[PATCH v3 1/3] bpf: Add new bpf map type to store the pointer to struct perf_event

From: Kaixu Xia <xiakaixu@huawei.com>
To: <ast@plumgrid.com>, <davem@davemloft.net>, <acme@kernel.org>,
	<mingo@redhat.com>, <a.p.zijlstra@chello.nl>,
	<masami.hiramatsu.pt@hitachi.com>, <jolsa@kernel.org>
Cc: <xiakaixu@huawei.com>, <wangnan0@huawei.com>,
	<linux-kernel@vger.kernel.org>, <pi3orama@163.com>,
	<hekuang@huawei.com>
Subject: [PATCH v3 1/3] bpf: Add new bpf map type to store the pointer to struct perf_event
Date: Thu, 23 Jul 2015 09:42:40 +0000	[thread overview]
Message-ID: <1437644562-84431-2-git-send-email-xiakaixu@huawei.com> (raw)
In-Reply-To: <1437644562-84431-1-git-send-email-xiakaixu@huawei.com>

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 <xiakaixu@huawei.com>
---
 include/linux/bpf.h        |   2 +
 include/linux/perf_event.h |   2 +
 include/uapi/linux/bpf.h   |   1 +
 kernel/bpf/arraymap.c      | 113 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c      |  15 ++++++
 kernel/events/core.c       |  23 +++++++++
 6 files changed, 156 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4383476..9cf74c0 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;
 
@@ -143,6 +144,7 @@ struct bpf_array {
 	union {
 		char value[0] __aligned(8);
 		struct bpf_prog *prog[0] __aligned(8);
+		struct perf_event *events[0] __aligned(8);
 	};
 };
 #define MAX_TAIL_CALL_CNT 32
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2027809..2ea4067 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -641,6 +641,7 @@ 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 void perf_event_print_debug(void);
 extern void perf_pmu_disable(struct pmu *pmu);
 extern void perf_pmu_enable(struct pmu *pmu);
@@ -979,6 +980,7 @@ 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 struct perf_event *perf_event_get(unsigned int fd)		{ return NULL; }
 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; }
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 cb31229..e97efbc 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -255,3 +255,116 @@ static int __init register_prog_array_map(void)
 	return 0;
 }
 late_initcall(register_prog_array_map);
+
+static struct bpf_map *perf_event_array_map_alloc(union bpf_attr *attr)
+{
+	/* only the pointer to struct perf_event can be stored in
+	 * perf_event_array map
+	 */
+	if (attr->value_size != sizeof(u32))
+		return ERR_PTR(-EINVAL);
+
+	return array_map_alloc(attr);
+}
+
+static void perf_event_array_map_free(struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct perf_event *event;
+	int i;
+
+	synchronize_rcu();
+
+	/* release the struct perf_event in perf_event_array_map */
+	for(i = 0; i < array->map.max_entries; i++) {
+		event = array->events[i];
+		if (event)
+			perf_event_release_kernel(event);
+	}
+	kvfree(array);
+}
+
+static int perf_event_array_map_get_next_key(struct bpf_map *map, void *key,
+					     void *next_key)
+{
+	return -EINVAL;
+}
+
+static void *perf_event_array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+static struct perf_event *convert_map_with_perf_event(void *value)
+{
+	struct perf_event *event;
+	u32 fd;
+
+	fd = *(u32 *)value;
+
+	event = perf_event_get(fd);
+	if (IS_ERR(event))
+		return NULL;
+
+	/* limit the event type to PERF_TYPE_RAW
+	 * and PERF_TYPE_HARDWARE.
+	 */
+	if (event->attr.type != PERF_TYPE_RAW &&
+	    event->attr.type != PERF_TYPE_HARDWARE)
+		return NULL;
+
+	return event;
+}
+
+/* only called from syscall */
+static int perf_event_array_map_update_elem(struct bpf_map *map, void *key,
+					    void *value, u64 map_flags)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct perf_event *event;
+	u32 index = *(u32 *)key;
+
+	if (map_flags != BPF_ANY)
+		return -EINVAL;
+
+	if (index >= array->map.max_entries)
+		return -E2BIG;
+
+	/* check if the value is already stored */
+	if (array->events[index])
+		return -EINVAL;
+
+	/* convert the fd to the pointer to struct perf_event */
+	event = convert_map_with_perf_event(value);
+	if (!event)
+		return -EBADF;
+
+	xchg(array->events + index, event);
+	return 0;
+}
+
+static int perf_event_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+static const struct bpf_map_ops perf_event_array_ops = {
+	.map_alloc = perf_event_array_map_alloc,
+	.map_free = perf_event_array_map_free,
+	.map_get_next_key = perf_event_array_map_get_next_key,
+	.map_lookup_elem = perf_event_array_map_lookup_elem,
+	.map_update_elem = perf_event_array_map_update_elem,
+	.map_delete_elem = perf_event_array_map_delete_elem,
+};
+
+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/bpf/verifier.c b/kernel/bpf/verifier.c
index 039d866..c70f7e7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -924,6 +924,21 @@ static int check_call(struct verifier_env *env, int func_id)
 		 */
 		return -EINVAL;
 
+	if (map && map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
+	    func_id != BPF_FUNC_perf_event_read)
+		/* perf_event_array map type needs extra care:
+		 * only allow to pass it into bpf_perf_event_read() for now.
+		 * bpf_map_update/delete_elem() must only be done via syscall
+		 */
+		return -EINVAL;
+
+	if (func_id == BPF_FUNC_perf_event_read &&
+	    map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+		/* don't allow any other map type to be passed into
+		 * bpf_perf_event_read()
+		 */
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3dae34..08cb467 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8574,6 +8574,29 @@ 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)
+{
+	struct perf_event *event;
+	struct fd f;
+
+	f = fdget(fd);
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	if (f.file->f_op != &perf_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	event = f.file->private_data;
+
+	atomic_long_inc(&event->refcount);
+	fdput(f);
+
+	return event;
+}
+
 /*
  * inherit a event from parent task to child task:
  */
-- 
1.8.3.4

