3 files changed, 109 insertions, 1 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e8ad3c590a23..61448c19a132 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -246,6 +246,7 @@ struct perf_event;
 #define PERF_PMU_CAP_ITRACE                     0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS         0x40
 #define PERF_PMU_CAP_NO_EXCLUDE                 0x80
+#define PERF_PMU_CAP_AUX_OUTPUT                 0x100
 
 /**
  * struct pmu - generic performance monitoring unit
@@ -447,6 +448,16 @@ struct pmu {
                                         /* optional */
 
         /*
+         * Check if event can be used for aux_output purposes for
+         * events of this PMU.
+         *
+         * Runs from perf_event_open(). Should return 0 for "no match"
+         * or non-zero for "match".
+         */
+        int (*aux_output_match)         (struct perf_event *event);
+                                        /* optional */
+
+        /*
          * Filter events for PMU-specific reasons.
          */
         int (*filter_match)             (struct perf_event *event); /* optional */
@@ -681,6 +692,9 @@ struct perf_event {
         struct perf_addr_filter_range   *addr_filter_ranges;
         unsigned long                   addr_filters_gen;
 
+        /* for aux_output events */
+        struct perf_event               *aux_event;
+
         void (*destroy)(struct perf_event *);
         struct rcu_head                 rcu_head;
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7198ddd0c6b1..bb7b271397a6 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -374,7 +374,8 @@ struct perf_event_attr {
                                 namespaces     :  1, /* include namespaces data */
                                 ksymbol        :  1, /* include ksymbol events */
                                 bpf_event      :  1, /* include bpf events */
-                                __reserved_1   : 33;
+                                aux_output     :  1, /* generate AUX records instead of events */
+                                __reserved_1   : 32;
 
         union {
                 __u32           wakeup_events;    /* wakeup every n events */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0463c1151bae..2aad959e6def 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1887,6 +1887,89 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
         ctx->generation++;
 }
 
+static int
+perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
+{
+        if (!has_aux(aux_event))
+                return 0;
+
+        if (!event->pmu->aux_output_match)
+                return 0;
+
+        return event->pmu->aux_output_match(aux_event);
+}
+
+static void put_event(struct perf_event *event);
+static void event_sched_out(struct perf_event *event,
+                            struct perf_cpu_context *cpuctx,
+                            struct perf_event_context *ctx);
+
+static void perf_put_aux_event(struct perf_event *event)
+{
+        struct perf_event_context *ctx = event->ctx;
+        struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+        struct perf_event *iter;
+
+        /*
+         * If event uses aux_event tear down the link
+         */
+        if (event->aux_event) {
+                iter = event->aux_event;
+                event->aux_event = NULL;
+                put_event(iter);
+                return;
+        }
+
+        /*
+         * If the event is an aux_event, tear down all links to
+         * it from other events.
+         */
+        for_each_sibling_event(iter, event->group_leader) {
+                if (iter->aux_event != event)
+                        continue;
+
+                iter->aux_event = NULL;
+                put_event(event);
+
+                /*
+                 * If it's ACTIVE, schedule it out and put it into ERROR
+                 * state so that we don't try to schedule it again. Note
+                 * that perf_event_enable() will clear the ERROR status.
+                 */
+                event_sched_out(iter, cpuctx, ctx);
+                perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+        }
+}
+
+static int perf_get_aux_event(struct perf_event *event,
+                              struct perf_event *group_leader)
+{
+        /*
+         * Our group leader must be an aux event if we want to be
+         * an aux_output. This way, the aux event will precede its
+         * aux_output events in the group, and therefore will always
+         * schedule first.
+         */
+        if (!group_leader)
+                return 0;
+
+        if (!perf_aux_output_match(event, group_leader))
+                return 0;
+
+        if (!atomic_long_inc_not_zero(&group_leader->refcount))
+                return 0;
+
+        /*
+         * Link aux_outputs to their aux event; this is undone in
+         * perf_group_detach() by perf_put_aux_event(). When the
+         * group in torn down, the aux_output events loose their
+         * link to the aux_event and can't schedule any more.
+         */
+        event->aux_event = group_leader;
+
+        return 1;
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
         struct perf_event *sibling, *tmp;
@@ -1902,6 +1985,8 @@ static void perf_group_detach(struct perf_event *event)
 
         event->attach_state &= ~PERF_ATTACH_GROUP;
 
+        perf_put_aux_event(event);
+
         /*
          * If this is a sibling, remove it from its group.
          */
@@ -10426,6 +10511,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
                 goto err_ns;
         }
 
+        if (event->attr.aux_output &&
+            !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+                err = -EOPNOTSUPP;
+                goto err_pmu;
+        }
+
         err = exclusive_event_init(event);
         if (err)
                 goto err_pmu;
@@ -11082,6 +11173,8 @@ SYSCALL_DEFINE5(perf_event_open,
                 }
         }
 
+        if (event->attr.aux_output && !perf_get_aux_event(event, group_leader))
+                goto err_locked;
 
         /*
          * Must be under the same ctx::mutex as perf_install_in_context(),