perf_counter: sysctl for system wide perf counters
Impact: add sysctl for paranoid/relaxed perfcounters policy
Allow the use of system wide perf counters to everybody, but provide
a sysctl to disable it for the paranoid security minded.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090409085524.514046352@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 76376ec..7efb7eb 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -42,6 +42,8 @@
static atomic_t nr_munmap_tracking __read_mostly;
static atomic_t nr_comm_tracking __read_mostly;
+int sysctl_perf_counter_priv __read_mostly; /* do we need to be privileged */
+
/*
* Mutex for (sysadmin-configurable) counter reservations:
*/
@@ -1132,7 +1134,7 @@
*/
if (cpu != -1) {
/* Must be root to operate on a CPU counter: */
- if (!capable(CAP_SYS_ADMIN))
+ if (sysctl_perf_counter_priv && !capable(CAP_SYS_ADMIN))
return ERR_PTR(-EACCES);
if (cpu < 0 || cpu > num_possible_cpus())