An error occurred fetching the project authors.
  1. 25 Oct, 2023 4 commits
    • Ian Rogers's avatar
      perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit · 56e144fe
      Ian Rogers authored
      Fix leak where mem_info__put wouldn't release the maps/map as used by
      perf mem. Add exit functions and use elsewhere that the maps and map
      are released.
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: K Prateek Nayak <kprateek.nayak@amd.com>
      Cc: Ravi Bangoria <ravi.bangoria@amd.com>
      Cc: Sandipan Das <sandipan.das@amd.com>
      Cc: Anshuman Khandual <anshuman.khandual@arm.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Nick Terrell <terrelln@fb.com>
      Cc: Sean Christopherson <seanjc@google.com>
      Cc: Changbin Du <changbin.du@huawei.com>
      Cc: liuwenyu <liuwenyu7@huawei.com>
      Cc: Yang Jihong <yangjihong1@huawei.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Song Liu <song@kernel.org>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
      Cc: Yanteng Si <siyanteng@loongson.cn>
      Cc: Liam Howlett <liam.howlett@oracle.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Link: https://lore.kernel.org/r/20231024222353.3024098-12-irogers@google.comSigned-off-by: default avatarNamhyung Kim <namhyung@kernel.org>
      56e144fe
    • Ian Rogers's avatar
      perf callchain: Make brtype_stat in callchain_list optional · 6ba29fbb
      Ian Rogers authored
      struct callchain_list is 352bytes in size, 232 of which are
      brtype_stat. brtype_stat is only used for certain callchain_list
      items so make it optional, allocating when necessary. So that
      printing doesn't need to deal with an optional brtype_stat, pass
      an empty/zero version.
      
      Before:
      ```
      struct callchain_list {
              u64                        ip;                   /*     0     8 */
              struct map_symbol          ms;                   /*     8    24 */
              struct {
                      _Bool              unfolded;             /*    32     1 */
                      _Bool              has_children;         /*    33     1 */
              };                                               /*    32     2 */
      
              /* XXX 6 bytes hole, try to pack */
      
              u64                        branch_count;         /*    40     8 */
              u64                        from_count;           /*    48     8 */
              u64                        predicted_count;      /*    56     8 */
              /* --- cacheline 1 boundary (64 bytes) --- */
              u64                        abort_count;          /*    64     8 */
              u64                        cycles_count;         /*    72     8 */
              u64                        iter_count;           /*    80     8 */
              u64                        iter_cycles;          /*    88     8 */
              struct branch_type_stat    brtype_stat;          /*    96   232 */
              /* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */
              const char  *              srcline;              /*   328     8 */
              struct list_head           list;                 /*   336    16 */
      
              /* size: 352, cachelines: 6, members: 13 */
              /* sum members: 346, holes: 1, sum holes: 6 */
              /* last cacheline: 32 bytes */
      };
      ```
      
      After:
      ```
      struct callchain_list {
              u64                        ip;                   /*     0     8 */
              struct map_symbol          ms;                   /*     8    24 */
              struct {
                      _Bool              unfolded;             /*    32     1 */
                      _Bool              has_children;         /*    33     1 */
              };                                               /*    32     2 */
      
              /* XXX 6 bytes hole, try to pack */
      
              u64                        branch_count;         /*    40     8 */
              u64                        from_count;           /*    48     8 */
              u64                        predicted_count;      /*    56     8 */
              /* --- cacheline 1 boundary (64 bytes) --- */
              u64                        abort_count;          /*    64     8 */
              u64                        cycles_count;         /*    72     8 */
              u64                        iter_count;           /*    80     8 */
              u64                        iter_cycles;          /*    88     8 */
              struct branch_type_stat *  brtype_stat;          /*    96     8 */
              const char  *              srcline;              /*   104     8 */
              struct list_head           list;                 /*   112    16 */
      
