Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit a23967c1 authored by Alexei Starovoitov's avatar Alexei Starovoitov
Browse files

Merge branch 'bpf-tracing-multiprog-tp-query' 



Yonghong Song says:

====================
Commit e87c6bc3 ("bpf: permit multiple bpf attachments
for a single perf event") added support to attach multiple
bpf programs to a single perf event. Given a perf event
(kprobe, uprobe, or kernel tracepoint), the perf ioctl interface
is used to query bpf programs attached to the same trace event.

There already exists a BPF_PROG_QUERY command for introspection
currently used by cgroup+bpf. We did have an implementation for
querying tracepoint+bpf through the same interface. However, it
looks cleaner to use ioctl() style of api here, since attaching
bpf prog to tracepoint/kuprobe is also done via ioctl.

Patch #1 had the core implementation and patch #2 added
a test case in tools bpf selftests suite.

Changelogs:
v3 -> v4:
  - Fix a compilation error with newer gcc like 6.3.1 while
    old gcc 4.8.5 is okay. I was using &uquery->ids to represent
    the address to the ids array to make it explicit that the
    address is passed, and this syntax is rightly rejected
    by gcc 6.3.1.
v2 -> v3:
  - Change uapi structure perf_event_query_bpf to be more
    clearer based on Peter's suggestion, and adjust
    other codes accordingly.
v1 -> v2:
  - Rebase on top of net-next.
  - Use existing bpf_prog_array_length function instead of
    implementing the same functionality in function
    bpf_prog_array_copy_info.
====================

Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
parents 63060c39 d279f1f8

include/linux/bpf.h

+4 −0
Original line number Diff line number Diff line
@@ -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

+22 −0
Original line number Diff line number Diff line
@@ -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

+21 −0
Original line number Diff line number Diff line
@@ -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

+3 −0
Original line number Diff line number Diff line
@@ -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

+23 −0
Original line number Diff line number Diff line
@@ -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;

}