
+		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
 	if (!evlist->mmap)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index ec7d3a24e276..71137977af28 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -20,6 +20,7 @@ struct perf_mmap {
 	int		 fd;
 	refcount_t	 refcnt;
 	u64		 prev;
+	bool		 overwrite;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
 };
-- 
2.14.3

[PATCH 23/54] perf mmap: Store mmap scope in struct perf_mmap()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

There is too much boilerplate in the perf_mmap__read*() interfaces.

The 'start' and 'end' variables should be stored in struct perf_mmap at
initialization. They will be used later.

The old 'startp' and 'endp' pointers are used by perf_mmap__read_event()
now.  They cannot be removed. So the old 'startp/endp' and new
'md->start/md->end' will exist simultaneously now.  The old one will be
removed later.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-2-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/mmap.c | 12 ++++++++----
 tools/perf/util/mmap.h |  2 ++
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 4f27c464ce0b..09acaf7392bb 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -250,13 +250,15 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 
 	*startp = overwrite ? head : old;
 	*endp = overwrite ? old : head;
+	md->start = md->overwrite ? head : old;
+	md->end = md->overwrite ? old : head;
 
-	if (*startp == *endp)
+	if (md->start == md->end)
 		return -EAGAIN;
 
-	size = *endp - *startp;
+	size = md->end - md->start;
 	if (size > (unsigned long)(md->mask) + 1) {
-		if (!overwrite) {
+		if (!md->overwrite) {
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 			md->prev = head;
@@ -268,8 +270,10 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 		 * Backward ring buffer is full. We still have a chance to read
 		 * most of data from it.
 		 */
-		if (overwrite_rb_find_range(data, md->mask, head, startp, endp))
+		if (overwrite_rb_find_range(data, md->mask, head, &md->start, &md->end))
 			return -EINVAL;
+		*startp = md->start;
+		*endp = md->end;
 	}
 
 	return 0;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 71137977af28..9359e934ab14 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -20,6 +20,8 @@ struct perf_mmap {
 	int		 fd;
 	refcount_t	 refcnt;
 	u64		 prev;
+	u64		 start;
+	u64		 end;
 	bool		 overwrite;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
-- 
2.14.3

[PATCH 24/54] perf mmap: Use the stored scope data in perf_mmap__push()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

Using the 'start' and 'end' which are stored in struct perf_mmap to
replace the temporary 'start' and 'end'.
The temporary variables will be discarded later.

It doesn't need to pass 'overwrite' to perf_mmap__push(). It's stored in
struct perf_mmap.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-3-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c |  2 +-
 tools/perf/util/mmap.c      | 24 ++++++++++++------------
 tools/perf/util/mmap.h      |  4 ++--
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 14d82f0fe5cc..753ffcecf254 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -533,7 +533,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
 		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) {
+			if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 09acaf7392bb..8c1d033638c2 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -279,8 +279,8 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 	return 0;
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite,
-		    void *to, int push(void *to, void *buf, size_t size))
+int perf_mmap__push(struct perf_mmap *md, void *to,
+		    int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
 	u64 end, start;
@@ -289,16 +289,16 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 	void *buf;
 	int rc = 0;
 
-	rc = perf_mmap__read_init(md, overwrite, &start, &end);
+	rc = perf_mmap__read_init(md, md->overwrite, &start, &end);
 	if (rc < 0)
 		return (rc == -EAGAIN) ? 0 : -1;
 
-	size = end - start;
+	size = md->end - md->start;
 
-	if ((start & md->mask) + size != (end & md->mask)) {
-		buf = &data[start & md->mask];
-		size = md->mask + 1 - (start & md->mask);
-		start += size;
+	if ((md->start & md->mask) + size != (md->end & md->mask)) {
+		buf = &data[md->start & md->mask];
+		size = md->mask + 1 - (md->start & md->mask);
+		md->start += size;
 
 		if (push(to, buf, size) < 0) {
 			rc = -1;
@@ -306,9 +306,9 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 		}
 	}
 
-	buf = &data[start & md->mask];
-	size = end - start;
-	start += size;
+	buf = &data[md->start & md->mask];
+	size = md->end - md->start;
+	md->start += size;
 
 	if (push(to, buf, size) < 0) {
 		rc = -1;
@@ -316,7 +316,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, overwrite);
+	perf_mmap__consume(md, md->overwrite);
 out:
 	return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 9359e934ab14..65f5b26d8668 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -93,8 +93,8 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map,
 					bool overwrite,
 					u64 *startp, u64 end);
 
-int perf_mmap__push(struct perf_mmap *md, bool backward,
-		    void *to, int push(void *to, void *buf, size_t size));
+int perf_mmap__push(struct perf_mmap *md, void *to,
+		    int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
-- 
2.14.3

[PATCH 25/54] perf mmap: Use the stored data in perf_mmap__read_event()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

Using the 'start', 'end' and 'overwrite' which are stored in
struct perf_mmap to replace the parameters of perf_mmap__read_event().
The parameters will be discarded later.

No functional change.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-4-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/mmap.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 8c1d033638c2..2933942abfe2 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -76,8 +76,9 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
  * perf_mmap__read_done()
  */
 union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite,
-					u64 *startp, u64 end)
+					bool overwrite __maybe_unused,
+					u64 *startp __maybe_unused,
+					u64 end __maybe_unused)
 {
 	union perf_event *event;
 
@@ -87,17 +88,14 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map,
 	if (!refcount_read(&map->refcnt))
 		return NULL;
 
-	if (startp == NULL)
-		return NULL;
-
 	/* non-overwirte doesn't pause the ringbuffer */
-	if (!overwrite)
-		end = perf_mmap__read_head(map);
+	if (!map->overwrite)
+		map->end = perf_mmap__read_head(map);
 
-	event = perf_mmap__read(map, startp, end);
+	event = perf_mmap__read(map, &map->start, map->end);
 
-	if (!overwrite)
-		map->prev = *startp;
+	if (!map->overwrite)
+		map->prev = map->start;
 
 	return event;
 }
-- 
2.14.3

[PATCH 26/54] perf mmap: Use stored 'overwrite' in perf_mmap__consume()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

The 'overwrite' is set at allocation. It will not be changed.  Using it
to replace the parameter of perf_mmap__consume().  The parameters will
be discarded later.

No functional change.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/mmap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 2933942abfe2..8a2dac90056c 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -118,9 +118,9 @@ void perf_mmap__put(struct perf_mmap *map)
 		perf_mmap__munmap(map);
 }
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite __maybe_unused)
 {
-	if (!overwrite) {
+	if (!map->overwrite) {
 		u64 old = map->prev;
 
 		perf_mmap__write_tail(map, old);
-- 
2.14.3

[PATCH 27/54] perf mmap: Simplify perf_mmap__consume()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

It isn't necessary to pass the 'overwrite' argument to
perf_mmap__consume().  Discard it.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-6-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +-
 tools/perf/builtin-kvm.c                     | 4 ++--
 tools/perf/builtin-top.c                     | 2 +-
 tools/perf/builtin-trace.c                   | 2 +-
 tools/perf/tests/code-reading.c              | 2 +-
 tools/perf/tests/keep-tracking.c             | 2 +-
 tools/perf/tests/mmap-basic.c                | 2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  | 2 +-
 tools/perf/tests/perf-record.c               | 2 +-
 tools/perf/tests/sw-clock.c                  | 2 +-
 tools/perf/tests/switch-tracking.c           | 2 +-
 tools/perf/tests/task-exit.c                 | 2 +-
 tools/perf/util/mmap.c                       | 6 +++---
 tools/perf/util/mmap.h                       | 2 +-
 tools/perf/util/python.c                     | 2 +-
 15 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 7f82d91ef473..a9bc77df6a65 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -134,7 +134,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				comm2_time = sample.time;
 			}
 next_event:
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 		}
 		perf_mmap__read_done(md);
 	}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index d2703d3b8366..165c044616b6 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -760,7 +760,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}
@@ -770,7 +770,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 		 * FIXME: Here we can't consume the event, as perf_session__queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
 		 */
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 
 		if (err) {
 			pr_err("Failed to enqueue sample: %d\n", err);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index bb4f9fafd11d..11b4a413039f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -879,7 +879,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		} else
 			++session->evlist->stats.nr_unknown_events;
 next_event:
-		perf_mmap__consume(md, opts->overwrite);
+		perf_mmap__consume(md);
 	}
 
 	perf_mmap__read_done(md);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5b81060a8117..27eadf3018c6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2522,7 +2522,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 			trace__handle_event(trace, event, &sample);
 next_event:
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 
 			if (interrupted)
 				goto out_disable;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 03ed8c77b1bb..f7c199acb7ac 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -420,7 +420,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 
 		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 			if (ret < 0)
 				return ret;
 		}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 4590d8fb91ab..1f1db5965d05 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -42,7 +42,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 		}
 		perf_mmap__read_done(md);
 	}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 44c58d69cd87..f473e106aeba 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -135,7 +135,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			goto out_delete_evlist;
 		}
 		nr_events[evsel->idx]++;
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 	}
 	perf_mmap__read_done(md);
 
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 620b21023f72..7837ae936679 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -101,7 +101,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 				++nr_events;
 
 				if (type != PERF_RECORD_SAMPLE) {
-					perf_mmap__consume(md, false);
+					perf_mmap__consume(md);
 					continue;
 				}
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 31f3f70adca6..6ff5f99b3e0e 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -272,7 +272,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 					++errs;
 				}
 
-				perf_mmap__consume(md, false);
+				perf_mmap__consume(md);
 			}
 			perf_mmap__read_done(md);
 		}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index e6320e267ba5..b58297b9a83d 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -114,7 +114,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		total_periods += sample.period;
 		nr_samples++;
 next_event:
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 	}
 	perf_mmap__read_done(md);
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 10c4dcdc2324..dbf9e20f7d56 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -270,7 +270,7 @@ static int process_events(struct perf_evlist *evlist,
 		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
-			 perf_mmap__consume(md, false);
+			 perf_mmap__consume(md);
 			if (ret < 0)
 				goto out_free_nodes;
 		}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 02b0888b72a3..5aa2e68e9d05 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -120,7 +120,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 	}
 	perf_mmap__read_done(md);
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 8a2dac90056c..62312e06d75b 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -118,7 +118,7 @@ void perf_mmap__put(struct perf_mmap *map)
 		perf_mmap__munmap(map);
 }
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite __maybe_unused)
+void perf_mmap__consume(struct perf_mmap *map)
 {
 	if (!map->overwrite) {
 		u64 old = map->prev;
@@ -260,7 +260,7 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 			md->prev = head;
-			perf_mmap__consume(md, overwrite);
+			perf_mmap__consume(md);
 			return -EAGAIN;
 		}
 
@@ -314,7 +314,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, md->overwrite);
+	perf_mmap__consume(md);
 out:
 	return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 65f5b26d8668..043916a20de6 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -66,7 +66,7 @@ void perf_mmap__munmap(struct perf_mmap *map);
 void perf_mmap__get(struct perf_mmap *map);
 void perf_mmap__put(struct perf_mmap *map);
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
+void perf_mmap__consume(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 35fb5ef7d290..ca077f8be1f0 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1013,7 +1013,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
-		perf_mmap__consume(md, false);
+		perf_mmap__consume(md);
 
 		if (err)
 			return PyErr_Format(PyExc_OSError,
-- 
2.14.3

[PATCH 28/54] perf mmap: Simplify perf_mmap__read_event()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