              /* size: 128, cachelines: 2, members: 13 */
              /* sum members: 122, holes: 1, sum holes: 6 */
      };
      ```
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: K Prateek Nayak <kprateek.nayak@amd.com>
      Cc: Ravi Bangoria <ravi.bangoria@amd.com>
      Cc: Sandipan Das <sandipan.das@amd.com>
      Cc: Anshuman Khandual <anshuman.khandual@arm.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Nick Terrell <terrelln@fb.com>
      Cc: Sean Christopherson <seanjc@google.com>
      Cc: Changbin Du <changbin.du@huawei.com>
      Cc: liuwenyu <liuwenyu7@huawei.com>
      Cc: Yang Jihong <yangjihong1@huawei.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Song Liu <song@kernel.org>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
      Cc: Yanteng Si <siyanteng@loongson.cn>
      Cc: Liam Howlett <liam.howlett@oracle.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Link: https://lore.kernel.org/r/20231024222353.3024098-10-irogers@google.comSigned-off-by: default avatarNamhyung Kim <namhyung@kernel.org>
      6ba29fbb
    • Ian Rogers's avatar
      perf callchain: Make display use of branch_type_stat const · d47d876d
      Ian Rogers authored
      Display code doesn't modify the branch_type_stat so switch uses to
      const. This is done to aid refactoring struct callchain_list where
      current the branch_type_stat is embedded even if not used.
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: K Prateek Nayak <kprateek.nayak@amd.com>
      Cc: Ravi Bangoria <ravi.bangoria@amd.com>
      Cc: Sandipan Das <sandipan.das@amd.com>
      Cc: Anshuman Khandual <anshuman.khandual@arm.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Nick Terrell <terrelln@fb.com>
      Cc: Sean Christopherson <seanjc@google.com>
      Cc: Changbin Du <changbin.du@huawei.com>
      Cc: liuwenyu <liuwenyu7@huawei.com>
      Cc: Yang Jihong <yangjihong1@huawei.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Song Liu <song@kernel.org>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
      Cc: Yanteng Si <siyanteng@loongson.cn>
      Cc: Liam Howlett <liam.howlett@oracle.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Link: https://lore.kernel.org/r/20231024222353.3024098-9-irogers@google.comSigned-off-by: default avatarNamhyung Kim <namhyung@kernel.org>
      d47d876d
    • Ian Rogers's avatar
      libperf rc_check: Add RC_CHK_EQUAL · 78c32f4c
      Ian Rogers authored
      Comparing pointers with reference count checking is tricky to avoid a
      SEGV. Add a convenience macro to simplify and use.
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: K Prateek Nayak <kprateek.nayak@amd.com>
      Cc: Ravi Bangoria <ravi.bangoria@amd.com>
      Cc: Sandipan Das <sandipan.das@amd.com>
      Cc: Anshuman Khandual <anshuman.khandual@arm.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Nick Terrell <terrelln@fb.com>
      Cc: Sean Christopherson <seanjc@google.com>
      Cc: Changbin Du <changbin.du@huawei.com>
      Cc: liuwenyu <liuwenyu7@huawei.com>
      Cc: Yang Jihong <yangjihong1@huawei.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Song Liu <song@kernel.org>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
      Cc: Yanteng Si <siyanteng@loongson.cn>
      Cc: Liam Howlett <liam.howlett@oracle.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Link: https://lore.kernel.org/r/20231024222353.3024098-5-irogers@google.comSigned-off-by: default avatarNamhyung Kim <namhyung@kernel.org>
      78c32f4c
  2. 12 Jun, 2023 2 commits
    • Ian Rogers's avatar
      perf callchain: Use pthread keys for tls callchain_cursor · 8ab12a20
      Ian Rogers authored
      Pthread keys are more portable than __thread and allow the association
      of a destructor with the key. Use the destructor to clean up TLS
      callchain cursors to aid understanding memory leaks.
      
      Committer notes:
      
      Had to fixup a series of unconverted places and also check for the
      return of get_tls_callchain_cursor() as it may fail and return NULL.
      
      In that unlikely case we now either print something to a file, if the
      caller was expecting to print a callchain, or return an error code to
      state that resolving the callchain isn't possible.
      
      In some cases this was made easier because thread__resolve_callchain()
      already can fail for other reasons, so this new one (cursor == NULL) can
      be added and the callers don't have to explicitely check for this new
      condition.
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Ali Saidi <alisaidi@amazon.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
      Cc: Brian Robbins <brianrob@linux.microsoft.com>
      Cc: Changbin Du <changbin.du@huawei.com>
      Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
      Cc: Fangrui Song <maskray@google.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: Ivan Babrou <ivan@cloudflare.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: John Garry <john.g.garry@oracle.com>
      Cc: K Prateek Nayak <kprateek.nayak@amd.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Liam Howlett <liam.howlett@oracle.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Mike Leach <mike.leach@linaro.org>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Ravi Bangoria <ravi.bangoria@amd.com>
      Cc: Sean Christopherson <seanjc@google.com>
      Cc: Steinar H. Gunderson <sesse@google.com>
      Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
      Cc: Wenyu Liu <liuwenyu7@huawei.com>
      Cc: Will Deacon <will@kernel.org>
      Cc: Yang Jihong <yangjihong1@huawei.com>
      Cc: Ye Xingchen <ye.xingchen@zte.com.cn>
      Cc: Yuan Can <yuancan@huawei.com>
      Cc: coresight@lists.linaro.org
      Cc: linux-arm-kernel@lists.infradead.org
      Link: https://lore.kernel.org/r/20230608232823.4027869-25-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      8ab12a20
    • Ian Rogers's avatar
      perf map/maps/thread: Changes to reference counting · bffb5b0c
      Ian Rogers authored
      Fix missed reference count gets and puts as detected with leak
      sanitizer and reference count checking.
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Ali Saidi <alisaidi@amazon.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
      Cc: Brian Robbins <brianrob@linux.microsoft.com>
      Cc: Changbin Du <changbin.du@huawei.com>
      Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
      Cc: Fangrui Song <maskray@google.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: Ivan Babrou <ivan@cloudflare.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: John Garry <john.g.garry@oracle.com>
      Cc: K Prateek Nayak <kprateek.nayak@amd.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Liam Howlett <liam.howlett@oracle.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Mike Leach <mike.leach@linaro.org>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Ravi Bangoria <ravi.bangoria@amd.com>
      Cc: Sean Christopherson <seanjc@google.com>
      Cc: Steinar H. Gunderson <sesse@google.com>
      Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
      Cc: Wenyu Liu <liuwenyu7@huawei.com>
      Cc: Will Deacon <will@kernel.org>
      Cc: Yang Jihong <yangjihong1@huawei.com>
      Cc: Ye Xingchen <ye.xingchen@zte.com.cn>
      Cc: Yuan Can <yuancan@huawei.com>
      Cc: coresight@lists.linaro.org
      Cc: linux-arm-kernel@lists.infradead.org
      Link: https://lore.kernel.org/r/20230608232823.4027869-21-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      bffb5b0c
  3. 07 Apr, 2023 2 commits
    • Ian Rogers's avatar
      perf map: Changes to reference counting · ec417ad4
      Ian Rogers authored
      When a pointer to a map exists do a get, when that pointer is
      overwritten or freed, put the map. This avoids issues with gets and
      puts being inconsistently used causing, use after puts, etc. For
      example, the map in struct addr_location is changed to hold a
      reference count. Reference count checking and address sanitizer were
      used to identify issues.
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
      Cc: Darren Hart <dvhart@infradead.org>
      Cc: Davidlohr Bueso <dave@stgolabs.net>
      Cc: Dmitriy Vyukov <dvyukov@google.com>
      Cc: Eric Dumazet <edumazet@google.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: Hao Luo <haoluo@google.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: John Garry <john.g.garry@oracle.com>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miaoqian Lin <linmq006@gmail.com>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Riccardo Mancini <rickyman7@gmail.com>
      Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
      Cc: Song Liu <song@kernel.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
      Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: Thomas Richter <tmricht@linux.ibm.com>
      Cc: Yury Norov <yury.norov@gmail.com>
      Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      ec417ad4
    • Liam Howlett's avatar
      tools: Rename __fallthrough to fallthrough · f7a858bf
      Liam Howlett authored
      Rename the fallthrough attribute to better align with the kernel
      version.  Copy the definition from include/linux/compiler_attributes.h
      including the #else clause.  Adding the #else clause allows the tools
      compiler.h header to drop the check for a definition entirely and keeps
      both definitions together.
      
