perf: Add context field to perf_event

The perf_event overflow handler does not receive any caller-derived
argument, so many callers need to resort to looking up the perf_event
in their local data structure.  This is ugly and doesn't scale if a
single callback services many perf_events.

Fix by adding a context parameter to perf_event_create_kernel_counter()
(and derived hardware breakpoints APIs) and storing it in the perf_event.
The field can be accessed from the callback as event->overflow_handler_context.
All callers are updated.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1309362157-6596-2-git-send-email-avi@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 23 insertions, 10 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 81de28dc..ba8e0f4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5745,7 +5745,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		 struct task_struct *task,
 		 struct perf_event *group_leader,
 		 struct perf_event *parent_event,
-		 perf_overflow_handler_t overflow_handler)
+		 perf_overflow_handler_t overflow_handler,
+		 void *context)
 {
 	struct pmu *pmu;
 	struct perf_event *event;
@@ -5803,10 +5804,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 #endif
 	}
 
-	if (!overflow_handler && parent_event)
+	if (!overflow_handler && parent_event) {
 		overflow_handler = parent_event->overflow_handler;
+		context = parent_event->overflow_handler_context;
+	}
 
 	event->overflow_handler	= overflow_handler;
+	event->overflow_handler_context = context;
 
 	if (attr->disabled)
 		event->state = PERF_EVENT_STATE_OFF;
@@ -6073,7 +6077,8 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL);
+	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
+				 NULL, NULL);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
 		goto err_task;
@@ -6258,7 +6263,8 @@ err_fd:
 struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 				 struct task_struct *task,
-				 perf_overflow_handler_t overflow_handler)
+				 perf_overflow_handler_t overflow_handler,
+				 void *context)
 {
 	struct perf_event_context *ctx;
 	struct perf_event *event;
@@ -6268,7 +6274,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	 * Get the target context (task or percpu):
 	 */
 
-	event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler);
+	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
+				 overflow_handler, context);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
 		goto err;
@@ -6552,7 +6559,7 @@ inherit_event(struct perf_event *parent_event,
 					   parent_event->cpu,
 					   child,
 					   group_leader, parent_event,
-					   NULL);
+				           NULL, NULL);
 	if (IS_ERR(child_event))
 		return child_event;
 	get_ctx(child_ctx);
@@ -6579,6 +6586,8 @@ inherit_event(struct perf_event *parent_event,
 
 	child_event->ctx = child_ctx;
 	child_event->overflow_handler = parent_event->overflow_handler;
+	child_event->overflow_handler_context
+		= parent_event->overflow_handler_context;
 
 	/*
 	 * Precalculate sample_data sizes
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 086adf2..b7971d6 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -431,9 +431,11 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
 struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
+			    void *context,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, tsk, triggered);
+	return perf_event_create_kernel_counter(attr, -1, tsk, triggered,
+						context);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
@@ -502,7 +504,8 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  */
 struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
-			    perf_overflow_handler_t triggered)
+			    perf_overflow_handler_t triggered,
+			    void *context)
 {
 	struct perf_event * __percpu *cpu_events, **pevent, *bp;
 	long err;
@@ -515,7 +518,8 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		pevent = per_cpu_ptr(cpu_events, cpu);
-		bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered);
+		bp = perf_event_create_kernel_counter(attr, cpu, NULL,
+						      triggered, context);
 
 		*pevent = bp;
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index a6708e67..a933e3a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -375,7 +375,7 @@ static int watchdog_nmi_enable(int cpu)
 	hw_nmi_watchdog_set_attr(wd_attr);
 
 	/* Try to register using hardware perf events */
-	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
+	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
 	if (!IS_ERR(event)) {
 		printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
 		goto out_save;