It isn't necessary to pass the 'overwrite', 'start' and 'end' argument
to perf_mmap__read_event().  Discard them.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-7-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +-
 tools/perf/builtin-kvm.c                     | 2 +-
 tools/perf/builtin-top.c                     | 2 +-
 tools/perf/builtin-trace.c                   | 2 +-
 tools/perf/tests/backward-ring-buffer.c      | 2 +-
 tools/perf/tests/bpf.c                       | 2 +-
 tools/perf/tests/code-reading.c              | 2 +-
 tools/perf/tests/keep-tracking.c             | 2 +-
 tools/perf/tests/mmap-basic.c                | 2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  | 2 +-
 tools/perf/tests/perf-record.c               | 2 +-
 tools/perf/tests/sw-clock.c                  | 2 +-
 tools/perf/tests/switch-tracking.c           | 2 +-
 tools/perf/tests/task-exit.c                 | 2 +-
 tools/perf/util/mmap.c                       | 5 +----
 tools/perf/util/mmap.h                       | 4 +---
 tools/perf/util/python.c                     | 2 +-
 17 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index a9bc77df6a65..17cf7fc3c7d5 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -115,7 +115,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			if (event->header.type != PERF_RECORD_COMM ||
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 165c044616b6..e9f69b8f8e25 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -757,7 +757,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	if (err < 0)
 		return (err == -EAGAIN) ? 0 : -1;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
 			perf_mmap__consume(md);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 11b4a413039f..eb19cf92a388 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -824,7 +824,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
 		return;
 
-	while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		ret = perf_evlist__parse_sample(evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 27eadf3018c6..29fda506ac75 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2509,7 +2509,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			++trace->nr_events;
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index e0b1b414d466..e0eae1053ddc 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -36,7 +36,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 		u64 start, end;
 
 		perf_mmap__read_init(map, true, &start, &end);
-		while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(map)) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 09c9c9f9e827..384c20f4c902 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -183,7 +183,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			const u32 type = event->header.type;
 
 			if (type == PERF_RECORD_SAMPLE)
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f7c199acb7ac..f7919666bc2c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -418,7 +418,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
 			perf_mmap__consume(md);
 			if (ret < 0)
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 1f1db5965d05..ad477b7cf238 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -36,7 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 		md = &evlist->mmap[i];
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&
 			    (pid_t)event->comm.pid == getpid() &&
 			    (pid_t)event->comm.tid == getpid() &&
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index f473e106aeba..7790eb3303e6 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -112,7 +112,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 7837ae936679..b0be2da65da7 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -93,7 +93,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 			if (perf_mmap__read_init(md, false, &start, &end) < 0)
 				continue;
 
-			while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+			while ((event = perf_mmap__read_event(md)) != NULL) {
 				const u32 type = event->header.type;
 				int tp_flags;
 				struct perf_sample sample;
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 6ff5f99b3e0e..59be0942b787 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -171,7 +171,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 			if (perf_mmap__read_init(md, false, &start, &end) < 0)
 				continue;
 
-			while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+			while ((event = perf_mmap__read_event(md)) != NULL) {
 				const u32 type = event->header.type;
 				const char *name = perf_event__name(type);
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index b58297b9a83d..403f2d9cee96 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -99,7 +99,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index dbf9e20f7d56..99839de3caee 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -267,7 +267,7 @@ static int process_events(struct perf_evlist *evlist,
 		if (perf_mmap__read_init(md, false, &start, &end) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
 			 perf_mmap__consume(md);
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5aa2e68e9d05..2df0c0573e2c 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -116,7 +116,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 62312e06d75b..2fbe4c8a02d2 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -75,10 +75,7 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
  * }
  * perf_mmap__read_done()
  */
-union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite __maybe_unused,
-					u64 *startp __maybe_unused,
-					u64 end __maybe_unused)
+union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 {
 	union perf_event *event;
 
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 043916a20de6..ae9499b80110 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -89,9 +89,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 
-union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite,
-					u64 *startp, u64 end);
+union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
 		    int push(void *to, void *buf, size_t size));
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ca077f8be1f0..4798db93e7ee 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -995,7 +995,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	if (perf_mmap__read_init(md, false, &start, &end) < 0)
 		goto end;
 
-	event = perf_mmap__read_event(md, false, &start, end);
+	event = perf_mmap__read_event(md);
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
-- 
2.14.3

[PATCH 29/54] perf mmap: Simplify perf_mmap__read_init()

[Arnaldo Carvalho de Melo]

From: Kan Liang <kan.liang@linux.intel.com>

It isn't necessary to pass the 'start', 'end' and 'overwrite' arguments
to perf_mmap__read_init().  The data is stored in the struct perf_mmap.

Discard the parameters.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1520350567-80082-8-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  3 +--
 tools/perf/builtin-kvm.c                     |  3 +--
 tools/perf/builtin-top.c                     |  3 +--
 tools/perf/builtin-trace.c                   |  3 +--
 tools/perf/tests/backward-ring-buffer.c      |  3 +--
 tools/perf/tests/bpf.c                       |  3 +--
 tools/perf/tests/code-reading.c              |  3 +--
 tools/perf/tests/keep-tracking.c             |  3 +--
 tools/perf/tests/mmap-basic.c                |  3 +--
 tools/perf/tests/openat-syscall-tp-fields.c  |  3 +--
 tools/perf/tests/perf-record.c               |  3 +--
 tools/perf/tests/sw-clock.c                  |  3 +--
 tools/perf/tests/switch-tracking.c           |  3 +--
 tools/perf/tests/task-exit.c                 |  3 +--
 tools/perf/util/mmap.c                       | 10 ++--------
 tools/perf/util/mmap.h                       |  3 +--
 tools/perf/util/python.c                     |  3 +--
 17 files changed, 18 insertions(+), 40 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 17cf7fc3c7d5..7a7721604b86 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -61,7 +61,6 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	u64 test_tsc, comm1_tsc, comm2_tsc;
 	u64 test_time, comm1_time = 0, comm2_time = 0;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
@@ -112,7 +111,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index e9f69b8f8e25..72e2ca096bf5 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -746,14 +746,13 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 	struct perf_evlist *evlist = kvm->evlist;
 	union perf_event *event;
 	struct perf_mmap *md;
-	u64 end, start;
 	u64 timestamp;
 	s64 n = 0;
 	int err;
 
 	*mmap_time = ULLONG_MAX;
 	md = &evlist->mmap[idx];
-	err = perf_mmap__read_init(md, false, &start, &end);
+	err = perf_mmap__read_init(md);
 	if (err < 0)
 		return (err == -EAGAIN) ? 0 : -1;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index eb19cf92a388..0a26b56afcc5 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -817,11 +817,10 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	struct perf_session *session = top->session;
 	union perf_event *event;
 	struct machine *machine;
-	u64 end, start;
 	int ret;
 
 	md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
-	if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		return;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 29fda506ac75..87b95c9410b4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2503,10 +2503,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 		struct perf_mmap *md;
-		u64 end, start;
 
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index e0eae1053ddc..6d598cc071ae 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,9 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		struct perf_mmap *map = &evlist->overwrite_mmap[i];
 		union perf_event *event;
-		u64 start, end;
 
-		perf_mmap__read_init(map, true, &start, &end);
+		perf_mmap__read_init(map);
 		while ((event = perf_mmap__read_event(map)) != NULL) {
 			const u32 type = event->header.type;
 
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 384c20f4c902..79b54f8ddebf 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -177,10 +177,9 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 		struct perf_mmap *md;
-		u64 end, start;
 
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f7919666bc2c..99936352df4f 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -410,12 +410,11 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 {
 	union perf_event *event;
 	struct perf_mmap *md;
-	u64 end, start;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index ad477b7cf238..17c46f3e6f1e 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -28,13 +28,12 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 {
 	union perf_event *event;
 	struct perf_mmap *md;
-	u64 end, start;
 	int i, found;
 
 	found = 0;
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 		while ((event = perf_mmap__read_event(md)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 7790eb3303e6..bb8e6bcb0d96 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -39,7 +39,6 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 	struct perf_evsel *evsels[nsyscalls], *evsel;
 	char sbuf[STRERR_BUFSIZE];
 	struct perf_mmap *md;
-	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
@@ -109,7 +108,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		}
 
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto out_init;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index b0be2da65da7..344dc3ac2469 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -87,10 +87,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
 			struct perf_mmap *md;
-			u64 end, start;
 
 			md = &evlist->mmap[i];
-			if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			if (perf_mmap__read_init(md) < 0)
 				continue;
 
 			while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 59be0942b787..34394cc05077 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -165,10 +165,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
 			struct perf_mmap *md;
-			u64 end, start;
 
 			md = &evlist->mmap[i];
-			if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			if (perf_mmap__read_init(md) < 0)
 				continue;
 
 			while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 403f2d9cee96..f9490b237893 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -40,7 +40,6 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	attr.sample_freq = 500;
 
@@ -96,7 +95,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	perf_evlist__disable(evlist);
 
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto out_init;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 99839de3caee..9b5be51e5e7b 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -259,12 +259,11 @@ static int process_events(struct perf_evlist *evlist,
 	LIST_HEAD(events);
 	struct event_node *events_array, *node;
 	struct perf_mmap *md;
-	u64 end, start;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
 		while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 2df0c0573e2c..e92fa6029ac7 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -48,7 +48,6 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	signal(SIGCHLD, sig_handler);
 
@@ -113,7 +112,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 retry:
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto out_init;
 
 	while ((event = perf_mmap__read_event(md)) != NULL) {
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 2fbe4c8a02d2..074c4fd3b67e 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -235,16 +235,13 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6
 /*
  * Report the start and end of the available data in ringbuffer
  */
-int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
-			 u64 *startp, u64 *endp)
+int perf_mmap__read_init(struct perf_mmap *md)
 {
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 
-	*startp = overwrite ? head : old;
-	*endp = overwrite ? old : head;
 	md->start = md->overwrite ? head : old;
 	md->end = md->overwrite ? old : head;
 
@@ -267,8 +264,6 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 		 */
 		if (overwrite_rb_find_range(data, md->mask, head, &md->start, &md->end))
 			return -EINVAL;
-		*startp = md->start;
-		*endp = md->end;
 	}
 
 	return 0;
@@ -278,13 +273,12 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 		    int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
-	u64 end, start;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 	void *buf;
 	int rc = 0;
 
-	rc = perf_mmap__read_init(md, md->overwrite, &start, &end);
+	rc = perf_mmap__read_init(md);
 	if (rc < 0)
 		return (rc == -EAGAIN) ? 0 : -1;
 
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index ae9499b80110..d82294db1295 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -96,7 +96,6 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
-int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
-			 u64 *startp, u64 *endp);
+int perf_mmap__read_init(struct perf_mmap *md);
 void perf_mmap__read_done(struct perf_mmap *map);
 #endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4798db93e7ee..b956868fd445 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -984,7 +984,6 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
 	struct perf_mmap *md;
-	u64 end, start;
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -992,7 +991,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		return NULL;
 
 	md = &evlist->mmap[cpu];
-	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		goto end;
 
 	event = perf_mmap__read_event(md);
-- 
2.14.3

[PATCH 30/54] perf intel-pt: Fix overlap detection to identify consecutive buffers correctly

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Overlap detection was not not updating the buffer's 'consecutive' flag.
Marking buffers consecutive has the advantage that decoding begins from
the start of the buffer instead of the first PSB. Fix overlap detection
to identify consecutive buffers correctly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1520431349-30689-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  | 62 ++++++++++------------
 .../perf/util/intel-pt-decoder/intel-pt-decoder.h  |  2 +-
 tools/perf/util/intel-pt.c                         |  5 +-
 3 files changed, 34 insertions(+), 35 deletions(-)