      Change any __fallthrough statements to fallthrough anywhere it was used
      within perf.
      
      This allows other tools to use the same key word as the kernel.
      
      Committer notes:
      
      Did some missing conversions to:
      
        builtin-list.c
      
      Also included gtk.h before the 'fallthrough' definition in:
      
        tools/perf/ui/gtk/hists.c
        tools/perf/ui/gtk/helpline.c
        tools/perf/ui/gtk/browser.c
      
      As it is the arg name for a macro in glib.h:
      
        /var/home/acme/git/perf-tools-next/tools/include/linux/compiler-gcc.h:16:55: error: missing binary operator before token "("
           16 | # define fallthrough                    __attribute__((__fallthrough__))
              |                                                       ^
        /usr/include/glib-2.0/glib/gmacros.h:637:28: note: in expansion of macro ‘fallthrough’
          637 | #if g_macro__has_attribute(fallthrough)
      Reviewed-by: default avatarMiguel Ojeda <ojeda@kernel.org>
      Signed-off-by: default avatarLiam Howlett <Liam.Howlett@oracle.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Miguel Ojeda <ojeda@kernel.org>
      Cc: Nathan Chancellor <nathan@kernel.org>
      Cc: Nick Desaulniers <ndesaulniers@google.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
      Cc: Tom Rix <trix@redhat.com>
      Cc: linux-sparse@vger.kernel.org <linux-sparse@vger.kernel.org>
      Cc: llvm@lists.linux.dev <llvm@lists.linux.dev>
      Link: https://lore.kernel.org/r/20221125154947.2163498-1-Liam.Howlett@oracle.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      f7a858bf
  4. 04 Apr, 2023 2 commits
    • Ian Rogers's avatar
      perf map: Add accessor for dso · 63df0e4b
      Ian Rogers authored
      Later changes will add reference count checking for struct map, with
      dso being the most frequently accessed variable. Add an accessor so
      that the reference count check is only necessary in one place.
      
      Additional changes:
       - add a dso variable to avoid repeated map__dso calls.
       - in builtin-mem.c dump_raw_samples, code only partially tested for
         dso == NULL. Make the possibility of NULL consistent.
       - in thread.c thread__memcpy fix use of spaces and use tabs.
      
      Committer notes:
      
      Did missing conversions on these files:
      
         tools/perf/arch/powerpc/util/skip-callchain-idx.c
         tools/perf/arch/powerpc/util/sym-handling.c
         tools/perf/ui/browsers/hists.c
         tools/perf/ui/gtk/annotate.c
         tools/perf/util/cs-etm.c
         tools/perf/util/thread.c
         tools/perf/util/unwind-libunwind-local.c
         tools/perf/util/unwind-libunwind.c
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
      Cc: Darren Hart <dvhart@infradead.org>
      Cc: Davidlohr Bueso <dave@stgolabs.net>
      Cc: Dmitriy Vyukov <dvyukov@google.com>
      Cc: Eric Dumazet <edumazet@google.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: Hao Luo <haoluo@google.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: John Garry <john.g.garry@oracle.com>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miaoqian Lin <linmq006@gmail.com>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Riccardo Mancini <rickyman7@gmail.com>
      Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
      Cc: Song Liu <song@kernel.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
      Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: Thomas Richter <tmricht@linux.ibm.com>
      Cc: Yury Norov <yury.norov@gmail.com>
      Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      63df0e4b
    • Ian Rogers's avatar
      perf maps: Add functions to access maps · 5ab6d715
      Ian Rogers authored
      Introduce functions to access struct maps. These functions reduce the
      number of places reference counting is necessary. While tidying APIs do
      some small const-ification, in particlar to unwind_libunwind_ops.
      
