When kernel.perf_event_open is set to 3 (or greater), disallow all
access to performance events by users without CAP_SYS_ADMIN.
Add a Kconfig symbol CONFIG_SECURITY_PERF_EVENTS_RESTRICT that
makes this value the default.

This is based on a similar feature in grsecurity
(CONFIG_GRKERNSEC_PERF_HARDEN).  This version doesn't include making
the variable read-only.  It also allows enabling further restriction
at run-time regardless of whether the default is changed.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
I made a similar change to Debian's kernel packages in August,
including the more restrictive default, and no-one has complained yet.

Ben.

 Documentation/sysctl/kernel.txt | 4 +++-
 include/linux/perf_event.h      | 5 +++++
 kernel/events/core.c            | 8 ++++++++
 security/Kconfig                | 9 +++++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 88a2c8e..76e2ca8 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -629,12 +629,14 @@ allowed to execute.
 perf_event_paranoid:
 
 Controls use of the performance events system by unprivileged
-users (without CAP_SYS_ADMIN).  The default value is 1.
+users (without CAP_SYS_ADMIN).  The default value is 3 if
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT is set, or 1 otherwise.
 
  -1: Allow use of (almost) all events by all users
 >=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK
 >=1: Disallow CPU event access by users without CAP_SYS_ADMIN
 >=2: Disallow kernel profiling by users without CAP_SYS_ADMIN
+>=3: Disallow all event access by users without CAP_SYS_ADMIN
 
 ==============================================================
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a4..aa72940 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -989,6 +989,11 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 		loff_t *ppos);
 
 
+static inline bool perf_paranoid_any(void)
+{
+	return sysctl_perf_event_paranoid > 2;
+}
+
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
 	return sysctl_perf_event_paranoid > -1;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfc227c..85bc810 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -175,8 +175,13 @@ static struct srcu_struct pmus_srcu;
  *   0 - disallow raw tracepoint access for unpriv
  *   1 - disallow cpu events for unpriv
  *   2 - disallow kernel profiling for unpriv
+ *   3 - disallow all unpriv perf event use
  */
+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT
+int sysctl_perf_event_paranoid __read_mostly = 3;
+#else
 int sysctl_perf_event_paranoid __read_mostly = 1;
+#endif
 
 /* Minimum for 512 kiB + 1 user control page */
 int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
@@ -8265,6 +8270,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
+	if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
diff --git a/security/Kconfig b/security/Kconfig
index e452378..30a2603 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -18,6 +18,15 @@ config SECURITY_DMESG_RESTRICT
 
 	  If you are unsure how to answer this question, answer N.
 
+config SECURITY_PERF_EVENTS_RESTRICT
+	bool "Restrict unprivileged use of performance events"
+	depends on PERF_EVENTS
+	help
+	  If you say Y here, the kernel.perf_event_paranoid sysctl
+	  will be set to 3 by default, and no unprivileged use of the
+	  perf_event_open syscall will be permitted unless it is
+	  changed.
+
 config SECURITY
 	bool "Enable different security models"
 	depends on SYSFS