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index aa1593ce551d..00f25f4b5f48 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -2390,14 +2390,6 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 	return &decoder->state;
 }
 
-static bool intel_pt_at_psb(unsigned char *buf, size_t len)
-{
-	if (len < INTEL_PT_PSB_LEN)
-		return false;
-	return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR,
-		      INTEL_PT_PSB_LEN);
-}
-
 /**
  * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet.
  * @buf: pointer to buffer pointer
@@ -2486,6 +2478,7 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  * @buf: buffer
  * @len: size of buffer
  * @tsc: TSC value returned
+ * @rem: returns remaining size when TSC is found
  *
  * Find a TSC packet in @buf and return the TSC value.  This function assumes
  * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a
@@ -2493,7 +2486,8 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  *
  * Return: %true if TSC is found, false otherwise.
  */
-static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
+static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc,
+			      size_t *rem)
 {
 	struct intel_pt_pkt packet;
 	int ret;
@@ -2504,6 +2498,7 @@ static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
 			return false;
 		if (packet.type == INTEL_PT_TSC) {
 			*tsc = packet.payload;
+			*rem = len;
 			return true;
 		}
 		if (packet.type == INTEL_PT_PSBEND)
@@ -2554,6 +2549,8 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
  * @len_a: size of first buffer
  * @buf_b: second buffer
  * @len_b: size of second buffer
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * If the trace contains TSC we can look at the last TSC of @buf_a and the
  * first TSC of @buf_b in order to determine if the buffers overlap, and then
@@ -2566,33 +2563,41 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 						size_t len_a,
 						unsigned char *buf_b,
-						size_t len_b)
+						size_t len_b, bool *consecutive)
 {
 	uint64_t tsc_a, tsc_b;
 	unsigned char *p;
-	size_t len;
+	size_t len, rem_a, rem_b;
 
 	p = intel_pt_last_psb(buf_a, len_a);
 	if (!p)
 		return buf_b; /* No PSB in buf_a => no overlap */
 
 	len = len_a - (p - buf_a);
-	if (!intel_pt_next_tsc(p, len, &tsc_a)) {
+	if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) {
 		/* The last PSB+ in buf_a is incomplete, so go back one more */
 		len_a -= len;
 		p = intel_pt_last_psb(buf_a, len_a);
 		if (!p)
 			return buf_b; /* No full PSB+ => assume no overlap */
 		len = len_a - (p - buf_a);
-		if (!intel_pt_next_tsc(p, len, &tsc_a))
+		if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a))
 			return buf_b; /* No TSC in buf_a => assume no overlap */
 	}
 
 	while (1) {
 		/* Ignore PSB+ with no TSC */
-		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) &&
-		    intel_pt_tsc_cmp(tsc_a, tsc_b) < 0)
-			return buf_b; /* tsc_a < tsc_b => no overlap */
+		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b, &rem_b)) {
+			int cmp = intel_pt_tsc_cmp(tsc_a, tsc_b);
+
+			/* Same TSC, so buffers are consecutive */
+			if (!cmp && rem_b >= rem_a) {
+				*consecutive = true;
+				return buf_b + len_b - (rem_b - rem_a);
+			}
+			if (cmp < 0)
+				return buf_b; /* tsc_a < tsc_b => no overlap */
+		}
 
 		if (!intel_pt_step_psb(&buf_b, &len_b))
 			return buf_b + len_b; /* No PSB in buf_b => no data */
@@ -2606,6 +2611,8 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  * @buf_b: second buffer
  * @len_b: size of second buffer
  * @have_tsc: can use TSC packets to detect overlap
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * When trace samples or snapshots are recorded there is the possibility that
  * the data overlaps.  Note that, for the purposes of decoding, data is only
@@ -2616,7 +2623,7 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  */
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc)
+				     bool have_tsc, bool *consecutive)
 {
 	unsigned char *found;
 
@@ -2628,7 +2635,8 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		return buf_b; /* No overlap */
 
 	if (have_tsc) {
-		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b);
+		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b,
+						  consecutive);
 		if (found)
 			return found;
 	}
@@ -2643,28 +2651,16 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 	}
 
 	/* Now len_b >= len_a */
-	if (len_b > len_a) {
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
-	}
-
 	while (1) {
 		/* Potential overlap so check the bytes */
 		found = memmem(buf_a, len_a, buf_b, len_a);
-		if (found)
+		if (found) {
+			*consecutive = true;
 			return buf_b + len_a;
+		}
 
 		/* Try again at next PSB in buffer 'a' */
 		if (!intel_pt_step_psb(&buf_a, &len_a))
 			return buf_b; /* No overlap */
-
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
 	}
 }
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 921b22e8ca0e..fc1752d50019 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -117,7 +117,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
 
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc);
+				     bool have_tsc, bool *consecutive);
 
 int intel_pt__strerror(int code, char *buf, size_t buflen);
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 3773d9c54f45..4a7746249999 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -207,14 +207,17 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
+	bool consecutive = false;
 	void *start;
 
 	start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
-				      pt->have_tsc);
+				      pt->have_tsc, &consecutive);
 	if (!start)
 		return -EINVAL;
 	b->use_size = b->data + b->size - start;
 	b->use_data = start;
+	if (b->use_size && consecutive)
+		b->consecutive = true;
 	return 0;
 }
 
-- 
2.14.3

[PATCH 31/54] perf intel-pt: Fix sync_switch

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

sync_switch is a facility to synchronize decoding more closely with the
point in the kernel when the context actually switched.

The flag when sync_switch is enabled was global to the decoding, whereas
it is really specific to the CPU.

The trace data for different CPUs is put on different queues, so add
sync_switch to the intel_pt_queue structure and use that in preference
to the global setting in the intel_pt structure.

That fixes problems decoding one CPU's trace because sync_switch was
disabled on a different CPU's queue.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1520431349-30689-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4a7746249999..0979a6e8b2b7 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -143,6 +143,7 @@ struct intel_pt_queue {
 	bool stop;
 	bool step_through_buffers;
 	bool use_buffer_pid_tid;
+	bool sync_switch;
 	pid_t pid, tid;
 	int cpu;
 	int switch_state;
@@ -963,10 +964,12 @@ static int intel_pt_setup_queue(struct intel_pt *pt,
 			if (pt->timeless_decoding || !pt->have_sched_switch)
 				ptq->use_buffer_pid_tid = true;
 		}
+
+		ptq->sync_switch = pt->sync_switch;
 	}
 
 	if (!ptq->on_heap &&
-	    (!pt->sync_switch ||
+	    (!ptq->sync_switch ||
 	     ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
 		const struct intel_pt_state *state;
 		int ret;
@@ -1549,7 +1552,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch)
 		intel_pt_update_last_branch_rb(ptq);
 
-	if (!pt->sync_switch)
+	if (!ptq->sync_switch)
 		return 0;
 
 	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
@@ -1630,6 +1633,21 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	return switch_ip;
 }
 
+static void intel_pt_enable_sync_switch(struct intel_pt *pt)
+{
+	unsigned int i;
+
+	pt->sync_switch = true;
+
+	for (i = 0; i < pt->queues.nr_queues; i++) {
+		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+		struct intel_pt_queue *ptq = queue->priv;
+
+		if (ptq)
+			ptq->sync_switch = true;
+	}
+}
+
 static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 {
 	const struct intel_pt_state *state = ptq->state;
@@ -1646,7 +1664,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 			if (pt->switch_ip) {
 				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
 					     pt->switch_ip, pt->ptss_ip);
-				pt->sync_switch = true;
+				intel_pt_enable_sync_switch(pt);
 			}
 		}
 	}
@@ -1662,9 +1680,9 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 		if (state->err) {
 			if (state->err == INTEL_PT_ERR_NODATA)
 				return 1;
-			if (pt->sync_switch &&
+			if (ptq->sync_switch &&
 			    state->from_ip >= pt->kernel_start) {
-				pt->sync_switch = false;
+				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
 			if (pt->synth_opts.errors) {
@@ -1690,7 +1708,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				     state->timestamp, state->est_timestamp);
 			ptq->timestamp = state->est_timestamp;
 		/* Use estimated TSC in unknown switch state */
-		} else if (pt->sync_switch &&
+		} else if (ptq->sync_switch &&
 			   ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
 			   intel_pt_is_switch_ip(ptq, state->to_ip) &&
 			   ptq->next_tid == -1) {
@@ -1837,7 +1855,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
 		return 1;
 
 	ptq = intel_pt_cpu_to_ptq(pt, cpu);
-	if (!ptq)
+	if (!ptq || !ptq->sync_switch)
 		return 1;
 
 	switch (ptq->switch_state) {
-- 
2.14.3

[PATCH 32/54] perf intel-pt: Fix error recovery from missing TIP packet

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

When a TIP packet is expected but there is a different packet, it is an
error. However the unexpected packet might be something important like a
TSC packet, so after the error, it is necessary to continue from there,
rather than the next packet. That is achieved by setting pkt_step to
zero.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1520431349-30689-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 00f25f4b5f48..5e4d0bbafc8b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1616,6 +1616,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PWRX:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
+			decoder->pkt_step = 0;
 			return -ENOENT;
 
 		case INTEL_PT_OVF:
-- 
2.14.3

[PATCH 33/54] perf intel-pt: Fix timestamp following overflow

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

timestamp_insn_cnt is used to estimate the timestamp based on the number of
instructions since the last known timestamp.

If the estimate is not accurate enough decoding might not be correctly
synchronized with side-band events causing more trace errors.

However there are always timestamps following an overflow, so the
estimate is not needed and can indeed result in more errors.

Suppress the estimate by setting timestamp_insn_cnt to zero.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1520431349-30689-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 5e4d0bbafc8b..f9157aed1289 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1378,6 +1378,7 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	decoder->have_tma = false;
 	decoder->cbr = 0;
+	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
 	return -EOVERFLOW;
-- 
2.14.3

[PATCH 34/54] perf intel-pt/bts: In auxtrace_record__init_intel() evlist is never NULL

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Tidy auxtrace_record__init_intel() slightly by recognizing that evlist is
never NULL.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520431349-30689-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/auxtrace.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 6aa3f2a38321..b135af62011c 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -37,15 +37,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
-	if (evlist) {
-		evlist__for_each_entry(evlist, evsel) {
-			if (intel_pt_pmu &&
-			    evsel->attr.type == intel_pt_pmu->type)
-				found_pt = true;
-			if (intel_bts_pmu &&
-			    evsel->attr.type == intel_bts_pmu->type)
-				found_bts = true;
-		}
+	evlist__for_each_entry(evlist, evsel) {
+		if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type)
+			found_pt = true;
+		if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type)
+			found_bts = true;
 	}
 
 	if (found_pt && found_bts) {
-- 
2.14.3

[PATCH 35/54] perf intel-pt: Get rid of intel_pt_use_buffer_pid_tid()

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

With the new way sampling support will be implemented,
intel_pt_use_buffer_pid_tid() will not be needed. Get rid of it.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520431349-30689-7-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 39 +++------------------------------------
 1 file changed, 3 insertions(+), 36 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 0979a6e8b2b7..cfb3614f5def 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -222,32 +222,6 @@ static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *
 	return 0;
 }
 
-static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq,
-					struct auxtrace_queue *queue,
-					struct auxtrace_buffer *buffer)
-{
-	if (queue->cpu == -1 && buffer->cpu != -1)
-		ptq->cpu = buffer->cpu;
-
-	ptq->pid = buffer->pid;
-	ptq->tid = buffer->tid;
-
-	intel_pt_log("queue %u cpu %d pid %d tid %d\n",
-		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
-
-	thread__zput(ptq->thread);
-
-	if (ptq->tid != -1) {
-		if (ptq->pid != -1)
-			ptq->thread = machine__findnew_thread(ptq->pt->machine,
-							      ptq->pid,
-							      ptq->tid);
-		else
-			ptq->thread = machine__find_thread(ptq->pt->machine, -1,
-							   ptq->tid);
-	}
-}
-
 /* This function assumes data is processed sequentially only */
 static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 {
@@ -311,10 +285,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 		b->consecutive = true;
 	}
 
-	if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid ||
-					ptq->tid != buffer->tid))
-		intel_pt_use_buffer_pid_tid(ptq, queue, buffer);
-
 	if (ptq->step_through_buffers)
 		ptq->stop = true;
 
@@ -958,12 +928,9 @@ static int intel_pt_setup_queue(struct intel_pt *pt,
 			ptq->cpu = queue->cpu;
 		ptq->tid = queue->tid;
 
-		if (pt->sampling_mode) {
-			if (pt->timeless_decoding)
-				ptq->step_through_buffers = true;
-			if (pt->timeless_decoding || !pt->have_sched_switch)
-				ptq->use_buffer_pid_tid = true;
-		}
+		if (pt->sampling_mode && !pt->snapshot_mode &&
+		    pt->timeless_decoding)
+			ptq->step_through_buffers = true;
 
 		ptq->sync_switch = pt->sync_switch;
 	}
-- 
2.14.3

[PATCH 36/54] perf intel-pt: Tidy old_buffer handling in intel_pt_get_trace()

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

intel_pt_get_trace() fixes overlaps between the current buffer and the
previous buffer ('old_buffer').