      Committer notes:
      
      Fixed up tools/perf/util/unwind-libunwind.c:
      
      -               return ops->get_entries(cb, arg, thread, data, max_stack);
      +               return ops->get_entries(cb, arg, thread, data, max_stack, best_effort);
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
      Cc: Darren Hart <dvhart@infradead.org>
      Cc: Davidlohr Bueso <dave@stgolabs.net>
      Cc: Dmitriy Vyukov <dvyukov@google.com>
      Cc: Eric Dumazet <edumazet@google.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: Hao Luo <haoluo@google.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: John Garry <john.g.garry@oracle.com>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miaoqian Lin <linmq006@gmail.com>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Riccardo Mancini <rickyman7@gmail.com>
      Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
      Cc: Song Liu <song@kernel.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
      Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: Thomas Richter <tmricht@linux.ibm.com>
      Cc: Yury Norov <yury.norov@gmail.com>
      Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      5ab6d715
  5. 04 Oct, 2022 1 commit
  6. 12 Jul, 2022 1 commit
  7. 14 Feb, 2022 1 commit
    • Ian Rogers's avatar
      perf maps: Use a pointer for kmaps · 1a97cee6
      Ian Rogers authored
      struct maps is reference counted, using a pointer is more idiomatic.
      
      Committer notes:
      
      Delay:
      
         maps = machine__kernel_maps(&vmlinux);
      
      To after:
      
        machine__init(&vmlinux, "", HOST_KERNEL_ID);
      
      To avoid this on f34:
      
        In file included from /var/home/acme/git/perf/tools/perf/util/build-id.h:10,
                         from /var/home/acme/git/perf/tools/perf/util/dso.h:13,
                         from tests/vmlinux-kallsyms.c:8:
        In function ‘machine__kernel_maps’,
            inlined from ‘test__vmlinux_matches_kallsyms’ at tests/vmlinux-kallsyms.c:122:22:
        /var/home/acme/git/perf/tools/perf/util/machine.h:86:23: error: ‘vmlinux.kmaps’ is used uninitialized [-Werror=uninitialized]
           86 |         return machine->kmaps;
              |                ~~~~~~~^~~~~~~
        tests/vmlinux-kallsyms.c: In function ‘test__vmlinux_matches_kallsyms’:
        tests/vmlinux-kallsyms.c:121:34: note: ‘vmlinux’ declared here
          121 |         struct machine kallsyms, vmlinux;
              |                                  ^~~~~~~
        cc1: all warnings being treated as errors
      Signed-off-by: default avatarIan Rogers <irogers@google.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: André Almeida <andrealmeid@collabora.com>
      Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
      Cc: Darren Hart <dvhart@infradead.org>
      Cc: Davidlohr Bueso <dave@stgolabs.net>
      Cc: Dmitriy Vyukov <dvyukov@google.com>
      Cc: Eric Dumazet <edumazet@google.com>
      Cc: German Gomez <german.gomez@arm.com>
      Cc: Hao Luo <haoluo@google.com>
      Cc: James Clark <james.clark@arm.com>
      Cc: Jin Yao <yao.jin@linux.intel.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: John Garry <john.garry@huawei.com>
      Cc: Kajol Jain <kjain@linux.ibm.com>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Leo Yan <leo.yan@linaro.org>
      Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
      Cc: Mark Rutland <mark.rutland@arm.com>
      Cc: Masami Hiramatsu <mhiramat@kernel.org>
      Cc: Miaoqian Lin <linmq006@gmail.com>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Riccardo Mancini <rickyman7@gmail.com>
      Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
      Cc: Song Liu <song@kernel.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
      Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: Thomas Richter <tmricht@linux.ibm.com>
      Cc: Yury Norov <yury.norov@gmail.com>
      Link: http://lore.kernel.org/lkml/20220211103415.2737789-6-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      1a97cee6
  8. 21 Dec, 2021 1 commit
  9. 23 Mar, 2021 1 commit
  10. 14 Oct, 2020 3 commits
  11. 28 May, 2020 1 commit
  12. 26 Nov, 2019 2 commits
  13. 12 Nov, 2019 3 commits
  14. 20 Sep, 2019 1 commit
  15. 01 Sep, 2019 1 commit
  16. 31 Aug, 2019 1 commit
  17. 29 Aug, 2019 1 commit
  18. 26 Aug, 2019 1 commit
  19. 29 Jul, 2019 1 commit
  20. 09 Jul, 2019 2 commits
  21. 06 Feb, 2019 3 commits
  22. 04 Jan, 2019 1 commit
    • Jin Yao's avatar
      perf report: Fix wrong iteration count in --branch-history · a3366db0
      Jin Yao authored
      By calculating the removed loops, we can get the iteration count.
      
      But the iteration count could be reported incorrectly, reporting
      impossibly high counts.
      
      That's because previous code uses the number of removed LBR entries for
      the iteration count. That's not good. Fix this by increasing the
      iteration count when a loop is detected.
      
      When matching the chain, the iteration count would be added up, finally we need
      to compute the average value when printing out.
      
