1. 07 Nov, 2011 6 commits
    • Jiri Olsa's avatar
      tracing/latency: Fix header output for latency tracers · 7e9a49ef
      Jiri Olsa authored
      In case the the graph tracer (CONFIG_FUNCTION_GRAPH_TRACER) or even the
      function tracer (CONFIG_FUNCTION_TRACER) are not set, the latency tracers
      do not display proper latency header.
      
      The involved/fixed latency tracers are:
              wakeup_rt
              wakeup
              preemptirqsoff
              preemptoff
              irqsoff
      
      The patch adds proper handling of tracer configuration options for latency
      tracers, and displaying correct header info accordingly.
      
      * The current output (for wakeup tracer) with both graph and function
        tracers disabled is:
      
        # tracer: wakeup
        #
          <idle>-0       0d.h5    1us+:      0:120:R   + [000]     7:  0:R watchdog/0
          <idle>-0       0d.h5    3us+: ttwu_do_activate.clone.1 <-try_to_wake_up
          ...
      
      * The fixed output is:
      
        # tracer: wakeup
        #
        # wakeup latency trace v1.1.5 on 3.1.0-tip+
        # --------------------------------------------------------------------
        # latency: 55 us, #4/4, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
        #    -----------------
        #    | task: migration/0-6 (uid:0 nice:0 policy:1 rt_prio:99)
        #    -----------------
        #
        #                  _------=> CPU#
        #                 / _-----=> irqs-off
        #                | / _----=> need-resched
        #                || / _---=> hardirq/softirq
        #                ||| / _--=> preempt-depth
        #                |||| /     delay
        #  cmd     pid   ||||| time  |   caller
        #     \   /      |||||  \    |   /
             cat-1129    0d..4    1us :   1129:120:R   + [000]     6:  0:R migration/0
             cat-1129    0d..4    2us+: ttwu_do_activate.clone.1 <-try_to_wake_up
      
      * The current output (for wakeup tracer) with only function
        tracer enabled is:
      
        # tracer: wakeup
        #
             cat-1140    0d..4    1us+:   1140:120:R   + [000]     6:  0:R migration/0
             cat-1140    0d..4    2us : ttwu_do_activate.clone.1 <-try_to_wake_up
      
      * The fixed output is:
        # tracer: wakeup
        #
        # wakeup latency trace v1.1.5 on 3.1.0-tip+
        # --------------------------------------------------------------------
        # latency: 207 us, #109/109, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
        #    -----------------
        #    | task: watchdog/1-12 (uid:0 nice:0 policy:1 rt_prio:99)
        #    -----------------
        #
        #                  _------=> CPU#
        #                 / _-----=> irqs-off
        #                | / _----=> need-resched
        #                || / _---=> hardirq/softirq
        #                ||| / _--=> preempt-depth
        #                |||| /     delay
        #  cmd     pid   ||||| time  |   caller
        #     \   /      |||||  \    |   /
          <idle>-0       1d.h5    1us+:      0:120:R   + [001]    12:  0:R watchdog/1
          <idle>-0       1d.h5    3us : ttwu_do_activate.clone.1 <-try_to_wake_up
      
      Link: http://lkml.kernel.org/r/20111107150849.GE1807@m.brq.redhat.com
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@redhat.com>
      Signed-off-by: default avatarJiri Olsa <jolsa@redhat.com>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      7e9a49ef
    • Steven Rostedt's avatar
      ftrace: Fix hash record accounting bug · d4d34b98
      Steven Rostedt authored
      If the set_ftrace_filter is cleared by writing just whitespace to
      it, then the filter hash refcounts will be decremented but not
      updated. This causes two bugs:
      
      1) No functions will be enabled for tracing when they all should be
      
      2) If the users clears the set_ftrace_filter twice, it will crash ftrace:
      
      ------------[ cut here ]------------
      WARNING: at /home/rostedt/work/git/linux-trace.git/kernel/trace/ftrace.c:1384 __ftrace_hash_rec_update.part.27+0x157/0x1a7()
      Modules linked in:
      Pid: 2330, comm: bash Not tainted 3.1.0-test+ #32
      Call Trace:
       [<ffffffff81051828>] warn_slowpath_common+0x83/0x9b
       [<ffffffff8105185a>] warn_slowpath_null+0x1a/0x1c
       [<ffffffff810ba362>] __ftrace_hash_rec_update.part.27+0x157/0x1a7
       [<ffffffff810ba6e8>] ? ftrace_regex_release+0xa7/0x10f
       [<ffffffff8111bdfe>] ? kfree+0xe5/0x115
       [<ffffffff810ba51e>] ftrace_hash_move+0x2e/0x151
       [<ffffffff810ba6fb>] ftrace_regex_release+0xba/0x10f
       [<ffffffff8112e49a>] fput+0xfd/0x1c2
       [<ffffffff8112b54c>] filp_close+0x6d/0x78
       [<ffffffff8113a92d>] sys_dup3+0x197/0x1c1
       [<ffffffff8113a9a6>] sys_dup2+0x4f/0x54
       [<ffffffff8150cac2>] system_call_fastpath+0x16/0x1b
      ---[ end trace 77a3a7ee73794a02 ]---
      
      Link: http://lkml.kernel.org/r/20111101141420.GA4918@debianReported-by: default avatarRabin Vincent <rabin@rab.in>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      d4d34b98
    • Steven Rostedt's avatar
      perf: Fix parsing of __print_flags() in TP_printk() · 49908a1b
      Steven Rostedt authored
      A update is made to the sched:sched_switch event that adds some
      logic to the first parameter of the __print_flags() that shows the
      state of tasks. This change cause perf to fail parsing the flags.
      