However the previous buffer might not have had usable data (no PSB) so
the comparison must be made against the previous buffer that had usable
data.

Tidy that by keeping a pointer for that purpose in struct intel_pt_queue.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520431349-30689-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index cfb3614f5def..9a4f9cdb752f 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -132,6 +132,7 @@ struct intel_pt_queue {
 	struct intel_pt *pt;
 	unsigned int queue_nr;
 	struct auxtrace_buffer *buffer;
+	struct auxtrace_buffer *old_buffer;
 	void *decoder;
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
@@ -226,7 +227,8 @@ static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *
 static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 {
 	struct intel_pt_queue *ptq = data;
-	struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer;
+	struct auxtrace_buffer *buffer = ptq->buffer;
+	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
 	struct auxtrace_queue *queue;
 
 	if (ptq->stop) {
@@ -235,7 +237,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 
 	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-next:
+
 	buffer = auxtrace_buffer__next(queue, buffer);
 	if (!buffer) {
 		if (old_buffer)
@@ -267,16 +269,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 	b->ref_timestamp = buffer->reference;
 
-	/*
-	 * If in snapshot mode and the buffer has no usable data, get next
-	 * buffer and again check overlap against old_buffer.
-	 */
-	if (ptq->pt->snapshot_mode && !b->len)
-		goto next;
-
-	if (old_buffer)
-		auxtrace_buffer__drop_data(old_buffer);
-
 	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
 						      !buffer->consecutive)) {
 		b->consecutive = false;
@@ -288,8 +280,14 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	if (ptq->step_through_buffers)
 		ptq->stop = true;
 
-	if (!b->len)
+	if (b->len) {
+		if (old_buffer)
+			auxtrace_buffer__drop_data(old_buffer);
+		ptq->old_buffer = buffer;
+	} else {
+		auxtrace_buffer__drop_data(buffer);
 		return intel_pt_get_trace(b, data);
+	}
 
 	return 0;
 }
-- 
2.14.3

[PATCH 37/54] perf intel-pt: Remove a check for sampling mode

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Intel PT code already has some preparation for AUX area sampling mode.

However the implementation has changed from the first proposal and one
of the side-effects is that it will not be impossible to support snapshot
mode and sampling mode at the same time.

Although there are no plans to support it, let validation (not yet
implemented) control whether it is allowed rather than low-level
functions.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520431349-30689-9-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 9a4f9cdb752f..5c5c155fba78 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2061,9 +2061,6 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session,
 	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
 					   auxtrace);
 
-	if (pt->sampling_mode)
-		return 0;
-
 	if (!pt->data_queued) {
 		struct auxtrace_buffer *buffer;
 		off_t data_offset;
-- 
2.14.3

[PATCH 38/54] perf intel-pt: Adjust overlap-checking to support sampling mode

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Adjust overlap-checking to support sampling mode.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1520431349-30689-10-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 5c5c155fba78..0effaff57020 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -230,6 +230,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	struct auxtrace_buffer *buffer = ptq->buffer;
 	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
 	struct auxtrace_queue *queue;
+	bool might_overlap;
 
 	if (ptq->stop) {
 		b->len = 0;
@@ -256,7 +257,8 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 			return -ENOMEM;
 	}
 
-	if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer &&
+	might_overlap = ptq->pt->snapshot_mode || ptq->pt->sampling_mode;
+	if (might_overlap && !buffer->consecutive && old_buffer &&
 	    intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
 		return -ENOMEM;
 
@@ -269,8 +271,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 	b->ref_timestamp = buffer->reference;
 
-	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
-						      !buffer->consecutive)) {
+	if (!old_buffer || (might_overlap && !buffer->consecutive)) {
 		b->consecutive = false;
 		b->trace_nr = buffer->buffer_nr + 1;
 	} else {
-- 
2.14.3

[PATCH 39/54] perf annotate: Fix s390 target function disassembly

[Arnaldo Carvalho de Melo]

From: Thomas Richter <tmricht@linux.vnet.ibm.com>

'perf annotate' displays function call assembler instructions with a
right arrow. Hitting enter on this line/instruction causes the browser
to disassemble this target function and show it on the screen.  On s390
this results in an error message 'The called function was not found.'

The function call assembly line parsing does not handle the s390 bras
and brasl instructions. Function call__parse expects the target as first
operand:

	callq	e9140 <__fxstat>

S390 has a register number as first operand:

	brasl	%r14,41d60 <abort>

Therefore the target addresses on s390 are always zero which is an
invalid address.

Introduce a s390 specific call parsing function which skips the first
operand on s390.

Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180307134325.96106-1-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/s390/annotate/instructions.c | 53 +++++++++++++++++++++++++++-
 tools/perf/util/annotate.c                   |  2 +-
 2 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 01df9d8303e1..e80589fc5b58 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -1,6 +1,57 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 
+static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
+			    struct map *map)
+{
+	char *endptr, *tok, *name;
+	struct addr_map_symbol target = {
+		.map = map,
+	};
+
+	tok = strchr(ops->raw, ',');
+	if (!tok)
+		return -1;
+
+	ops->target.addr = strtoull(tok + 1, &endptr, 16);
+
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		return -1;
+
+	name++;
+
+	if (arch->objdump.skip_functions_char &&
+	    strchr(name, arch->objdump.skip_functions_char))
+		return -1;
+
+	tok = strchr(name, '>');
+	if (tok == NULL)
+		return -1;
+
+	*tok = '\0';
+	ops->target.name = strdup(name);
+	*tok = '>';
+
+	if (ops->target.name == NULL)
+		return -1;
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+
+	if (map_groups__find_ams(&target) == 0 &&
+	    map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.sym;
+
+	return 0;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops);
+
+static struct ins_ops s390_call_ops = {
+	.parse	   = s390_call__parse,
+	.scnprintf = call__scnprintf,
+};
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
 	struct ins_ops *ops = NULL;
@@ -14,7 +65,7 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 	if (!strcmp(name, "bras") ||
 	    !strcmp(name, "brasl") ||
 	    !strcmp(name, "basr"))
-		ops = &call_ops;
+		ops = &s390_call_ops;
 	if (!strcmp(name, "br"))
 		ops = &ret_ops;
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 49ff825f745c..bc3302da702b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -248,7 +248,7 @@ static struct ins_ops call_ops = {
 
 bool ins__is_call(const struct ins *ins)
 {
-	return ins->ops == &call_ops;
+	return ins->ops == &call_ops || ins->ops == &s390_call_ops;
 }
 
 static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused)
-- 
2.14.3

[PATCH 40/54] perf report: Fix the output for stdio events list

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

Changing the output header for reporting forced groups via --groups
option on non grouped events, like:

  $ perf record -e 'cycles,instructions'
  $ perf report --stdio --group

Before:

  # Samples: 24  of event 'anon group { cycles:u, instructions:u }'

After:

  # Samples: 24  of events 'cycles:u, instructions:u'

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Fixes: ad52b8cb4886 ("perf report: Add support to display group output for non group events")
Link: http://lkml.kernel.org/r/20180307155020.32613-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c    | 17 ++++++++++++++---
 tools/perf/ui/browsers/hists.c |  5 +++--
 tools/perf/util/evsel.c        | 20 ++++++++++++++++----
 tools/perf/util/evsel.h        |  1 +
 4 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1eedb1815c4c..c3603d4c0c57 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -400,8 +400,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
-	if (evname != NULL)
-		ret += fprintf(fp, " of event '%s'", evname);
+	if (evname != NULL) {
+		ret += fprintf(fp, " of event%s '%s'",
+			       evsel->nr_members > 1 ? "s" : "", evname);
+	}
 
 	if (rep->time_str)
 		ret += fprintf(fp, " (time slices: %s)", rep->time_str);
@@ -1175,8 +1177,17 @@ int cmd_report(int argc, const char **argv)
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (group_set && !session->evlist->nr_groups)
+	/*
+	 * Events in data file are not collect in groups, but we still want
+	 * the group display. Set the artificial group and set the leader's
+	 * forced_leader flag to notify the display code.
+	 */
+	if (group_set && !session->evlist->nr_groups) {
+		struct perf_evsel *leader = perf_evlist__first(session->evlist);
+
 		perf_evlist__set_leader(session->evlist);
+		leader->forced_leader = true;
+	}
 
 	if (itrace_synth_opts.last_branch)
 		has_br_stack = true;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index de2bde232cb3..8b4e82548f8e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2261,8 +2261,9 @@ static int perf_evsel_browser_title(struct hist_browser *browser,
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
-			   "Samples: %lu%c of event '%s',%s%sEvent count (approx.): %" PRIu64,
-			   nr_samples, unit, ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
+			   "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
+			   nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
+			   ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
 
 
 	if (hists->uid_filter_str)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e937894654b2..1ac8d9236efd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -622,22 +622,34 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel)
 	return evsel->group_name ?: "anon group";
 }
 
+/*
+ * Returns the group details for the specified leader,
+ * with following rules.
+ *
+ *  For record -e '{cycles,instructions}'
+ *    'anon group { cycles:u, instructions:u }'
+ *
+ *  For record -e 'cycles,instructions' and report --group
+ *    'cycles:u, instructions:u'
+ */
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 {
-	int ret;
+	int ret = 0;
 	struct perf_evsel *pos;
 	const char *group_name = perf_evsel__group_name(evsel);
 
-	ret = scnprintf(buf, size, "%s", group_name);
+	if (!evsel->forced_leader)
+		ret = scnprintf(buf, size, "%s { ", group_name);
 
-	ret += scnprintf(buf + ret, size - ret, " { %s",
+	ret += scnprintf(buf + ret, size - ret, "%s",
 			 perf_evsel__name(evsel));
 
 	for_each_group_member(pos, evsel)
 		ret += scnprintf(buf + ret, size - ret, ", %s",
 				 perf_evsel__name(pos));
 
