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

[Alexey Budankov]

Hi Ravi,

On 10.07.2020 16:31, Ravi Bangoria wrote:
> Hi Alexey,
> 
>> Currently access to perf_events, i915_perf and other performance
>> monitoring and observability subsystems of the kernel is open only for
>> a privileged process [1] with CAP_SYS_ADMIN capability enabled in the
>> process effective set [2].
>>
>> This patch set introduces CAP_PERFMON capability designed to secure
>> system performance monitoring and observability operations so that
>> CAP_PERFMON would assist CAP_SYS_ADMIN capability in its governing role
>> for performance monitoring and observability subsystems of the kernel.
> 
> I'm seeing an issue with CAP_PERFMON when I try to record data for a
> specific target. I don't know whether this is sort of a regression or
> an expected behavior.

Thanks for reporting and root causing this case. The behavior looks like
kind of expected since currently CAP_PERFMON takes over the related part
of CAP_SYS_ADMIN credentials only. Actually Perf security docs [1] say
that access control is also subject to CAP_SYS_PTRACE credentials.

CAP_PERFMON could be used to extend and substitute ptrace_may_access()
check in perf_events subsystem to simplify user experience at least in
this specific case.

Alexei

[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html

> 
> Without setting CAP_PERFMON:
> 
> Â $ getcap ./perf
> Â $ ./perf stat -a ls
> ÂÂÂ Error:
> ÂÂÂ Access to performance monitoring and observability operations is limited.
> Â $ ./perf stat ls
> ÂÂÂ Performance counter stats for 'ls':
> ÂÂ ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 2.06 msec task-clock:uÂÂÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.418 CPUs utilized
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ context-switches:uÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ cpu-migrations:uÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> 
> With CAP_PERFMON:
> 
> Â $ getcap ./perf
> ÂÂÂ ./perf = cap_perfmon+ep
> Â $ ./perf stat -a ls
> ÂÂÂ Performance counter stats for 'system wide':
> ÂÂ ÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 142.42 msec cpu-clockÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ #ÂÂ 25.062 CPUs utilized
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 182ÂÂÂÂÂ context-switchesÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.001 M/sec
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 48ÂÂÂÂÂ cpu-migrationsÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.337 K/sec
> Â $ ./perf stat ls
> ÂÂÂ Error:
> ÂÂÂ Access to performance monitoring and observability operations is limited.
> 
> Am I missing something silly?
> 
> Analysis:
> ---------
> A bit more analysis lead me to below kernel code fs/exec.c:
> 
> Â begin_new_exec()
> Â {
> ÂÂÂÂÂÂÂ ...
> ÂÂÂÂÂÂÂ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
> ÂÂÂÂÂÂÂÂÂÂÂ !(uid_eq(current_euid(), current_uid()) &&
> ÂÂÂÂÂÂÂÂÂÂÂÂÂ gid_eq(current_egid(), current_gid())))
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ set_dumpable(current->mm, suid_dumpable);
> ÂÂÂÂÂÂÂ else
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ set_dumpable(current->mm, SUID_DUMP_USER);
> 
> ÂÂÂÂÂÂÂ ...
> ÂÂÂÂÂÂÂ commit_creds(bprm->cred);
> Â }
> 
> When I execute './perf stat ls', it's going into else condition and thus sets
> dumpable flag as SUID_DUMP_USER. Then in commit_creds():
> 
> Â int commit_creds(struct cred *new)
> Â {
> ÂÂÂÂÂÂÂ ...
> ÂÂÂÂÂÂÂ /* dumpability changes */
> ÂÂÂÂÂÂÂ if (...
> ÂÂÂÂÂÂÂÂÂÂÂ !cred_cap_issubset(old, new)) {
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ if (task->mm)
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ set_dumpable(task->mm, suid_dumpable);
> Â }
> 
> !cred_cap_issubset(old, new) fails for perf without any capability and thus
> it doesn't execute set_dumpable(). Whereas that condition passes for perf
> with CAP_PERFMON and thus it overwrites old value (SUID_DUMP_USER) with
> suid_dumpable in mm_flags. On an Ubuntu, suid_dumpable default value is
> SUID_DUMP_ROOT. On Fedora, it's SUID_DUMP_DISABLE. (/proc/sys/fs/suid_dumpable).
> 
> Now while opening an event:
> 
> Â perf_event_open()
> ÂÂÂ ptrace_may_access()
> ÂÂÂÂÂ __ptrace_may_access() {
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ ...
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ if (mm &&
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ ((get_dumpable(mm) != SUID_DUMP_USER) &&
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ !ptrace_has_cap(cred, mm->user_ns, mode)))
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ return -EPERM;
> ÂÂÂÂÂ }
> 
> This if condition passes for perf with CAP_PERFMON and thus it returns -EPERM.
> But it fails for perf without CAP_PERFMON and thus it goes ahead and returns
> success. So opening an event fails when perf has CAP_PREFMON and tries to open
> process specific event as normal user.
> 
> Workarounds:
> ------------
> Based on above analysis, I found couple of workarounds (examples are on
> Ubuntu 18.04.4 powerpc):
> 
> Workaround1:
> Setting SUID_DUMP_USER as default (in /proc/sys/fs/suid_dumpable) solves the
> issue.
> 
> Â # echo 1 > /proc/sys/fs/suid_dumpable
> Â $ getcap ./perf
> ÂÂÂ ./perf = cap_perfmon+ep
> Â $ ./perf stat ls
> ÂÂÂ Performance counter stats for 'ls':
> ÂÂ ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 1.47 msec task-clockÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.806 CPUs utilized
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ context-switchesÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ cpu-migrationsÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> 
> Workaround2:
> Using CAP_SYS_PTRACE along with CAP_PERFMON solves the issue.
> 
> Â $ cat /proc/sys/fs/suid_dumpable
> ÂÂÂ 2
> Â # setcap "cap_perfmon,cap_sys_ptrace=ep" ./perf
> Â $ ./perf stat ls
> ÂÂÂ Performance counter stats for 'ls':
> ÂÂ ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 1.41 msec task-clockÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.826 CPUs utilized
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ context-switchesÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ cpu-migrationsÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> 
> Workaround3:
> Adding CAP_PERFMON to parent of perf (/bin/bash) also solves the issue.
> 
> Â $ cat /proc/sys/fs/suid_dumpable
> ÂÂÂ 2
> Â # setcap "cap_perfmon=ep" /bin/bash
> Â # setcap "cap_perfmon=ep" ./perf
> Â $ bash
> Â $ ./perf stat ls
> ÂÂÂ Performance counter stats for 'ls':
> ÂÂ ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 1.47 msec task-clockÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.806 CPUs utilized
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ context-switchesÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂ cpu-migrationsÂÂÂÂÂÂÂÂÂÂÂ #ÂÂÂ 0.000 K/sec
> 
> - Ravi