[PATCH v3 05/23] perf: Add a pmu capability for "exclusive" events

[Alexander Shishkin <alexander.shishkin@linux.intel.com>]

Usually, pmus that do, for example, instruction tracing, would only ever
be able to have one event per task per cpu (or per perf_context). For such
pmus it makes sense to disallow creating conflicting events early on, so
as to provide consistent behavior for the user.

This patch adds a pmu capability that indicates such constraint on event
creation.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 include/linux/perf_event.h |  1 +
 kernel/events/core.c       | 45 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 71be27169c..b8902ebcb7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -172,6 +172,7 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_AUX_NO_SG			0x02
 #define PERF_PMU_CAP_AUX_SW_DOUBLEBUF		0x04
+#define PERF_PMU_CAP_EXCLUSIVE			0x08
 
 /**
  * struct pmu - generic performance monitoring unit
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c07768d0a0..361a45eee2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7149,6 +7149,32 @@ out:
 	return ret;
 }
 
+static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
+{
+	if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
+	    (e1->cpu == e2->cpu ||
+	     e1->cpu == -1 ||
+	     e2->cpu == -1))
+		return true;
+	return false;
+}
+
+static bool exclusive_event_ok(struct perf_event *event,
+			      struct perf_event_context *ctx)
+{
+	struct perf_event *iter_event;
+
+	if (!(event->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+		return true;
+
+	list_for_each_entry(iter_event, &ctx->event_list, event_entry) {
+		if (exclusive_event_match(iter_event, event))
+			return false;
+	}
+
+	return true;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -7300,6 +7326,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_alloc;
 	}
 
+	if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) {
+		err = -EBUSY;
+		goto err_context;
+	}
+
 	if (task) {
 		put_task_struct(task);
 		task = NULL;
@@ -7385,6 +7416,12 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (!exclusive_event_ok(event, ctx)) {
+		mutex_unlock(&ctx->mutex);
+		fput(event_file);
+		goto err_context;
+	}
+
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
@@ -7468,6 +7505,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
+	if (!exclusive_event_ok(event, ctx)) {
+		mutex_unlock(&ctx->mutex);
+		perf_unpin_context(ctx);
+		put_ctx(ctx);
+		err = -EBUSY;
+		goto err_free;
+	}
+
 	perf_install_in_context(ctx, event, cpu);
 	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
-- 
2.1.0.rc1