-	ret += scnprintf(buf + ret, size - ret, " }");
+	if (!evsel->forced_leader)
+		ret += scnprintf(buf + ret, size - ret, " }");
 
 	return ret;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 55ae1cda7396..d3ee3af618ef 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -125,6 +125,7 @@ struct perf_evsel {
 	bool			per_pkg;
 	bool			precise_max;
 	bool			ignore_missing_thread;
+	bool			forced_leader;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
-- 
2.14.3

[PATCH 41/54] perf report: Display perf.data header info

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

Display more header info from perf.data file, following values:

  $ perf report -i perf.data --header-only
  ...
  # header version : 1
  # data offset    : 424
  # data size      : 3364280
  # feat offset    : 3364704

It's handy for debuging.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a326e0d8b5b6..e0c3cad0fd8d 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2318,7 +2318,12 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	if (ret == -1)
 		return -1;
 
-	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
+	fprintf(fp, "# captured on    : %s", ctime(&st.st_ctime));
+
+	fprintf(fp, "# header version : %u\n", header->version);
+	fprintf(fp, "# data offset    : %" PRIu64 "\n", header->data_offset);
+	fprintf(fp, "# data size      : %" PRIu64 "\n", header->data_size);
+	fprintf(fp, "# feat offset    : %" PRIu64 "\n", header->feat_offset);
 
 	perf_header__process_sections(header, fd, &hd,
 				      perf_file_section__fprintf_info);
-- 
2.14.3

[PATCH 42/54] perf record: Move machine variable down the function

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

It's used far more down to be declared on the top of the __cmd_record.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 753ffcecf254..31d4d70e2f6a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -854,7 +854,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	int status = 0;
 	unsigned long waking = 0;
 	const bool forks = argc > 0;
-	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
 	struct record_opts *opts = &rec->opts;
 	struct perf_data *data = &rec->data;
@@ -959,8 +958,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
-	machine = &session->machines.host;
-
 	err = record__synthesize(rec, false);
 	if (err < 0)
 		goto out_child;
@@ -988,6 +985,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * Let the child rip
 	 */
 	if (forks) {
+		struct machine *machine = &session->machines.host;
 		union perf_event *event;
 		pid_t tgid;
 
-- 
2.14.3

[PATCH 43/54] perf record: Remove progname from struct record

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

It's no longer used.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 31d4d70e2f6a..b81494587120 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -71,7 +71,6 @@ struct record {
 	struct auxtrace_record	*itr;
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
-	const char		*progname;
 	int			realtime_prio;
 	bool			no_buildid;
 	bool			no_buildid_set;
@@ -861,8 +860,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	bool disabled = false, draining = false;
 	int fd;
 
-	rec->progname = argv[0];
-
 	atexit(record__sig_exit);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
-- 
2.14.3

[PATCH 44/54] perf tools: Add refcnt into struct mem_info

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

It's passed along several hists entries in --hierarchy mode, so it's
better we keep track of it.

The current fail I see is that it gets removed in hierarchy --mem-mode
mode, where it's shared in the different hierarchies, but removed from
the template hist entry, so the report crashes.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-6-jolsa@kernel.org
[ Rename mem_info__aloc() to mem_info__new(), to fix the typo and use the convention for constructors ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c    |  4 ++--
 tools/perf/util/machine.c |  2 +-
 tools/perf/util/symbol.c  | 22 ++++++++++++++++++++++
 tools/perf/util/symbol.h  | 19 ++++++++++++++++---
 4 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 44a8456cea10..7d968892ee39 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -536,7 +536,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 			 * This mem info was allocated from sample__resolve_mem
 			 * and will not be used anymore.
 			 */
-			zfree(&entry->mem_info);
+			mem_info__zput(entry->mem_info);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
@@ -1139,7 +1139,7 @@ void hist_entry__delete(struct hist_entry *he)
 	if (he->mem_info) {
 		map__zput(he->mem_info->iaddr.map);
 		map__zput(he->mem_info->daddr.map);
-		zfree(&he->mem_info);
+		mem_info__zput(he->mem_info);
 	}
 
 	zfree(&he->stat_acc);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 12b7427444a3..43fbbee409ec 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1697,7 +1697,7 @@ static void ip__resolve_data(struct thread *thread,
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al)
 {
-	struct mem_info *mi = zalloc(sizeof(*mi));
+	struct mem_info *mi = mem_info__new();
 
 	if (!mi)
 		return NULL;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a1a312d99f30..62b2dd2253eb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2221,3 +2221,25 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
 	free(bf);
 	return 0;
 }
+
+struct mem_info *mem_info__get(struct mem_info *mi)
+{
+	if (mi)
+		refcount_inc(&mi->refcnt);
+	return mi;
+}
+
+void mem_info__put(struct mem_info *mi)
+{
+	if (mi && refcount_dec_and_test(&mi->refcnt))
+		free(mi);
+}
+
+struct mem_info *mem_info__new(void)
+{
+	struct mem_info *mi = zalloc(sizeof(*mi));
+
+	if (mi)
+		refcount_set(&mi->refcnt, 1);
+	return mi;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 0563f33c1eb3..70c16741f50a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -200,9 +200,10 @@ struct branch_info {
 };
 
 struct mem_info {
-	struct addr_map_symbol iaddr;
-	struct addr_map_symbol daddr;
-	union perf_mem_data_src data_src;
+	struct addr_map_symbol	iaddr;
+	struct addr_map_symbol	daddr;
+	union perf_mem_data_src	data_src;
+	refcount_t		refcnt;
 };
 
 struct addr_location {
@@ -389,4 +390,16 @@ int sdt_notes__get_count(struct list_head *start);
 #define SDT_NOTE_NAME "stapsdt"
 #define NR_ADDR 3
 
+struct mem_info *mem_info__new(void);
+struct mem_info *mem_info__get(struct mem_info *mi);
+void   mem_info__put(struct mem_info *mi);
+
+static inline void __mem_info__zput(struct mem_info **mi)
+{
+	mem_info__put(*mi);
+	*mi = NULL;
+}
+
+#define mem_info__zput(mi) __mem_info__zput(&mi)
+
 #endif /* __PERF_SYMBOL */
-- 
2.14.3

[PATCH 45/54] perf c2c: Use mem_info refcnt logic

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

Switch to refcnt logic instead of duplicating mem_info objects. No
functional change, just saving some memory.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-7-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-c2c.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 539c3d460158..98d243fa0c06 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -237,9 +237,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (mi == NULL)
 		return -ENOMEM;
 
-	mi_dup = memdup(mi, sizeof(*mi));
-	if (!mi_dup)
-		goto free_mi;
+	/*
+	 * The mi object is released in hists__add_entry_ops,
+	 * if it gets sorted out into existing data, so we need
+	 * to take the copy now.
+	 */
+	mi_dup = mem_info__get(mi);
 
 	c2c_decode_stats(&stats, mi);
 
@@ -247,7 +250,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				  &al, NULL, NULL, mi,
 				  sample, true);
 	if (he == NULL)
-		goto free_mi_dup;
+		goto free_mi;
 
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	c2c_add_stats(&c2c_he->stats, &stats);
@@ -272,19 +275,15 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 		mi = mi_dup;
 
-		mi_dup = memdup(mi, sizeof(*mi));
-		if (!mi_dup)
-			goto free_mi;
-
 		c2c_hists = he__get_c2c_hists(he, c2c.cl_sort, 2);
 		if (!c2c_hists)
-			goto free_mi_dup;
+			goto free_mi;
 
 		he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops,
 					  &al, NULL, NULL, mi,
 					  sample, true);
 		if (he == NULL)
-			goto free_mi_dup;
+			goto free_mi;
 
 		c2c_he = container_of(he, struct c2c_hist_entry, he);
 		c2c_add_stats(&c2c_he->stats, &stats);
@@ -303,10 +302,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	addr_location__put(&al);
 	return ret;
 
-free_mi_dup:
-	free(mi_dup);
 free_mi:
-	free(mi);
+	mem_info__put(mi_dup);
+	mem_info__put(mi);
 	ret = -ENOMEM;
 	goto out;
 }
-- 
2.14.3

[PATCH 46/54] perf tools: Add MEM_TOPOLOGY feature to perf data file

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

Adding MEM_TOPOLOGY feature to perf data file,
that will carry physical memory map and its
node assignments.

The format of data in MEM_TOPOLOGY is as follows:

  0 - version          | for future changes
  8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes
 16 - count            | number of nodes

 For each node we store map of physical indexes for
 each node:

 32 - node id          | node index
 40 - size             | size of bitmap
 48 - bitmap           | bitmap of memory indexes that belongs to node
                       | /sys/devices/system/node/node<NODE>/memory<INDEX>

The MEM_TOPOLOGY could be displayed with following
report command:

  $ perf report --header-only -I
  ...
  # memory nodes (nr 1, block size 0x8000000):
  #    0 [7G]: 0-23,32-69

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-8-jolsa@kernel.org
[ Rename 'index' to 'idx', as this breaks the build in rhel5, 6 and other systems where this is used by glibc headers ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bitmap.h |   2 +-
 tools/perf/util/env.h        |   9 ++
 tools/perf/util/header.c     | 305 +++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/header.h     |   1 +
 4 files changed, 316 insertions(+), 1 deletion(-)

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index ca160270fdfa..63440cc8d618 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -98,7 +98,7 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
 
 /**
  * bitmap_alloc - Allocate bitmap
- * @nr: Bit to set
+ * @nbits: Number of bits
  */
 static inline unsigned long *bitmap_alloc(int nbits)
 {
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index bf970f57dce0..c4ef2e523367 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -27,6 +27,12 @@ struct numa_node {
 	struct cpu_map	*map;
 };
 
+struct memory_node {
+	u64		 node;
+	u64		 size;
+	unsigned long	*set;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -43,6 +49,7 @@ struct perf_env {
 	int			nr_sibling_cores;
 	int			nr_sibling_threads;
 	int			nr_numa_nodes;
+	int			nr_memory_nodes;
 	int			nr_pmu_mappings;
 	int			nr_groups;
 	char			*cmdline;
@@ -54,6 +61,8 @@ struct perf_env {
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
 	struct numa_node	*numa_nodes;
+	struct memory_node	*memory_nodes;
+	unsigned long long	 memory_bsize;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e0c3cad0fd8d..e14b3f7c7212 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -17,6 +17,7 @@
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <linux/time64.h>
+#include <dirent.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -37,6 +38,7 @@
 #include "asm/bug.h"
 #include "tool.h"
 #include "time-utils.h"
+#include "units.h"
 
 #include "sane_ctype.h"
 
@@ -131,6 +133,25 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size)
 	return __do_write_buf(ff, buf, size);
 }
 
+/* Return: 0 if succeded, -ERR if failed. */
+static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size)
+{
+	u64 *p = (u64 *) set;
+	int i, ret;
+
+	ret = do_write(ff, &size, sizeof(size));
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
+		ret = do_write(ff, p + i, sizeof(*p));
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
 /* Return: 0 if succeded, -ERR if failed. */
 int write_padded(struct feat_fd *ff, const void *bf,
 		 size_t count, size_t count_aligned)
@@ -243,6 +264,38 @@ static char *do_read_string(struct feat_fd *ff)
 	return NULL;
 }
 
