linux-kernel - Re: [PATCH v8 00/12] Introduce CAP_PERFMON to secure system performance monitoring and observability

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 7 Apr 2020 14:23:40 -0300
From:   Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
To:     Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
Cc:     Alexey Budankov <alexey.budankov@...ux.intel.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Alexei Starovoitov <ast@...nel.org>,
        Ingo Molnar <mingo@...hat.com>,
        James Morris <jmorris@...ei.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Serge Hallyn <serge@...lyn.com>, Jiri Olsa <jolsa@...hat.com>,
        Song Liu <songliubraving@...com>,
        Andi Kleen <ak@...ux.intel.com>,
        Stephane Eranian <eranian@...gle.com>,
        Igor Lubashev <ilubashe@...mai.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        "linux-security-module@...r.kernel.org" 
        <linux-security-module@...r.kernel.org>,
        "selinux@...r.kernel.org" <selinux@...r.kernel.org>,
        "intel-gfx@...ts.freedesktop.org" <intel-gfx@...ts.freedesktop.org>,
        "linux-doc@...r.kernel.org" <linux-doc@...r.kernel.org>,
        linux-man@...r.kernel.org
Subject: Re: [PATCH v8 00/12] Introduce CAP_PERFMON to secure system
 performance monitoring and observability

Em Tue, Apr 07, 2020 at 01:56:43PM -0300, Arnaldo Carvalho de Melo escreveu:
> 
> But then, even with that attr.exclude_kernel set to 1 we _still_ get
> kernel samples, which looks like another bug, now trying with strace,
> which leads us to another rabbit hole:
> 
> [perf@...e ~]$ strace -e perf_event_open -o /tmp/out.put perf top --stdio
> Error:
> You may not have permission to collect system-wide stats.
> 
> Consider tweaking /proc/sys/kernel/perf_event_paranoid,
> which controls use of the performance events system by
> unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).
> 
> The current value is 2:
> 
>   -1: Allow use of (almost) all events by all users
>       Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
> >= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN
>       Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN
> >= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN
> >= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN
> 
> To make this setting permanent, edit /etc/sysctl.conf too, e.g.:
> 
> 	kernel.perf_event_paranoid = -1
> 
> [perf@...e ~]$
> 
> If I remove that strace -e ... from the front, 'perf top' is back
> working as a non-cap_sys_admin user, just with cap_perfmon.
> 

So I couldn't figure it out so far why is that exclude_kernel is being
set to 1, as perf-top when no event is passed defaults to this to find
out what to use as a default event:

  perf_evlist__add_default(top.evlist)
     perf_evsel__new_cycles(true);
	struct perf_event_attr attr = {
                .type   = PERF_TYPE_HARDWARE,
                .config = PERF_COUNT_HW_CPU_CYCLES,
                .exclude_kernel = !perf_event_can_profile_kernel(),
        };

			perf_event_paranoid_check(1);
			        return perf_cap__capable(CAP_SYS_ADMIN) ||
				       perf_cap__capable(CAP_PERFMON) ||
				       perf_event_paranoid() <= max_level;


And then that second condition should hold true, it returns true, and
then .exclude_kernel should be set to !true -> zero.o

Now the wallclock says I need to stop being a programmer and turn into a
daycare provider for Pedro, cya!

- Arnaldo