[RFC PATCH 1/2] perf: Add the flag sample_disable not to output data on samples

[Kaixu Xia]

In some scenarios we don't want to output trace data when sampling
to reduce overhead. This patch adds the flag sample_disable to
implement this function. By setting this flag and integrating with
ebpf, we can control the data output process and get the samples we
are most interested in.

Signed-off-by: Kaixu Xia <xiaka...@huawei.com>
---
 include/linux/bpf.h        | 1 +
 include/linux/perf_event.h | 2 ++
 kernel/bpf/arraymap.c      | 5 +++++
 kernel/events/core.c       | 3 +++
 4 files changed, 11 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f57d7fe..25e073d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -39,6 +39,7 @@ struct bpf_map {
        u32 max_entries;
        const struct bpf_map_ops *ops;
        struct work_struct work;
+       atomic_t perf_sample_disable;
 };
 
 struct bpf_map_type_list {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 092a0e8..0606d1d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -483,6 +483,8 @@ struct perf_event {
        perf_overflow_handler_t         overflow_handler;
        void                            *overflow_handler_context;
 
+       atomic_t                        *sample_disable;
+
 #ifdef CONFIG_EVENT_TRACING
        struct trace_event_call         *tp_event;
        struct event_filter             *filter;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 29ace10..4ae82c9 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -51,6 +51,9 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
        array->elem_size = elem_size;
 
+       if (attr->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+               atomic_set(&array->map.perf_sample_disable, 1);
+
        return &array->map;
 }
 
@@ -298,6 +301,8 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map 
*map, int fd)
                perf_event_release_kernel(event);
                return ERR_PTR(-EINVAL);
        }
+
+       event->sample_disable = &map->perf_sample_disable;
        return event;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b11756f..f6ef45c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6337,6 +6337,9 @@ static int __perf_event_overflow(struct perf_event *event,
                irq_work_queue(&event->pending);
        }
 
+       if ((event->sample_disable) && atomic_read(event->sample_disable))
+               return ret;
+
        if (event->overflow_handler)
                event->overflow_handler(event, data, regs);
        else
-- 
1.8.3.4

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html