+/* Return: 0 if succeded, -ERR if failed. */
+static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize)
+{
+	unsigned long *set;
+	u64 size, *p;
+	int i, ret;
+
+	ret = do_read_u64(ff, &size);
+	if (ret)
+		return ret;
+
+	set = bitmap_alloc(size);
+	if (!set)
+		return -ENOMEM;
+
+	bitmap_zero(set, size);
+
+	p = (u64 *) set;
+
+	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
+		ret = do_read_u64(ff, p + i);
+		if (ret < 0) {
+			free(set);
+			return ret;
+		}
+	}
+
+	*pset  = set;
+	*psize = size;
+	return 0;
+}
+
 static int write_tracing_data(struct feat_fd *ff,
 			      struct perf_evlist *evlist)
 {
@@ -1196,6 +1249,176 @@ static int write_sample_time(struct feat_fd *ff,
 			sizeof(evlist->last_sample_time));
 }
 
+
+static int memory_node__read(struct memory_node *n, unsigned long idx)
+{
+	unsigned int phys, size = 0;
+	char path[PATH_MAX];
+	struct dirent *ent;
+	DIR *dir;
+
+#define for_each_memory(mem, dir)					\
+	while ((ent = readdir(dir)))					\
+		if (strcmp(ent->d_name, ".") &&				\
+		    strcmp(ent->d_name, "..") &&			\
+		    sscanf(ent->d_name, "memory%u", &mem) == 1)
+
+	scnprintf(path, PATH_MAX,
+		  "%s/devices/system/node/node%lu",
+		  sysfs__mountpoint(), idx);
+
+	dir = opendir(path);
+	if (!dir) {
+		pr_warning("failed: cant' open memory sysfs data\n");
+		return -1;
+	}
+
+	for_each_memory(phys, dir) {
+		size = max(phys, size);
+	}
+
+	size++;
+
+	n->set = bitmap_alloc(size);
+	if (!n->set) {
+		closedir(dir);
+		return -ENOMEM;
+	}
+
+	bitmap_zero(n->set, size);
+	n->node = idx;
+	n->size = size;
+
+	rewinddir(dir);
+
+	for_each_memory(phys, dir) {
+		set_bit(phys, n->set);
+	}
+
+	closedir(dir);
+	return 0;
+}
+
+static int memory_node__sort(const void *a, const void *b)
+{
+	const struct memory_node *na = a;
+	const struct memory_node *nb = b;
+
+	return na->node - nb->node;
+}
+
+static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
+{
+	char path[PATH_MAX];
+	struct dirent *ent;
+	DIR *dir;
+	u64 cnt = 0;
+	int ret = 0;
+
+	scnprintf(path, PATH_MAX, "%s/devices/system/node/",
+		  sysfs__mountpoint());
+
+	dir = opendir(path);
+	if (!dir) {
+		pr_warning("failed: can't open node sysfs data\n");
+		return -1;
+	}
+
+	while (!ret && (ent = readdir(dir))) {
+		unsigned int idx;
+		int r;
+
+		if (!strcmp(ent->d_name, ".") ||
+		    !strcmp(ent->d_name, ".."))
+			continue;
+
+		r = sscanf(ent->d_name, "node%u", &idx);
+		if (r != 1)
+			continue;
+
+		if (WARN_ONCE(cnt >= size,
+			      "failed to write MEM_TOPOLOGY, way too many nodes\n"))
+			return -1;
+
+		ret = memory_node__read(&nodes[cnt++], idx);
+	}
+
+	*cntp = cnt;
+	closedir(dir);
+
+	if (!ret)
+		qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort);
+
+	return ret;
+}
+
+#define MAX_MEMORY_NODES 2000
+
+/*
+ * The MEM_TOPOLOGY holds physical memory map for every
+ * node in system. The format of data is as follows:
+ *
+ *  0 - version          | for future changes
+ *  8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes
+ * 16 - count            | number of nodes
+ *
+ * For each node we store map of physical indexes for
+ * each node:
+ *
+ * 32 - node id          | node index
+ * 40 - size             | size of bitmap
+ * 48 - bitmap           | bitmap of memory indexes that belongs to node
+ */
+static int write_mem_topology(struct feat_fd *ff __maybe_unused,
+			      struct perf_evlist *evlist __maybe_unused)
+{
+	static struct memory_node nodes[MAX_MEMORY_NODES];
+	u64 bsize, version = 1, i, nr;
+	int ret;
+
+	ret = sysfs__read_xll("devices/system/memory/block_size_bytes",
+			      (unsigned long long *) &bsize);
+	if (ret)
+		return ret;
+
+	ret = build_mem_topology(&nodes[0], MAX_MEMORY_NODES, &nr);
+	if (ret)
+		return ret;
+
+	ret = do_write(ff, &version, sizeof(version));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(ff, &bsize, sizeof(bsize));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(ff, &nr, sizeof(nr));
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < nr; i++) {
+		struct memory_node *n = &nodes[i];
+
+		#define _W(v)						\
+			ret = do_write(ff, &n->v, sizeof(n->v));	\
+			if (ret < 0)					\
+				goto out;
+
+		_W(node)
+		_W(size)
+
+		#undef _W
+
+		ret = do_write_bitmap(ff, n->set, n->size);
+		if (ret < 0)
+			goto out;
+	}
+
+out:
+	return ret;
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
 	fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1543,6 +1766,35 @@ static void print_sample_time(struct feat_fd *ff, FILE *fp)
 	fprintf(fp, "# sample duration : %10.3f ms\n", d);
 }
 
+static void memory_node__fprintf(struct memory_node *n,
+				 unsigned long long bsize, FILE *fp)
+{
+	char buf_map[100], buf_size[50];
+	unsigned long long size;
+
+	size = bsize * bitmap_weight(n->set, n->size);
+	unit_number__scnprintf(buf_size, 50, size);
+
+	bitmap_scnprintf(n->set, n->size, buf_map, 100);
+	fprintf(fp, "#  %3" PRIu64 " [%s]: %s\n", n->node, buf_size, buf_map);
+}
+
+static void print_mem_topology(struct feat_fd *ff, FILE *fp)
+{
+	struct memory_node *nodes;
+	int i, nr;
+
+	nodes = ff->ph->env.memory_nodes;
+	nr    = ff->ph->env.nr_memory_nodes;
+
+	fprintf(fp, "# memory nodes (nr %d, block size 0x%llx):\n",
+		nr, ff->ph->env.memory_bsize);
+
+	for (i = 0; i < nr; i++) {
+		memory_node__fprintf(&nodes[i], ff->ph->env.memory_bsize, fp);
+	}
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -2205,6 +2457,58 @@ static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused)
 	return 0;
 }
 
+static int process_mem_topology(struct feat_fd *ff,
+				void *data __maybe_unused)
+{
+	struct memory_node *nodes;
+	u64 version, i, nr, bsize;
+	int ret = -1;
+
+	if (do_read_u64(ff, &version))
+		return -1;
+
+	if (version != 1)
+		return -1;
+
+	if (do_read_u64(ff, &bsize))
+		return -1;
+
+	if (do_read_u64(ff, &nr))
+		return -1;
+
+	nodes = zalloc(sizeof(*nodes) * nr);
+	if (!nodes)
+		return -1;
+
+	for (i = 0; i < nr; i++) {
+		struct memory_node n;
+
+		#define _R(v)				\
+			if (do_read_u64(ff, &n.v))	\
+				goto out;		\
+
+		_R(node)
+		_R(size)
+
+		#undef _R
+
+		if (do_read_bitmap(ff, &n.set, &n.size))
+			goto out;
+
+		nodes[i] = n;
+	}
+
+	ff->ph->env.memory_bsize    = bsize;
+	ff->ph->env.memory_nodes    = nodes;
+	ff->ph->env.nr_memory_nodes = nr;
+	ret = 0;
+
+out:
+	if (ret)
+		free(nodes);
+	return ret;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2263,6 +2567,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
+	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 942bdec6d70d..90d4577a92dc 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -36,6 +36,7 @@ enum {
 	HEADER_STAT,
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
+	HEADER_MEM_TOPOLOGY,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
-- 
2.14.3

[PATCH 47/54] perf tools: Update tags with .cpp files

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

We have some .cpp files, make ctags/cscope aware of them.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-17-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 4679e237a7f5..f7517e1b73f8 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -708,15 +708,15 @@ TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
 	$(QUIET_GEN)$(RM) TAGS; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs etags -a $(TAG_FILES)
 
 tags:
 	$(QUIET_GEN)$(RM) tags; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
 	$(QUIET_GEN)$(RM) cscope*; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs cscope -b $(TAG_FILES)
 
 ### Testing rules
 
-- 
2.14.3

[PATCH 48/54] perf build: Add llvm/clang/cxx make tests into FEATURE_TESTS_EXTRA

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

So we can see the status when we build perf, like:

  $ make LIBCLANGLLVM=1 VF=1
  ...                           cxx: [ on  ]
  ...                          llvm: [ on  ]
  ...                  llvm-version: [ on  ]
  ...                         clang: [ on  ]

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-18-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.feature | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index c378f003b007..5b6dda3b1ca8 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -82,7 +82,11 @@ FEATURE_TESTS_EXTRA :=                  \
          liberty-z                      \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64
+         libunwind-debug-frame-aarch64  \
+         cxx                            \
+         llvm                           \
+         llvm-version                   \
+         clang
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 
-- 
2.14.3

[PATCH 49/54] perf build: Add llvm/clang make targets to FILES

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

So they can follow the OUTPUT variable setup as the rest of the
features.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-19-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/feature/Makefile | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0a490cb15149..f8ad640ffe5d 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -54,7 +54,10 @@ FILES=                                          \
          test-jvmti.bin				\
          test-sched_getcpu.bin			\
          test-setns.bin				\
-         test-libopencsd.bin
+         test-libopencsd.bin			\
+         test-clang.bin				\
+         test-llvm.bin				\
+         test-llvm-version.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
-- 
2.14.3

[PATCH 50/54] perf build: Force llvm/clang test compile output to .make.output

[Arnaldo Carvalho de Melo]

From: Jiri Olsa <jolsa@kernel.org>

So we can see the output of feature compile in following files:

  tools/build/feature/test-llvm.make.output
  tools/build/feature/test-llvm-version.make.output
  tools/build/feature/test-clang.make.output

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180307155020.32613-20-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/feature/Makefile | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index f8ad640ffe5d..dac9563b5470 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -260,11 +260,13 @@ $(OUTPUT)test-llvm.bin:
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
 		$(shell $(LLVM_CONFIG) --libs Core BPF)		\
-		$(shell $(LLVM_CONFIG) --system-libs)
+		$(shell $(LLVM_CONFIG) --system-libs)		\
+		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-llvm-version.bin:
 	$(BUILDXX) -std=gnu++11 				\
-		-I$(shell $(LLVM_CONFIG) --includedir)
+		-I$(shell $(LLVM_CONFIG) --includedir)		\
+		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-clang.bin:
 	$(BUILDXX) -std=gnu++11 				\
@@ -274,7 +276,8 @@ $(OUTPUT)test-clang.bin:
 		  -lclangFrontend -lclangEdit -lclangLex	\
 		  -lclangAST -Wl,--end-group 			\
 		$(shell $(LLVM_CONFIG) --libs Core option)	\
-		$(shell $(LLVM_CONFIG) --system-libs)
+		$(shell $(LLVM_CONFIG) --system-libs)		\
+		> $(@:.bin=.make.output) 2>&1
 
 -include $(OUTPUT)*.d
 
-- 
2.14.3

[PATCH 51/54] perf report: Provide libtraceevent with a kernel symbol resolver

[Arnaldo Carvalho de Melo]

From: Wang YanQing <udknight@gmail.com>

So that beautifiers wanting to resolve kernel function addresses to
names can do its work, and when we use "perf report" for output of "perf
kmem record", we will get kernel symbol output.