      For example,
      
        $ perf report --branch-history --stdio --no-children
      
      Before:
      
        ---f2 +0
           |
           |--33.62%--f1 +9 (cycles:1)
           |          f1 +0
           |          main +22 (cycles:1)
           |          main +17
           |          main +38 (cycles:1)
           |          main +27
           |          f1 +26 (cycles:1)
           |          f1 +24
           |          f2 +27 (cycles:7)
           |          f2 +0
           |          f1 +19 (cycles:1)
           |          f1 +14
           |          f2 +27 (cycles:11)
           |          f2 +0
           |          f1 +9 (cycles:1 iter:2968 avg_cycles:3)
           |          f1 +0
           |          main +22 (cycles:1 iter:2968 avg_cycles:3)
           |          main +17
           |          main +38 (cycles:1 iter:2968 avg_cycles:3)
      
      2968 is an impossible high iteration count and avg_cycles is too small.
      
      After:
      
        ---f2 +0
           |
           |--33.62%--f1 +9 (cycles:1)
           |          f1 +0
           |          main +22 (cycles:1)
           |          main +17
           |          main +38 (cycles:1)
           |          main +27
           |          f1 +26 (cycles:1)
           |          f1 +24
           |          f2 +27 (cycles:7)
           |          f2 +0
           |          f1 +19 (cycles:1)
           |          f1 +14
           |          f2 +27 (cycles:11)
           |          f2 +0
           |          f1 +9 (cycles:1 iter:1 avg_cycles:23)
           |          f1 +0
           |          main +22 (cycles:1 iter:1 avg_cycles:23)
           |          main +17
           |          main +38 (cycles:1 iter:1 avg_cycles:23)
      
      avg_cycles:23 is the average cycles of this iteration.
      
      Fixes: c4ee0625 ("perf report: Calculate the average cycles of iterations")
      Signed-off-by: default avatarJin Yao <yao.jin@linux.intel.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Andi Kleen <ak@linux.intel.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: Kan Liang <kan.liang@linux.intel.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Link: http://lkml.kernel.org/r/1546582230-17507-1-git-send-email-yao.jin@linux.intel.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      a3366db0
  23. 17 Jan, 2018 1 commit
    • Arnaldo Carvalho de Melo's avatar
      perf unwind: Do not look just at the global callchain_param.record_mode · eabad8c6
      Arnaldo Carvalho de Melo authored
      When setting up DWARF callchains on specific events, without using
      'record' or 'trace' --call-graph, but instead doing it like:
      
      	perf trace -e cycles/call-graph=dwarf/
      
      The unwind__prepare_access() call in thread__insert_map() when we
      process PERF_RECORD_MMAP(2) metadata events were not being performed,
      precluding us from using per-event DWARF callchains, handling them just
      when we asked for all events to be DWARF, using "--call-graph dwarf".
      
      We do it in the PERF_RECORD_MMAP because we have to look at one of the
      executable maps to figure out the executable type (64-bit, 32-bit) of
      the DSO laid out in that mmap. Also to look at the architecture where
      the perf.data file was recorded.
      
      All this probably should be deferred to when we process a sample for
      some thread that has callchains, so that we do this processing only for
      the threads with samples, not for all of them.
      
      For now, fix using DWARF on specific events.
      
      Before:
      
        # perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
        PING ::1(::1) 56 data bytes
        64 bytes from ::1: icmp_seq=1 ttl=64 time=0.048 ms
      
        --- ::1 ping statistics ---
        1 packets transmitted, 1 received, 0% packet loss, time 0ms
        rtt min/avg/max/mdev = 0.048/0.048/0.048/0.000 ms
           0.000 probe_libc:inet_pton:(7fe9597bb350))
        Problem processing probe_libc:inet_pton callchain, skipping...
        #
      
      After:
      
        # perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
        PING ::1(::1) 56 data bytes
        64 bytes from ::1: icmp_seq=1 ttl=64 time=0.060 ms
      
        --- ::1 ping statistics ---
        1 packets transmitted, 1 received, 0% packet loss, time 0ms
        rtt min/avg/max/mdev = 0.060/0.060/0.060/0.000 ms
             0.000 probe_libc:inet_pton:(7fd4aa930350))
                                               __inet_pton (inlined)
                                               gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
                                               __GI_getaddrinfo (inlined)
                                               [0xffffaa804e51af3f] (/usr/bin/ping)
                                               __libc_start_main (/usr/lib64/libc-2.26.so)
                                               [0xffffaa804e51b379] (/usr/bin/ping)
        #
        # perf trace --call-graph=dwarf --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
        PING ::1(::1) 56 data bytes
        64 bytes from ::1: icmp_seq=1 ttl=64 time=0.057 ms
      
        --- ::1 ping statistics ---
        1 packets transmitted, 1 received, 0% packet loss, time 0ms
        rtt min/avg/max/mdev = 0.057/0.057/0.057/0.000 ms
             0.000 probe_libc:inet_pton:(7f9363b9e350))
                                               __inet_pton (inlined)
                                               gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
                                               __GI_getaddrinfo (inlined)
                                               [0xffffa9e8a14e0f3f] (/usr/bin/ping)
                                               __libc_start_main (/usr/lib64/libc-2.26.so)
                                               [0xffffa9e8a14e1379] (/usr/bin/ping)
        #
        # perf trace --call-graph=fp --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
        PING ::1(::1) 56 data bytes
        64 bytes from ::1: icmp_seq=1 ttl=64 time=0.077 ms
      
