bpf/tracing: allow user space to query prog array on the same tp

Commit e87c6bc3 ("bpf: permit multiple bpf attachments
for a single perf event") added support to attach multiple
bpf programs to a single perf event.
Although this provides flexibility, users may want to know
what other bpf programs attached to the same tp interface.
Besides getting visibility for the underlying bpf system,
such information may also help consolidate multiple bpf programs,
understand potential performance issues due to a large array,
and debug (e.g., one bpf program which overwrites return code
may impact subsequent program results).

Commit 2541517c ("tracing, perf: Implement BPF programs
attached to kprobes") utilized the existing perf ioctl
interface and added the command PERF_EVENT_IOC_SET_BPF
to attach a bpf program to a tracepoint. This patch adds a new
ioctl command, given a perf event fd, to query the bpf program
array attached to the same perf tracepoint event.

The new uapi ioctl command:
  PERF_EVENT_IOC_QUERY_BPF

The new uapi/linux/perf_event.h structure:
  struct perf_event_query_bpf {
       __u32	ids_len;
       __u32	prog_cnt;
       __u32	ids[0];
  };

User space provides buffer "ids" for kernel to copy to.
When returning from the kernel, the number of available
programs in the array is set in "prog_cnt".

The usage:
  struct perf_event_query_bpf *query =
    malloc(sizeof(*query) + sizeof(u32) * ids_len);
  query.ids_len = ids_len;
  err = ioctl(pmu_efd, PERF_EVENT_IOC_QUERY_BPF, query);
  if (err == 0) {
    /* query.prog_cnt is the number of available progs,
     * number of progs in ids: (ids_len == 0) ? 0 : query.prog_cnt
     */
  } else if (errno == ENOSPC) {
    /* query.ids_len number of progs copied,
     * query.prog_cnt is the number of available progs
     */
  } else {
      /* other errors */
  }
Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -254,6 +254,7 @@ typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
+int bpf_event_query_prog_array(struct perf_event *event, void __user *info);
 
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
@@ -285,6 +286,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 
 void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
 				struct bpf_prog *old_prog);
+int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+			     __u32 __user *prog_ids, u32 request_cnt,
+			     __u32 __user *prog_cnt);
 int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,

include/uapi/linux/perf_event.h

@@ -418,6 +418,27 @@ struct perf_event_attr {
 	__u16	__reserved_2;	/* align to __u64 */
 };
 
+/*
+ * Structure used by below PERF_EVENT_IOC_QUERY_BPF command
+ * to query bpf programs attached to the same perf tracepoint
+ * as the given perf event.
+ */
+struct perf_event_query_bpf {
+	/*
+	 * The below ids array length
+	 */
+	__u32	ids_len;
+	/*
+	 * Set by the kernel to indicate the number of
+	 * available programs
+	 */
+	__u32	prog_cnt;
+	/*
+	 * User provided buffer to store program ids
+	 */
+	__u32	ids[0];
+};
+
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))
 
 /*
@@ -433,6 +454,7 @@ struct perf_event_attr {
 #define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
 #define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
 #define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
+#define PERF_EVENT_IOC_QUERY_BPF	_IOWR('$', 10, struct perf_event_query_bpf *)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,

kernel/bpf/core.c

@@ -1462,6 +1462,8 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 	rcu_read_lock();
 	prog = rcu_dereference(progs)->progs;
 	for (; *prog; prog++) {
+		if (*prog == &dummy_bpf_prog.prog)
+			continue;
 		id = (*prog)->aux->id;
 		if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
 			rcu_read_unlock();
@@ -1545,6 +1547,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 	return 0;
 }
 
+int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+			     __u32 __user *prog_ids, u32 request_cnt,
+			     __u32 __user *prog_cnt)
+{
+	u32 cnt = 0;
+
+	if (array)
+		cnt = bpf_prog_array_length(array);
+
+	if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
+		return -EFAULT;
+
+	/* return early if user requested only program count or nothing to copy */
+	if (!request_cnt || !cnt)
+		return 0;
+
+	return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
 	struct bpf_prog_aux *aux;

kernel/events/core.c

@@ -4723,6 +4723,9 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 		rcu_read_unlock();
 		return 0;
 	}
+
+	case PERF_EVENT_IOC_QUERY_BPF:
+		return bpf_event_query_prog_array(event, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}

kernel/trace/bpf_trace.c

@@ -820,3 +820,26 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 unlock:
 	mutex_unlock(&bpf_event_mutex);
 }
+
+int bpf_event_query_prog_array(struct perf_event *event, void __user *info)
+{
+	struct perf_event_query_bpf __user *uquery = info;
+	struct perf_event_query_bpf query = {};
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (event->attr.type != PERF_TYPE_TRACEPOINT)
+		return -EINVAL;
+	if (copy_from_user(&query, uquery, sizeof(query)))
+		return -EFAULT;
+
+	mutex_lock(&bpf_event_mutex);
+	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
+				       uquery->ids,
+				       query.ids_len,
+				       &uquery->prog_cnt);
+	mutex_unlock(&bpf_event_mutex);
+
+	return ret;
+}