This patch affect the output of "perf report" for the record data
generated by "perf kmem record" looks like below:

Before patch:
0.01%  call_site=ffffffff814e5828 ptr=0x99bb000 bytes_req=3616 bytes_alloc=4096 gfp_flags=GFP_ATOMIC
0.01%  call_site=ffffffff81370b87 ptr=0x428a3060 bytes_req=32 bytes_alloc=32 gfp_flags=GFP_KERNEL|GFP_ZERO

After patch:
0.01%  (aa_alloc_task_context+0x27) call_site=ffffffff81370b87 ptr=0x428a3060 bytes_req=32 bytes_alloc=32 gfp_flags=GFP_KERNEL|GFP_ZERO
0.01%  (__tty_buffer_request_room+0x88) call_site=ffffffff814e5828 ptr=0x99bb000 bytes_req=3616 bytes_alloc=4096 gfp_flags=GFP_ATOMIC

Signed-off-by: Wang YanQing <udknight@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180308032850.GA12383@udknight-ThinkPad-E550
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c3603d4c0c57..971ccba85464 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1348,6 +1348,15 @@ int cmd_report(int argc, const char **argv)
 		report.range_num = 1;
 	}
 
+	if (session->tevent.pevent &&
+	    pevent_set_function_resolver(session->tevent.pevent,
+					 machine__resolve_kernel_addr,
+					 &session->machines.host) < 0) {
+		pr_err("%s: failed to set libtraceevent function resolver\n",
+		       __func__);
+		return -1;
+	}
+
 	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
-- 
2.14.3

[PATCH 52/54] perf annotate: Support to display the IPC/Cycle in TUI mode

[Arnaldo Carvalho de Melo]

From: Jin Yao <yao.jin@linux.intel.com>

Unlike the perf report interactive annotate mode, the perf annotate
doesn't display the IPC/Cycle even if branch info is recorded in perf
data file.

perf record -b ...
perf annotate function

It should show IPC/cycle, but it doesn't.

This patch lets perf annotate support the displaying of IPC/Cycle if
branch info is in perf data.

For example,

  perf annotate compute_flag

  Percent│ IPC Cycle
         │
         │
         │                Disassembly of section .text:
         │
         │                0000000000400640 <compute_flag>:
         │                compute_flag():
         │                volatile int count;
         │                static unsigned int s_randseed;
         │
         │                __attribute__((noinline))
         │                int compute_flag()
         │                {
   22.96 │1.18   584        sub    $0x8,%rsp
         │                        int i;
         │
         │                        i = rand() % 2;
   23.02 │1.18     1      → callq  rand@plt
         │
         │                        return i;
   27.05 │3.37              mov    %eax,%edx
         │                }
         │3.37              add    $0x8,%rsp
         │                {
         │                        int i;
         │
         │                        i = rand() % 2;
         │
         │                        return i;
         │3.37              shr    $0x1f,%edx
         │3.37              add    %edx,%eax
         │3.37              and    $0x1,%eax
         │3.37              sub    %edx,%eax
         │                }
   26.97 │3.37     2      ← retq

Note that, this patch only supports TUI mode. For stdio, now it just keeps
original behavior. Will support it in a follow-up patch.

  $ perf annotate compute_flag --stdio

   Percent |      Source code & Disassembly of div for cycles:ppp (7993 samples)
  ------------------------------------------------------------------------------
           :
           :
           :
           :            Disassembly of section .text:
           :
           :            0000000000400640 <compute_flag>:
           :            compute_flag():
           :            volatile int count;
           :            static unsigned int s_randseed;
           :
           :            __attribute__((noinline))
           :            int compute_flag()
           :            {
      0.29 :   400640:       sub    $0x8,%rsp     # +100.00%
           :                    int i;
           :
           :                    i = rand() % 2;
     42.93 :   400644:       callq  400490 <rand@plt>     # -100.00% (p:100.00%)
           :
           :                    return i;
      0.10 :   400649:       mov    %eax,%edx     # +100.00%
           :            }
      0.94 :   40064b:       add    $0x8,%rsp
           :            {
           :                    int i;
           :
           :                    i = rand() % 2;
           :
           :                    return i;
     27.02 :   40064f:       shr    $0x1f,%edx
      0.15 :   400652:       add    %edx,%eax
      1.24 :   400654:       and    $0x1,%eax
      2.08 :   400657:       sub    %edx,%eax
           :            }
     25.26 :   400659:       retq # -100.00% (p:100.00%)

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/20180223170210.GC7045@tassilo.jf.intel.com
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1519724327-7773-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c | 88 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 82 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index f15731a3d438..ead6ae4549e5 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -44,6 +44,7 @@ struct perf_annotate {
 	bool	   full_paths;
 	bool	   print_line;
 	bool	   skip_missing;
+	bool	   has_br_stack;
 	const char *sym_hist_filter;
 	const char *cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -146,16 +147,73 @@ static void process_branch_stack(struct branch_stack *bs, struct addr_location *
 	free(bi);
 }
 
+static int hist_iter__branch_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al __maybe_unused,
+				      bool single __maybe_unused,
+				      void *arg __maybe_unused)
+{
+	struct hist_entry *he = iter->he;
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+	struct perf_evsel *evsel = iter->evsel;
+	int err;
+
+	hist__account_cycles(sample->branch_stack, al, sample, false);
+
+	bi = he->branch_info;
+	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
+
+	if (err)
+		goto out;
+
+	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
+
+out:
+	return err;
+}
+
+static int process_branch_callback(struct perf_evsel *evsel,
+				   struct perf_sample *sample,
+				   struct addr_location *al __maybe_unused,
+				   struct perf_annotate *ann,
+				   struct machine *machine)
+{
+	struct hist_entry_iter iter = {
+		.evsel		= evsel,
+		.sample		= sample,
+		.add_entry_cb	= hist_iter__branch_callback,
+		.hide_unresolved	= symbol_conf.hide_unresolved,
+		.ops		= &hist_iter_branch,
+	};
+
+	struct addr_location a;
+	int ret;
+
+	if (machine__resolve(machine, &a, sample) < 0)
+		return -1;
+
+	if (a.sym == NULL)
+		return 0;
+
+	if (a.map != NULL)
+		a.map->dso->hit = 1;
+
+	ret = hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann);
+	return ret;
+}
+
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
-				  struct perf_annotate *ann)
+				  struct perf_annotate *ann,
+				  struct machine *machine)
 {
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	int ret;
 
-	if (ann->sym_hist_filter != NULL &&
+	if ((!ann->has_br_stack || !ui__has_annotation()) &&
+	    ann->sym_hist_filter != NULL &&
 	    (al->sym == NULL ||
 	     strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
 		/* We're only interested in a symbol named sym_hist_filter */
@@ -178,6 +236,9 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 	 */
 	process_branch_stack(sample->branch_stack, al, sample);
 
+	if (ann->has_br_stack && ui__has_annotation())
+		return process_branch_callback(evsel, sample, al, ann, machine);
+
 	he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
 	if (he == NULL)
 		return -ENOMEM;
@@ -206,7 +267,8 @@ static int process_sample_event(struct perf_tool *tool,
 	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
 		goto out_put;
 
-	if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
+	if (!al.filtered &&
+	    perf_evsel__add_sample(evsel, sample, &al, ann, machine)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		ret = -1;
@@ -238,6 +300,10 @@ static void hists__find_annotations(struct hists *hists,
 		if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
 			goto find_next;
 
+		if (ann->sym_hist_filter &&
+		    (strcmp(he->ms.sym->name, ann->sym_hist_filter) != 0))
+			goto find_next;
+
 		notes = symbol__annotation(he->ms.sym);
 		if (notes->src == NULL) {
 find_next:
@@ -269,6 +335,7 @@ static void hists__find_annotations(struct hists *hists,
 			nd = rb_next(nd);
 		} else if (use_browser == 1) {
 			key = hist_entry__tui_annotate(he, evsel, NULL);
+
 			switch (key) {
 			case -1:
 				if (!ann->skip_missing)
@@ -489,6 +556,9 @@ int cmd_annotate(int argc, const char **argv)
 	if (annotate.session == NULL)
 		return -1;
 
+	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
+						      HEADER_BRANCH_STACK);
+
 	ret = symbol__annotation_init();
 	if (ret < 0)
 		goto out_delete;
@@ -499,9 +569,6 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		goto out_delete;
 
-	if (setup_sorting(NULL) < 0)
-		usage_with_options(annotate_usage, options);
-
 	if (annotate.use_stdio)
 		use_browser = 0;
 	else if (annotate.use_tui)
@@ -511,6 +578,15 @@ int cmd_annotate(int argc, const char **argv)
 
 	setup_browser(true);
 
+	if (use_browser == 1 && annotate.has_br_stack) {
+		sort__mode = SORT_MODE__BRANCH;
+		if (setup_sorting(annotate.session->evlist) < 0)
+			usage_with_options(annotate_usage, options);
+	} else {
+		if (setup_sorting(NULL) < 0)
+			usage_with_options(annotate_usage, options);
+	}
+
 	ret = __cmd_annotate(&annotate);
 
 out_delete:
-- 
2.14.3

[PATCH 53/54] perf annotate: Handle s390 PC relative load and store instruction.

[Arnaldo Carvalho de Melo]

From: Thomas Richter <tmricht@linux.vnet.ibm.com>

S390 has several load and store instructions with target operand
addressing relative to the program counter, for example lrl, lgrl, strl,
stgrl.

These instructions are handled similar to x86. Objdump output displays
those instructions as:

   9595c: c4 2d 00 09 9c 54   lgrl   %r7,1c8540 <mp_+0x60>

This output is parsed (like on x86) and perf annotate shows those lines
as:

   lgrl   %r7,mp_+0x60

This patch handles the s390 specific instruction parsing for PC relative
load and store instructions.

Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180308120913.14802-1-tmricht@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/s390/annotate/instructions.c | 63 ++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index e80589fc5b58..46c21831f2ac 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -52,6 +52,61 @@ static struct ins_ops s390_call_ops = {
 	.scnprintf = call__scnprintf,
 };
 
+static int s390_mov__parse(struct arch *arch __maybe_unused,
+			   struct ins_operands *ops,
+			   struct map *map __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	ops->target.name = strdup(s + 1);
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops);
+
+static struct ins_ops s390_mov_ops = {
+	.parse	   = s390_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
 	struct ins_ops *ops = NULL;
@@ -68,6 +123,14 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 		ops = &s390_call_ops;
 	if (!strcmp(name, "br"))
 		ops = &ret_ops;
+	/* override load/store relative to PC */
+	if (!strcmp(name, "lrl") ||
+	    !strcmp(name, "lgrl") ||
+	    !strcmp(name, "lgfrl") ||
+	    !strcmp(name, "llgfrl") ||
+	    !strcmp(name, "strl") ||
+	    !strcmp(name, "stgrl"))
+		ops = &s390_mov_ops;
 
 	if (ops)
 		arch__associate_ins_ops(arch, name, ops);
-- 
2.14.3

[PATCH 54/54] perf tools: Update quipper information

[Arnaldo Carvalho de Melo]

From: Stephane Eranian <eranian@google.com>

This patch updates the links to the Quipper library.  It is now
available from GitHub and has been updated.