        --- ::1 ping statistics ---
        1 packets transmitted, 1 received, 0% packet loss, time 0ms
        rtt min/avg/max/mdev = 0.077/0.077/0.077/0.000 ms
             0.000 probe_libc:inet_pton:(7f4947e1c350))
                                               __inet_pton (inlined)
                                               gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
                                               __GI_getaddrinfo (inlined)
                                               [0xffffaa716d88ef3f] (/usr/bin/ping)
                                               __libc_start_main (/usr/lib64/libc-2.26.so)
                                               [0xffffaa716d88f379] (/usr/bin/ping)
        #
        # perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=fp/ ping -6 -c 1 ::1
        PING ::1(::1) 56 data bytes
        64 bytes from ::1: icmp_seq=1 ttl=64 time=0.078 ms
      
        --- ::1 ping statistics ---
        1 packets transmitted, 1 received, 0% packet loss, time 0ms
        rtt min/avg/max/mdev = 0.078/0.078/0.078/0.000 ms
             0.000 probe_libc:inet_pton:(7fa157696350))
                                               __GI___inet_pton (/usr/lib64/libc-2.26.so)
                                               getaddrinfo (/usr/lib64/libc-2.26.so)
                                               [0xffffa9ba39c74f40] (/usr/bin/ping)
        #
      Acked-by: default avatarNamhyung Kim <namhyung@kernel.org>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: David Ahern <dsahern@gmail.com>
      Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
      Cc: Wang Nan <wangnan0@huawei.com>
      Link: https://lkml.kernel.org/r/20180116182650.GE16107@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      eabad8c6
  24. 02 Nov, 2017 1 commit
    • Greg Kroah-Hartman's avatar
      License cleanup: add SPDX GPL-2.0 license identifier to files with no license · b2441318
      Greg Kroah-Hartman authored
      Many source files in the tree are missing licensing information, which
      makes it harder for compliance tools to determine the correct license.
      
      By default all files without license information are under the default
      license of the kernel, which is GPL version 2.
      
      Update the files which contain no license information with the 'GPL-2.0'
      SPDX license identifier.  The SPDX identifier is a legally binding
      shorthand, which can be used instead of the full boiler plate text.
      
      This patch is based on work done by Thomas Gleixner and Kate Stewart and
      Philippe Ombredanne.
      
      How this work was done:
      
      Patches were generated and checked against linux-4.14-rc6 for a subset of
      the use cases:
       - file had no licensing information it it.
       - file was a */uapi/* one with no licensing information in it,
       - file was a */uapi/* one with existing licensing information,
      
      Further patches will be generated in subsequent months to fix up cases
      where non-standard license headers were used, and references to license
      had to be inferred by heuristics based on keywords.
      
      The analysis to determine which SPDX License Identifier to be applied to
      a file was done in a spreadsheet of side by side results from of the
      output of two independent scanners (ScanCode & Windriver) producing SPDX
      tag:value files created by Philippe Ombredanne.  Philippe prepared the
      base worksheet, and did an initial spot review of a few 1000 files.
      
      The 4.13 kernel was the starting point of the analysis with 60,537 files
      assessed.  Kate Stewart did a file by file comparison of the scanner
      results in the spreadsheet to determine which SPDX license identifier(s)
      to be applied to the file. She confirmed any determination that was not
      immediately clear with lawyers working with the Linux Foundation.
      
      Criteria used to select files for SPDX license identifier tagging was:
       - Files considered eligible had to be source code files.
       - Make and config files were included as candidates if they contained >5
         lines of source
       - File already had some variant of a license header in it (even if <5
         lines).
      
      All documentation files were explicitly excluded.
      
      The following heuristics were used to determine which SPDX license
      identifiers to apply.
      
       - when both scanners couldn't find any license traces, file was
         considered to have no license information in it, and the top level
         COPYING file license applied.
      
         For non */uapi/* files that summary was:
      
         SPDX license identifier                            # files
         ---------------------------------------------------|-------
         GPL-2.0                                              11139
      
         and resulted in the first patch in this series.
      
         If that file was a */uapi/* path one, it was "GPL-2.0 WITH
         Linux-syscall-note" otherwise it was "GPL-2.0".  Results of that was:
      
         SPDX license identifier                            # files
         ---------------------------------------------------|-------
         GPL-2.0 WITH Linux-syscall-note                        930
      
         and resulted in the second patch in this series.
      
       - if a file had some form of licensing information in it, and was one
         of the */uapi/* ones, it was denoted with the Linux-syscall-note if
         any GPL family license was found in the file or had no licensing in
         it (per prior point).  Results summary:
      
         SPDX license identifier                            # files
         ---------------------------------------------------|------
         GPL-2.0 WITH Linux-syscall-note                       270
         GPL-2.0+ WITH Linux-syscall-note                      169
         ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause)    21
         ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)    17
         LGPL-2.1+ WITH Linux-syscall-note                      15
         GPL-1.0+ WITH Linux-syscall-note                       14
         ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause)    5
         LGPL-2.0+ WITH Linux-syscall-note                       4
         LGPL-2.1 WITH Linux-syscall-note                        3
         ((GPL-2.0 WITH Linux-syscall-note) OR MIT)              3
         ((GPL-2.0 WITH Linux-syscall-note) AND MIT)             1
      
         and that resulted in the third patch in this series.
      
