Introduce a new bpf map type 'BPF_MAP_TYPE_PERF_EVENT_ARRAY'.
This map only stores the pointer to struct perf_event. The
user space event FDs from perf_event_open() syscall are converted
to the pointer to struct perf_event and stored in map.
Signed-off-by: Kaixu Xia <xiaka...@huawei.com>
---
include/linux/bpf.h | 1 +
include/linux/perf_event.h | 8 +++++++
include/uapi/linux/bpf.h | 1 +
kernel/bpf/arraymap.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++
kernel/events/core.c | 25 ++++++++++++++++++++
5 files changed, 92 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a8ce262..d0b394a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -10,6 +10,7 @@
#include <uapi/linux/bpf.h>
#include <linux/workqueue.h>
#include <linux/file.h>
+#include <linux/perf_event.h>
struct bpf_map;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2027809..81fc99e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -641,6 +641,8 @@ extern int perf_event_init_task(struct task_struct *child);
extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
+extern struct perf_event *perf_event_get(unsigned int fd);
+extern struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
@@ -979,6 +981,11 @@ static inline int perf_event_init_task(struct task_struct
*child) { return 0; }
static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
+static inline struct perf_event *perf_event_get(unsigned int fd) {
return ERR_PTR(-EINVAL); }
+static inline struct perf_event_attr *perf_event_attrs(struct perf_event
*event)
+{
+ return ERR_PTR(-EINVAL);
+}
static inline void perf_event_print_debug(void)
{ }
static inline int perf_event_task_disable(void)
{ return -EINVAL; }
static inline int perf_event_task_enable(void) {
return -EINVAL; }
@@ -1011,6 +1018,7 @@ static inline void perf_event_enable(struct perf_event
*event) { }
static inline void perf_event_disable(struct perf_event *event)
{ }
static inline int __perf_event_disable(void *info) {
return -1; }
static inline void perf_event_task_tick(void) { }
+static inline int perf_event_release_kernel(struct perf_event *event) {
return 0; }
#endif
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 29ef6f9..69a1f6b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -114,6 +114,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH,
BPF_MAP_TYPE_ARRAY,
BPF_MAP_TYPE_PROG_ARRAY,
+ BPF_MAP_TYPE_PERF_EVENT_ARRAY,
};
enum bpf_prog_type {
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 45df657..b1e98ff 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -273,3 +273,60 @@ static int __init register_prog_array_map(void)
return 0;
}
late_initcall(register_prog_array_map);
+
+static void perf_event_array_map_free(struct bpf_map *map)
+{
+ bpf_fd_array_map_clear(map);
+ fd_array_map_free(map);
+}
+
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+ struct perf_event *event;
+ struct perf_event_attr *attr;
+
+ event = perf_event_get(fd);
+ if (IS_ERR(event))
+ return event;
+
+ attr = perf_event_attrs(event);
+ if (IS_ERR(attr))
+ return attr;
+
+ if (attr->type != PERF_TYPE_RAW &&
+ attr->type != PERF_TYPE_HARDWARE) {
+ perf_event_release_kernel(event);
+ return ERR_PTR(-EINVAL);
+ }
+ return event;
+}
+
+static void perf_event_fd_array_put_ptr(void *ptr)
+{
+ struct perf_event *event = ptr;
+
+ perf_event_release_kernel(event);
+}
+
+static const struct bpf_map_ops perf_event_array_ops = {
+ .map_alloc = fd_array_map_alloc,
+ .map_free = perf_event_array_map_free,
+ .map_get_next_key = array_map_get_next_key,
+ .map_lookup_elem = fd_array_map_lookup_elem,
+ .map_update_elem = fd_array_map_update_elem,
+ .map_delete_elem = fd_array_map_delete_elem,
+ .map_fd_get_ptr = perf_event_fd_array_get_ptr,
+ .map_fd_put_ptr = perf_event_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list perf_event_array_type __read_mostly = {
+ .ops = &perf_event_array_ops,
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+};
+
+static int __init register_perf_event_array_map(void)
+{
+ bpf_register_map_type(&perf_event_array_type);
+ return 0;
+}
+late_initcall(register_perf_event_array_map);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3dae34..6251b53 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8574,6 +8574,31 @@ void perf_event_delayed_put(struct task_struct *task)
WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
}
+struct perf_event *perf_event_get(unsigned int fd)
+{
+ int err;
+ struct fd f;
+ struct perf_event *event;
+
+ err = perf_fget_light(fd, &f);
+ if (err)
+ return ERR_PTR(err);
+
+ event = f.file->private_data;
+ atomic_long_inc(&event->refcount);
+ fdput(f);
+
+ return event;
+}
+
+struct perf_event_attr *perf_event_attrs(struct perf_event *event)
+{
+ if (!event)
+ return ERR_PTR(-EINVAL);
+
+ return &event->attr;
+}
+
/*
* inherit a event from parent task to child task:
*/
--
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
