Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1385501

Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth via sysctl

From Alexei Starovoitov <alexei.starovoitov@gmail.com>
Newsgroups linux.kernel
Subject Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth via sysctl
Date 2016-04-23 00:20 +0200
Message-ID <rqRAD-Pr-47@gated-at.bofh.it> (permalink)
References <rq96y-799-13@gated-at.bofh.it> <rq9pU-7AD-15@gated-at.bofh.it> <rqQlb-88k-3@gated-at.bofh.it> <rqRqX-Lm-23@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Fri, Apr 22, 2016 at 04:05:31PM -0600, David Ahern wrote:
> On 4/22/16 2:52 PM, Arnaldo Carvalho de Melo wrote:
> >Em Wed, Apr 20, 2016 at 04:04:12PM -0700, Alexei Starovoitov escreveu:
> >>On Wed, Apr 20, 2016 at 07:47:30PM -0300, Arnaldo Carvalho de Melo wrote:
> >
> >>Nice. I like it. That's a great approach to hard problem.
> >>Java guys will be happy too.
> >>Please also adjust two places in kernel/bpf/stackmap.c
> >
> >>>+	{
> >>>+		.procname	= "perf_event_max_stack",
> >>>+		.data		= NULL, /* filled in by handler */
> >>>+		.maxlen		= sizeof(sysctl_perf_event_max_stack),
> >>>+		.mode		= 0644,
> >>>+		.proc_handler	= perf_event_max_stack_handler,
> >>>+		.extra1		= &zero,
> >
> >>zero seems to be the wrong minimum. I think it should be at least 2 to
> >>to fit user/kernel tags ?  Probably needs to define max as well.
> >
> >So, if someone asks for zero, it will not copy anything, but then, this
> >would be what the user had asked for :-)
> >
> >Ditto for the max, if someone asks for too big a callchain, then when
> >allocating it it will fail and no callchain will be produced, that or it
> >will be able to allocate but will take too long copying that many
> >addresses, and we would be prevented from doing so by some other
> >protection, iirc there is perf_cpu_time_max_percent, and then buffer
> >space will run out.
> >
> >So I think that leaving it as is is enough, no?
> >
> >Can I keep your Acked-by? David, can I keep yours?
> 
> Yes
> 
> 
> >diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
> >index 343c22f5e867..6fe77349fa9d 100644
> >--- a/kernel/events/callchain.c
> >+++ b/kernel/events/callchain.c
> >@@ -18,6 +18,14 @@ struct callchain_cpus_entries {
> >  	struct perf_callchain_entry	*cpu_entries[0];
> >  };
> >
> >+int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
> >+
> >+static size_t perf_callchain_entry__sizeof(void)
> >+{
> >+	return sizeof(struct perf_callchain_entry) +
> >+	       sizeof(__u64) * sysctl_perf_event_max_stack;
> >+}
> >+
> 
> To Alexei's comment, a max_stack of 0 still has a non-zero alloc size so
> that should be ok.
> 
> 
> >  static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
> >  static atomic_t nr_callchain_events;
> >  static DEFINE_MUTEX(callchain_mutex);
> >@@ -73,7 +81,7 @@ static int alloc_callchain_buffers(void)
> >  	if (!entries)
> >  		return -ENOMEM;
> >
> >-	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
> >+	size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;
> >
> >  	for_each_possible_cpu(cpu) {
> >  		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,

right... and looking into it further, realized that the patch is broken,
since get_callchain_entry() is doing:
  return &entries->cpu_entries[cpu][*rctx];
whereas it should be dynamic offset based on sysctl_perf_event_max_stack*8
So definitely needs another respin.

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH/RFC] perf core: Allow setting up max frame stack depth via  sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-21 00:50 +0200
  Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-21 01:10 +0200
    [PATCH/RFC v2] perf core: Allow setting up max frame stack depth via  sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-22 23:00 +0200
      Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-22 23:40 +0200
      Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl David Ahern <dsahern@gmail.com> - 2016-04-23 00:10 +0200
        Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-23 00:20 +0200
          Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-25 18:20 +0200
            Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-25 18:30 +0200
              Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-25 21:30 +0200
                Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-25 22:10 +0200
                Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-25 22:20 +0200
                Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-26 00:10 +0200
                Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-26 01:50 +0200
                Re: [PATCH/RFC v2] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-26 02:10 +0200
                [PATCH/RFC v3] perf core: Allow setting up max frame stack depth via  sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-26 02:30 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-26 02:50 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Brendan Gregg <brendan.d.gregg@gmail.com> - 2016-04-26 03:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-26 18:40 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl David Ahern <dsahern@gmail.com> - 2016-04-26 18:50 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-27 15:30 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Brendan Gregg <brendan.d.gregg@gmail.com> - 2016-04-26 22:10 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-26 23:10 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Peter Zijlstra <peterz@infradead.org> - 2016-04-27 00:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-27 15:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Brendan Gregg <brendan.d.gregg@gmail.com> - 2016-04-27 00:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Peter Zijlstra <peterz@infradead.org> - 2016-04-27 00:20 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-27 15:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-04-26 02:50 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Frederic Weisbecker <fweisbec@gmail.com> - 2016-04-27 00:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-27 15:00 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl Frederic Weisbecker <fweisbec@gmail.com> - 2016-04-27 18:10 +0200
                Re: [PATCH/RFC v3] perf core: Allow setting up max frame stack depth  via sysctl David Ahern <dsahern@gmail.com> - 2016-04-27 18:30 +0200
                [tip:perf/core] perf core: Allow setting up max frame stack depth  via sysctl tip-bot for Arnaldo Carvalho de Melo <tipbot@zytor.com> - 2016-04-27 17:50 +0200
  Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth via  sysctl David Ahern <dsahern@gmail.com> - 2016-04-21 01:20 +0200
    Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-21 02:20 +0200
  Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth  via sysctl Peter Zijlstra <peterz@infradead.org> - 2016-04-21 13:00 +0200
    Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-21 17:20 +0200
      Re: [PATCH/RFC] perf core: Allow setting up max frame stack depth  via sysctl Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-04-21 17:50 +0200

csiph-web