       - when the two scanners agreed on the detected license(s), that became
         the concluded license(s).
      
       - when there was disagreement between the two scanners (one detected a
         license but the other didn't, or they both detected different
         licenses) a manual inspection of the file occurred.
      
       - In most cases a manual inspection of the information in the file
         resulted in a clear resolution of the license that should apply (and
         which scanner probably needed to revisit its heuristics).
      
       - When it was not immediately clear, the license identifier was
         confirmed with lawyers working with the Linux Foundation.
      
       - If there was any question as to the appropriate license identifier,
         the file was flagged for further research and to be revisited later
         in time.
      
      In total, over 70 hours of logged manual review was done on the
      spreadsheet to determine the SPDX license identifiers to apply to the
      source files by Kate, Philippe, Thomas and, in some cases, confirmation
      by lawyers working with the Linux Foundation.
      
      Kate also obtained a third independent scan of the 4.13 code base from
      FOSSology, and compared selected files where the other two scanners
      disagreed against that SPDX file, to see if there was new insights.  The
      Windriver scanner is based on an older version of FOSSology in part, so
      they are related.
      
      Thomas did random spot checks in about 500 files from the spreadsheets
      for the uapi headers and agreed with SPDX license identifier in the
      files he inspected. For the non-uapi files Thomas did random spot checks
      in about 15000 files.
      
      In initial set of patches against 4.14-rc6, 3 files were found to have
      copy/paste license identifier errors, and have been fixed to reflect the
      correct identifier.
      
      Additionally Philippe spent 10 hours this week doing a detailed manual
      inspection and review of the 12,461 patched files from the initial patch
      version early this week with:
       - a full scancode scan run, collecting the matched texts, detected
         license ids and scores
       - reviewing anything where there was a license detected (about 500+
         files) to ensure that the applied SPDX license was correct
       - reviewing anything where there was no detection but the patch license
         was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
         SPDX license was correct
      
      This produced a worksheet with 20 files needing minor correction.  This
      worksheet was then exported into 3 different .csv files for the
      different types of files to be modified.
      
      These .csv files were then reviewed by Greg.  Thomas wrote a script to
      parse the csv files and add the proper SPDX tag to the file, in the
      format that the file expected.  This script was further refined by Greg
      based on the output to detect more types of files automatically and to
      distinguish between header and source .c files (which need different
      comment types.)  Finally Greg ran the script using the .csv files to
      generate the patches.
      Reviewed-by: default avatarKate Stewart <kstewart@linuxfoundation.org>
      Reviewed-by: default avatarPhilippe Ombredanne <pombredanne@nexb.com>
      Reviewed-by: default avatarThomas Gleixner <tglx@linutronix.de>
      Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      b2441318
  25. 31 Oct, 2017 1 commit
  26. 25 Oct, 2017 1 commit
    • Milian Wolff's avatar
      perf report: Use srcline from callchain for hist entries · 1fb7d06a
      Milian Wolff authored
      This also removes the symbol name from the srcline column, more on this
      below.
      
      This ensures we use the correct srcline, which could originate from a
      potentially inlined function. The hist entries used to query for the
      srcline based purely on the IP, which leads to wrong results for inlined
      entries.
      
      Before:
      
      ~~~~~
        perf report --inline -s srcline -g none --stdio
        ...
        # Children      Self  Source:Line
        # ........  ........  ..................................................................................................................................
        #
            94.23%     0.00%  __libc_start_main+18446603487898210537
            94.23%     0.00%  _start+41
            44.58%     0.00%  main+100
            44.58%     0.00%  std::_Norm_helper<true>::_S_do_it<double>+100
            44.58%     0.00%  std::__complex_abs+100
            44.58%     0.00%  std::abs<double>+100
            44.58%     0.00%  std::norm<double>+100
            36.01%     0.00%  hypot+18446603487892193300
            25.81%     0.00%  main+41
            25.81%     0.00%  std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+41
            25.81%     0.00%  std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+41
            25.75%    25.75%  random.h:143
            18.39%     0.00%  main+57
            18.39%     0.00%  std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+57
            18.39%     0.00%  std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+57
            13.80%    13.80%  random.tcc:3330
             5.64%     0.00%  ??:0
             4.13%     4.13%  __hypot_finite+163
             4.13%     0.00%  __hypot_finite+18446603487892193443
      ...
      ~~~~~
      
      After:
      
      ~~~~~
        perf report --inline -s srcline -g none --stdio
        ...
        # Children      Self  Source:Line
        # ........  ........  ...........................................
        #
            94.30%     1.19%  main.cpp:39
            94.23%     0.00%  __libc_start_main+18446603487898210537
            94.23%     0.00%  _start+41
            48.44%     1.70%  random.h:1823
            48.44%     0.00%  random.h:1814
            46.74%     2.53%  random.h:185
            44.68%     0.10%  complex:589
            44.68%     0.00%  complex:597
            44.68%     0.00%  complex:654
            44.68%     0.00%  complex:664
            40.61%    13.80%  random.tcc:3330
            36.01%     0.00%  hypot+18446603487892193300
            26.81%     0.00%  random.h:151
            26.81%     0.00%  random.h:332
            25.75%    25.75%  random.h:143
             5.64%     0.00%  ??:0
             4.13%     4.13%  __hypot_finite+163
             4.13%     0.00%  __hypot_finite+18446603487892193443
      ...
      ~~~~~
      
