ANDROID: security,perf: Allow further restriction of perf_event_open

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.

https://lkml.org/lkml/2016/1/11/587

Bug: 29054680
Bug: 120445712
Change-Id: Iff5bff4fc1042e85866df9faa01bce8d04335ab8
[jeffv: Upstream doesn't want it https://lkml.org/lkml/2016/6/17/101]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

Documentation/sysctl/kernel.txt

@@ -693,7 +693,8 @@ allowed to execute.
 perf_event_paranoid:
 
 Controls use of the performance events system by unprivileged
-users (without CAP_SYS_ADMIN).  The default value is 2.
+users (without CAP_SYS_ADMIN).  The default value is 3 if
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT is set, or 2 otherwise.
 
  -1: Allow use of (almost) all events by all users
      Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
@@ -701,6 +702,7 @@ users (without CAP_SYS_ADMIN).  The default value is 2.
      Disallow raw tracepoint access by users without CAP_SYS_ADMIN
 >=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
 
 ==============================================================
 

include/linux/perf_event.h

@@ -1179,6 +1179,11 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 int perf_event_max_stack_handler(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp, 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;

kernel/events/core.c

@@ -397,8 +397,13 @@ static cpumask_var_t perf_online_mask;
  *   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 = 2;
+#endif
 
 /* Minimum for 512 kiB + 1 user control page */
 int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
@@ -10410,6 +10415,9 @@ 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;

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