perf counters: add prctl interface to disable/enable counters

Add a way for self-monitoring tasks to disable/enable counters summarily,
via a prctl:

	PR_TASK_PERF_COUNTERS_DISABLE		31
	PR_TASK_PERF_COUNTERS_ENABLE		32

Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/linux/perf_counter.h

@@ -213,6 +213,8 @@ extern u64 hw_perf_save_disable(void);
 extern void hw_perf_restore(u64 ctrl);
 extern void atomic64_counter_set(struct perf_counter *counter, u64 val64);
 extern u64 atomic64_counter_read(struct perf_counter *counter);
+extern int perf_counter_task_disable(void);
+extern int perf_counter_task_enable(void);
 
 #else
 static inline void
@@ -226,6 +228,8 @@ static inline void perf_counter_notify(struct pt_regs *regs)		{ }
 static inline void perf_counter_print_debug(void)			{ }
 static inline void hw_perf_restore(u64 ctrl)			{ }
 static inline u64 hw_perf_save_disable(void)		      { return 0; }
+static inline int perf_counter_task_disable(void)	{ return -EINVAL; }
+static inline int perf_counter_task_enable(void)	{ return -EINVAL; }
 #endif
 
 #endif /* _LINUX_PERF_COUNTER_H */

include/linux/prctl.h

@@ -85,4 +85,7 @@
 #define PR_SET_TIMERSLACK 29
 #define PR_GET_TIMERSLACK 30
 
+#define PR_TASK_PERF_COUNTERS_DISABLE		31
+#define PR_TASK_PERF_COUNTERS_ENABLE		32
+
 #endif /* _LINUX_PRCTL_H */

kernel/perf_counter.c

@@ -415,6 +415,9 @@ counter_sched_in(struct perf_counter *counter,
 		 struct perf_counter_context *ctx,
 		 int cpu)
 {
+	if (counter->active == -1)
+		return;
+
 	counter->hw_ops->hw_perf_counter_enable(counter);
 	counter->active = 1;
 	counter->oncpu = cpu;	/* TODO: put 'cpu' into cpuctx->cpu */
@@ -479,6 +482,79 @@ void perf_counter_task_sched_in(struct task_struct *task, int cpu)
 	cpuctx->task_ctx = ctx;
 }
 
+int perf_counter_task_disable(void)
+{
+	struct task_struct *curr = current;
+	struct perf_counter_context *ctx = &curr->perf_counter_ctx;
+	struct perf_counter *counter;
+	u64 perf_flags;
+	int cpu;
+
+	if (likely(!ctx->nr_counters))
+		return 0;
+
+	local_irq_disable();
+	cpu = smp_processor_id();
+
+	perf_counter_task_sched_out(curr, cpu);
+
+	spin_lock(&ctx->lock);
+
+	/*
+	 * Disable all the counters:
+	 */
+	perf_flags = hw_perf_save_disable();
+
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		WARN_ON_ONCE(counter->active == 1);
+		counter->active = -1;
+	}
+	hw_perf_restore(perf_flags);
+
+	spin_unlock(&ctx->lock);
+
+	local_irq_enable();
+
+	return 0;
+}
+
+int perf_counter_task_enable(void)
+{
+	struct task_struct *curr = current;
+	struct perf_counter_context *ctx = &curr->perf_counter_ctx;
+	struct perf_counter *counter;
+	u64 perf_flags;
+	int cpu;
+
+	if (likely(!ctx->nr_counters))
+		return 0;
+
+	local_irq_disable();
+	cpu = smp_processor_id();
+
+	spin_lock(&ctx->lock);
+
+	/*
+	 * Disable all the counters:
+	 */
+	perf_flags = hw_perf_save_disable();
+
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		if (counter->active != -1)
+			continue;
+		counter->active = 0;
+	}
+	hw_perf_restore(perf_flags);
+
+	spin_unlock(&ctx->lock);
+
+	perf_counter_task_sched_in(curr, cpu);
+
+	local_irq_enable();
+
+	return 0;
+}
+
 void perf_counter_task_tick(struct task_struct *curr, int cpu)
 {
 	struct perf_counter_context *ctx = &curr->perf_counter_ctx;
@@ -951,13 +1027,9 @@ perf_counter_alloc(struct perf_counter_hw_event *hw_event,
  * @cpu:		target cpu
  * @group_fd:		group leader counter fd
  */
-asmlinkage int sys_perf_counter_open(
+asmlinkage int
-
+sys_perf_counter_open(struct perf_counter_hw_event *hw_event_uptr __user,
-	struct perf_counter_hw_event	*hw_event_uptr		__user,
+		      pid_t pid, int cpu, int group_fd)
-	pid_t				pid,
-	int				cpu,
-	int				group_fd)
-
 {
 	struct perf_counter *counter, *group_leader;
 	struct perf_counter_hw_event hw_event;

kernel/sys.c

@@ -14,6 +14,7 @@
 #include <linux/prctl.h>
 #include <linux/highuid.h>
 #include <linux/fs.h>
+#include <linux/perf_counter.h>
 #include <linux/resource.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
@@ -1716,6 +1717,12 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 		case PR_SET_TSC:
 			error = SET_TSC_CTL(arg2);
 			break;
+		case PR_TASK_PERF_COUNTERS_DISABLE:
+			error = perf_counter_task_disable();
+			break;
+		case PR_TASK_PERF_COUNTERS_ENABLE:
+			error = perf_counter_task_enable();
+			break;
 		case PR_GET_TIMERSLACK:
 			error = current->timer_slack_ns;
 			break;