      Note that this change removes the symbol from the source:line hist
      column. If this information is desired, users should explicitly query
      for it if needed. I.e. run this command instead:
      
      ~~~~~
        perf report --inline -s sym,srcline -g none --stdio
        ...
        # To display the perf.data header info, please use --header/--header-only options.
        #
        #
        # Total Lost Samples: 0
        #
        # Samples: 1K of event 'cycles:uppp'
        # Event count (approx.): 1381229476
        #
        # Children      Self  Symbol                                                                                                                               Source:Line
        # ........  ........  ...................................................................................................................................  ...........................................
        #
            94.30%     1.19%  [.] main                                                                                                                             main.cpp:39
            94.23%     0.00%  [.] __libc_start_main                                                                                                                __libc_start_main+18446603487898210537
            94.23%     0.00%  [.] _start                                                                                                                           _start+41
            48.44%     0.00%  [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined)  random.h:1814
            48.44%     0.00%  [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined)  random.h:1823
            46.74%     0.00%  [.] std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator() (inlined)  random.h:185
            44.68%     0.00%  [.] std::_Norm_helper<true>::_S_do_it<double> (inlined)                                                                              complex:654
            44.68%     0.00%  [.] std::__complex_abs (inlined)                                                                                                     complex:589
            44.68%     0.00%  [.] std::abs<double> (inlined)                                                                                                       complex:597
            44.68%     0.00%  [.] std::norm<double> (inlined)                                                                                                      complex:664
            39.80%    13.59%  [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >               random.tcc:3330
            36.01%     0.00%  [.] hypot                                                                                                                            hypot+18446603487892193300
            26.81%     0.00%  [.] std::__detail::__mod<unsigned long, 2147483647ul, 16807ul, 0ul> (inlined)                                                        random.h:151
            26.81%     0.00%  [.] std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>::operator() (inlined)                                 random.h:332
            25.75%     0.00%  [.] std::__detail::_Mod<unsigned long, 2147483647ul, 16807ul, 0ul, true, true>::__calc (inlined)                                     random.h:143
            25.19%    25.19%  [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >               random.h:143
             4.13%     4.13%  [.] __hypot_finite                                                                                                                   __hypot_finite+163
             4.13%     0.00%  [.] __hypot_finite                                                                                                                   __hypot_finite+18446603487892193443
      ...
      ~~~~~
      
      Compared to the old behavior, this reduces duplication in the output.
      Before we used to print the symbol name in the srcline column even
      when the sym column was explicitly requested. I.e. the output was:
      
      ~~~~~
        perf report --inline -s sym,srcline -g none --stdio
        ...
        # To display the perf.data header info, please use --header/--header-only options.
        #
        #
        # Total Lost Samples: 0
        #
        # Samples: 1K of event 'cycles:uppp'
        # Event count (approx.): 1381229476
        #
        # Children      Self  Symbol                                                                                                                               Source:Line
        # ........  ........  ...................................................................................................................................  ..................................................................................................................................
        #
            94.23%     0.00%  [.] __libc_start_main                                                                                                                __libc_start_main+18446603487898210537
            94.23%     0.00%  [.] _start                                                                                                                           _start+41
            44.58%     0.00%  [.] main                                                                                                                             main+100
            44.58%     0.00%  [.] std::_Norm_helper<true>::_S_do_it<double> (inlined)                                                                              std::_Norm_helper<true>::_S_do_it<double>+100
            44.58%     0.00%  [.] std::__complex_abs (inlined)                                                                                                     std::__complex_abs+100
            44.58%     0.00%  [.] std::abs<double> (inlined)                                                                                                       std::abs<double>+100
            44.58%     0.00%  [.] std::norm<double> (inlined)                                                                                                      std::norm<double>+100
            36.01%     0.00%  [.] hypot                                                                                                                            hypot+18446603487892193300
            25.81%     0.00%  [.] main                                                                                                                             main+41
            25.81%     0.00%  [.] std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator() (inlined)  std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+41
            25.81%     0.00%  [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined)  std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+41
            25.69%    25.69%  [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >               random.h:143
            18.39%     0.00%  [.] main                                                                                                                             main+57
            18.39%     0.00%  [.] std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator() (inlined)  std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()+57
            18.39%     0.00%  [.] std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> > (inlined)  std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >+57
            13.80%    13.80%  [.] std::generate_canonical<double, 53ul, std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >               random.tcc:3330
             4.13%     4.13%  [.] __hypot_finite                                                                                                                   __hypot_finite+163
             4.13%     0.00%  [.] __hypot_finite                                                                                                                   __hypot_finite+18446603487892193443
      ...
      ~~~~~
      Signed-off-by: default avatarMilian Wolff <milian.wolff@kdab.com>
      Reviewed-by: default avatarAndi Kleen <ak@linux.intel.com>
      Cc: David Ahern <dsahern@gmail.com>
      Cc: Jin Yao <yao.jin@linux.intel.com>
      Cc: Jiri Olsa <jolsa@kernel.org>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Link: http://lkml.kernel.org/r/20171019113836.5548-5-milian.wolff@kdab.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      1fb7d06a