      A simple fix is needed to have the parser be able to process ops
      within the argument.
      
      Cc: stable@vger.kernel.org
      Reported-by: default avatarAndrew Vagin <avagin@openvz.org>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      49908a1b
    • Gleb Natapov's avatar
      jump_label: jump_label_inc may return before the code is patched · c8452afb
      Gleb Natapov authored
      If cpu A calls jump_label_inc() just after atomic_add_return() is
      called by cpu B, atomic_inc_not_zero() will return value greater then
      zero and jump_label_inc() will return to a caller before jump_label_update()
      finishes its job on cpu B.
      
      Link: http://lkml.kernel.org/r/20111018175551.GH17571@redhat.com
      
      Cc: stable@vger.kernel.org
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Acked-by: default avatarJason Baron <jbaron@redhat.com>
      Signed-off-by: default avatarGleb Natapov <gleb@redhat.com>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      c8452afb
    • Steven Rostedt's avatar
      ftrace: Remove force undef config value left for testing · 8ee3c92b
      Steven Rostedt authored
      A forced undef of a config value was used for testing and was
      accidently left in during the final commit. This causes x86 to
      run slower than needed while running function tracing as well
      as causes the function graph selftest to fail when DYNMAIC_FTRACE
      is not set. This is because the code in MCOUNT expects the ftrace
      code to be processed with the config value set that happened to
      be forced not set.
      
      The forced config option was left in by:
          commit 6331c28c
          ftrace: Fix dynamic selftest failure on some archs
      
      Link: http://lkml.kernel.org/r/20111102150255.GA6973@debian
      
      Cc: stable@vger.kernel.org
      Reported-by: default avatarRabin Vincent <rabin@rab.in>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      8ee3c92b
    • Steven Rostedt's avatar
      lockdep: Show subclass in pretty print of lockdep output · e5e78d08
      Steven Rostedt authored
      The pretty print of the lockdep debug splat uses just the lock name
      to show how the locking scenario happens. But when it comes to
      nesting locks, the output becomes confusing which takes away the point
      of the pretty printing of the lock scenario.
      
      Without displaying the subclass info, we get the following output:
      
        Possible unsafe locking scenario:
      
              CPU0                    CPU1
              ----                    ----
         lock(slock-AF_INET);
                                      lock(slock-AF_INET);
                                      lock(slock-AF_INET);
         lock(slock-AF_INET);
      
        *** DEADLOCK ***
      
      The above looks more of a A->A locking bug than a A->B B->A.
      By adding the subclass to the output, we can see what really happened:
      
       other info that might help us debug this:
      
        Possible unsafe locking scenario:
      
              CPU0                    CPU1
              ----                    ----
         lock(slock-AF_INET);
                                      lock(slock-AF_INET/1);
                                      lock(slock-AF_INET);
         lock(slock-AF_INET/1);
      
        *** DEADLOCK ***
      
      This bug was discovered while tracking down a real bug caught by lockdep.
      
      Link: http://lkml.kernel.org/r/20111025202049.GB25043@hostway.ca
      
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Reported-by: default avatarThomas Gleixner <tglx@linutronix.de>
      Tested-by: default avatarSimon Kirby <sim@hostway.ca>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      e5e78d08
  2. 05 Nov, 2011 2 commits
    • Li Zefan's avatar
      tracing: update Documentation on max preds limit · 3890c136
      Li Zefan authored
      Preds is no longer stored in a fixed-size stack. The max preds now
      is 2^14, and is way more than enough, so don't bother to document it.
      
      Link: http://lkml.kernel.org/r/4EAA5E54.1080102@cn.fujitsu.comSigned-off-by: default avatarLi Zefan <lizf@cn.fujitsu.com>
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      3890c136
    • Steven Rostedt's avatar
      tracing: Add boiler plate for subsystem filter · 49aa2951
      Steven Rostedt authored
      The system filter can be used to set multiple event filters that
      exist within the system. But currently it displays the last filter
      written that does not necessarily correspond to the filters within
      the system. The system filter itself is not used to filter any events.
      The system filter is just a means to set filters of the events within
      it.
      
      Because this causes an ambiguous state when the system filter reads
      a filter string but the events within the system have different strings
      it is best to just show a boiler plate:
      
       ### global filter ###
       # Use this to set filters for multiple events.
       # Only events with the given fields will be affected.
       # If no events are modified, an error message will be displayed here.
      
      If an error occurs while writing to the system filter, the system
      filter will replace the boiler plate with the error message as it
      currently does.
      Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
      49aa2951
  3. 02 Nov, 2011 1 commit
  4. 31 Oct, 2011 1 commit
  5. 21 Oct, 2011 2 commits
  6. 20 Oct, 2011 5 commits
  7. 19 Oct, 2011 9 commits
  8. 18 Oct, 2011 10 commits
  9. 17 Oct, 2011 4 commits