perf: Allow normal events to output AUX data

In some cases, ordinary (non-AUX) events can generate data for AUX events.
For example, PEBS events can come out as records in the Intel PT stream
instead of their usual DS records, if configured to do so.

One requirement for such events is to consistently schedule together, to
ensure that the data from the "AUX output" events isn't lost while their
corresponding AUX event is not scheduled. We use grouping to provide this
guarantee: an "AUX output" event can be added to a group where an AUX event
is a group leader, and provided that the former supports writing to the
latter.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: kan.liang@linux.intel.com
Link: https://lkml.kernel.org/r/20190806084606.4021-2-alexander.shishkin@linux.intel.com

1 files changed, 93 insertions, 0 deletions

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(),