Reported-by: Lakshman Annadorai <lakshmana@google.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1520495985-2147-1-git-send-email-eranian@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf.data-file-format.txt | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index f7d85e89a98a..d00f0d51cab8 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -485,10 +485,5 @@ in pmu-tools parser. This allows to read perf.data from python and dump it.
 quipper
 
 The quipper C++ parser is available at
-https://chromium.googlesource.com/chromiumos/platform2
+http://github.com/google/perf_data_converter/tree/master/src/quipper
 
-It is under the chromiumos-wide-profiling/ subdirectory. This library can
-convert a perf data file to a protobuf and vice versa.
-
-Unfortunately this parser tends to be many versions behind and may not be able
-to parse data files generated by recent perf.
-- 
2.14.3

Re: [GIT PULL 00/54] perf/core improvements and fixes

[Ingo Molnar]

* Arnaldo Carvalho de Melo <acme@kernel.org> wrote:

> Hi Ingo,
> 
> 	Please consider pulling,
> 
> - Arnaldo
> 
> Test results at the end of this message, as usual.
> 
> The following changes since commit 3f986eefc89c528bf2d398a6dc3637b743a7139e:
> 
>   Merge branch 'perf/urgent' into perf/core, to resolve conflict (2018-03-07 09:23:12 +0100)
> 
> are available in the Git repository at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.17-20180308
> 
> for you to fetch changes up to 2427b432e63b4b911100f717c48289195b7a7d62:
> 
>   perf tools: Update quipper information (2018-03-08 11:30:54 -0300)
> 
> ----------------------------------------------------------------
> perf/core improvements and fixes:
> 
> - Support to display the IPC/Cycle in 'annotate' TUI, for systems
>   where this info can be obtained, like Intel's >= Skylake (Jin Yao)
> 
> - Support wildcards on PMU name in dynamic PMU events (Agustin Vega-Frias)
> 
> - Display pmu name when printing unmerged events in stat (Agustin Vega-Frias)
> 
> - Auto-merge PMU events created by prefix or glob match (Agustin Vega-Frias)
> 
> - Fix s390 'call' operations target function annotation (Thomas Richter)
> 
> - Handle s390 PC relative load and store instruction in the augmented
>   'annotate', code, used so far in the TUI modes of 'perf report' and
>   'perf annotate' (Thomas Richter)
> 
> - Provide libtraceevent with a kernel symbol resolver, so that
>   symbols in tracepoint fields can be resolved when showing them in
>   tools such as 'perf report' (Wang YanQing)
> 
> - Refactor the cgroups code to look more like other code in tools/perf,
>   using cgroup__{put,get} for refcount operations instead of its
>   open-coded equivalent, breaking larger functions, etc (Arnaldo Carvalho de Melo)
> 
> - Implement support for the -G/--cgroup target in 'perf trace', allowing
>   strace like tracing (plus other events, backtraces, etc) for cgroups
>   (Arnaldo Carvalho de Melo)
> 
> - Update thread shortname in 'perf sched map' when the thread's COMM
>   changes (Changbin Du)
> 
> - refcount 'struct mem_info', for better sharing it over several
>   users, avoid duplicating structs and fixing crashes related to
>   use after free (Jiri Olsa)
> 
> - Display perf.data version, offsets in 'perf report --header' (Jiri Olsa)
> 
> - Record the machine's memory topology information in a perf.data
>   feature section, to be used by tools such as 'perf c2c' (Jiri Olsa)
> 
> - Fix output of forced groups in the header for 'perf report' --stdio
>   and --tui (Jiri Olsa)
> 
> - Better support llvm, clang, cxx make tests in the build process (Jiri Olsa)
> 
> - Streamline the 'struct perf_mmap' methods, storing some info in the
>   struct instead of passing it via various methods, shortening its
>   signatures (Kan Liang)
> 
> - Update the quipper perf.data parser library site information (Stephane Eranian)
> 
> - Correct perf's man pages title markers for asciidoctor (Takashi Iwai)
> 
> - Intel PT fixes and refactorings paving the way for implementing
>   support for AUX area sampling (Adrian Hunter)
> 
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> 
> ----------------------------------------------------------------
> Adrian Hunter (13):
>       perf record: Combine some auxtrace initialization into a single function
>       perf auxtrace: Add missing parameters from kernel-doc comments
>       perf auxtrace: Rename some buffer-queuing functions
>       perf auxtrace: Make auxtrace_queues__add_buffer() return buffer_ptr
>       perf intel-pt: Fix overlap detection to identify consecutive buffers correctly
>       perf intel-pt: Fix sync_switch
>       perf intel-pt: Fix error recovery from missing TIP packet
>       perf intel-pt: Fix timestamp following overflow
>       perf intel-pt/bts: In auxtrace_record__init_intel() evlist is never NULL
>       perf intel-pt: Get rid of intel_pt_use_buffer_pid_tid()
>       perf intel-pt: Tidy old_buffer handling in intel_pt_get_trace()
>       perf intel-pt: Remove a check for sampling mode
>       perf intel-pt: Adjust overlap-checking to support sampling mode
> 
> Agustin Vega-Frias (3):
>       perf pmu: Support wildcards on pmu name in dynamic pmu events
>       perf pmu: Display pmu name when printing unmerged events in stat
>       perf pmu: Auto-merge PMU events created by prefix or glob match
> 
> Arnaldo Carvalho de Melo (11):
>       perf cgroup: Remove misplaced __maybe_unused
>       perf cgroup: Rename 'struct cgroup_sel' to 'struct cgroup'
>       perf cgroup: Introduce cgroup__delete()
>       perf cgroup: Rename close_cgroup() to cgroup__put()
>       perf cgroup: Introduce cgroup__get()
>       perf cgroup: Introduce find_cgroup() method
>       perf cgroup: Introduce cgroup__new() out of open coded equivalent
>       perf cgroup: Add evlist__findnew_cgroup()
>       perf cgroup: Add evlist__add_default_cgroup()
>       perf cgroup: Make the cgroup name be const char *
>       perf trace: Support setting cgroups as targets
> 
> Changbin Du (2):
>       perf sched: Move thread::shortname to thread_runtime
>       perf sched map: Re-annotate shortname if thread comm changed
> 
> Jin Yao (1):
>       perf annotate: Support to display the IPC/Cycle in TUI mode
> 
> Jiri Olsa (11):
>       perf report: Fix the output for stdio events list
>       perf report: Display perf.data header info
>       perf record: Move machine variable down the function
>       perf record: Remove progname from struct record
>       perf tools: Add refcnt into struct mem_info
>       perf c2c: Use mem_info refcnt logic
>       perf tools: Add MEM_TOPOLOGY feature to perf data file
>       perf tools: Update tags with .cpp files
>       perf build: Add llvm/clang/cxx make tests into FEATURE_TESTS_EXTRA
>       perf build: Add llvm/clang make targets to FILES
>       perf build: Force llvm/clang test compile output to .make.output
> 
> Kan Liang (8):
>       perf evlist: Store 'overwrite' in struct perf_mmap
>       perf mmap: Store mmap scope in struct perf_mmap()
>       perf mmap: Use the stored scope data in perf_mmap__push()
>       perf mmap: Use the stored data in perf_mmap__read_event()
>       perf mmap: Use stored 'overwrite' in perf_mmap__consume()
>       perf mmap: Simplify perf_mmap__consume()
>       perf mmap: Simplify perf_mmap__read_event()
>       perf mmap: Simplify perf_mmap__read_init()
> 
> Stephane Eranian (1):
>       perf tools: Update quipper information
> 
> Takashi Iwai (1):
>       perf tools: Correct title markers for asciidoctor
> 
> Thomas Richter (2):
>       perf annotate: Fix s390 target function disassembly
>       perf annotate: Handle s390 PC relative load and store instruction.
> 
> Wang YanQing (1):
>       perf report: Provide libtraceevent with a kernel symbol resolver
> 
>  tools/build/Makefile.feature                       |   6 +-
>  tools/build/feature/Makefile                       |  14 +-
>  tools/include/linux/bitmap.h                       |   2 +-
>  tools/perf/Documentation/perf-data.txt             |   2 +-
>  tools/perf/Documentation/perf-ftrace.txt           |   2 +-
>  tools/perf/Documentation/perf-kallsyms.txt         |   2 +-
>  tools/perf/Documentation/perf-list.txt             |   8 +-
>  tools/perf/Documentation/perf-sched.txt            |   2 +-
>  tools/perf/Documentation/perf-script-perl.txt      |   2 +-
>  tools/perf/Documentation/perf-stat.txt             |  17 ++
>  tools/perf/Documentation/perf-trace.txt            |  25 ++
>  tools/perf/Documentation/perf.data-file-format.txt |   7 +-
>  tools/perf/Makefile.perf                           |   6 +-
>  tools/perf/arch/s390/annotate/instructions.c       | 116 +++++++-
>  tools/perf/arch/x86/tests/perf-time-to-tsc.c       |   7 +-
>  tools/perf/arch/x86/util/auxtrace.c                |  14 +-
>  tools/perf/builtin-annotate.c                      |  88 +++++-
>  tools/perf/builtin-c2c.c                           |  24 +-
>  tools/perf/builtin-kvm.c                           |   9 +-
>  tools/perf/builtin-record.c                        |  45 +--
>  tools/perf/builtin-report.c                        |  26 +-
>  tools/perf/builtin-sched.c                         | 133 ++++++---
>  tools/perf/builtin-stat.c                          |  29 +-
>  tools/perf/builtin-top.c                           |   7 +-
>  tools/perf/builtin-trace.c                         |  57 +++-
>  tools/perf/tests/backward-ring-buffer.c            |   5 +-
>  tools/perf/tests/bpf.c                             |   5 +-
>  tools/perf/tests/code-reading.c                    |   7 +-
>  tools/perf/tests/keep-tracking.c                   |   7 +-
>  tools/perf/tests/mmap-basic.c                      |   7 +-
>  tools/perf/tests/openat-syscall-tp-fields.c        |   7 +-
>  tools/perf/tests/perf-record.c                     |   7 +-
>  tools/perf/tests/sw-clock.c                        |   7 +-
>  tools/perf/tests/switch-tracking.c                 |   7 +-
>  tools/perf/tests/task-exit.c                       |   7 +-
>  tools/perf/ui/browsers/hists.c                     |   5 +-
>  tools/perf/util/annotate.c                         |   2 +-
>  tools/perf/util/auxtrace.c                         |  37 ++-
>  tools/perf/util/auxtrace.h                         |   2 +
>  tools/perf/util/cgroup.c                           | 111 +++++---
>  tools/perf/util/cgroup.h                           |  13 +-
>  tools/perf/util/env.h                              |   9 +
>  tools/perf/util/evlist.c                           |   8 +-
>  tools/perf/util/evsel.c                            |  23 +-
>  tools/perf/util/evsel.h                            |   6 +-
>  tools/perf/util/header.c                           | 312 ++++++++++++++++++++-
>  tools/perf/util/header.h                           |   1 +
>  tools/perf/util/hist.c                             |   4 +-
>  .../perf/util/intel-pt-decoder/intel-pt-decoder.c  |  64 ++---
>  .../perf/util/intel-pt-decoder/intel-pt-decoder.h  |   2 +-
>  tools/perf/util/intel-pt.c                         | 110 ++++----
>  tools/perf/util/machine.c                          |   2 +-
>  tools/perf/util/mmap.c                             |  63 ++---
>  tools/perf/util/mmap.h                             |  16 +-
>  tools/perf/util/parse-events.c                     |  21 +-
>  tools/perf/util/parse-events.h                     |   2 +-
>  tools/perf/util/parse-events.l                     |   2 +-
>  tools/perf/util/parse-events.y                     |  18 +-
>  tools/perf/util/python.c                           |   7 +-
>  tools/perf/util/symbol.c                           |  22 ++
>  tools/perf/util/symbol.h                           |  19 +-
>  tools/perf/util/thread.h                           |   1 -
>  62 files changed, 1197 insertions(+), 401 deletions(-)

Pulled, thanks a lot Arnaldo!

	Ingo