Commit de4e05ca authored by Yonghong Song's avatar Yonghong Song Committed by Alexei Starovoitov
Browse files

bpf: Support bpf tracing/iter programs for BPF_LINK_CREATE 



Given a bpf program, the step to create an anonymous bpf iterator is:
  - create a bpf_iter_link, which combines bpf program and the target.
    In the future, there could be more information recorded in the link.
    A link_fd will be returned to the user space.
  - create an anonymous bpf iterator with the given link_fd.

The bpf_iter_link can be pinned to bpffs mount file system to
create a file based bpf iterator as well.

The benefit to use of bpf_iter_link:
  - using bpf link simplifies design and implementation as bpf link
    is used for other tracing bpf programs.
  - for file based bpf iterator, bpf_iter_link provides a standard
    way to replace underlying bpf programs.
  - for both anonymous and free based iterators, bpf link query
    capability can be leveraged.

The patch added support of tracing/iter programs for BPF_LINK_CREATE.
A new link type BPF_LINK_TYPE_ITER is added to facilitate link
querying. Currently, only prog_id is needed, so there is no
additional in-kernel show_fdinfo() and fill_link_info() hook
is needed for BPF_LINK_TYPE_ITER link.

Signed-off-by: default avatarYonghong Song <yhs@fb.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarAndrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175901.2475084-1-yhs@fb.com
parent 15d83c4d

include/linux/bpf.h

+1 −0
Original line number Diff line number Diff line
@@ -1143,6 +1143,7 @@ struct bpf_iter_reg { 
int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);

void bpf_iter_unreg_target(const char *target);

bool bpf_iter_prog_supported(struct bpf_prog *prog);

int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);



int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);

int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);

include/linux/bpf_types.h

+1 −0
Original line number Diff line number Diff line
@@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) 
#ifdef CONFIG_CGROUP_BPF

BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)

#endif

BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)

include/uapi/linux/bpf.h

+1 −0
Original line number Diff line number Diff line
@@ -229,6 +229,7 @@ enum bpf_link_type { 
	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,

	BPF_LINK_TYPE_TRACING = 2,

	BPF_LINK_TYPE_CGROUP = 3,

	BPF_LINK_TYPE_ITER = 4,



	MAX_BPF_LINK_TYPE,

};

kernel/bpf/bpf_iter.c

+62 −0
Original line number Diff line number Diff line
@@ -15,6 +15,11 @@ struct bpf_iter_target_info { 
	u32 btf_id;	/* cached value */

};



struct bpf_iter_link {

	struct bpf_link link;

	struct bpf_iter_target_info *tinfo;

};



static struct list_head targets = LIST_HEAD_INIT(targets);

static DEFINE_MUTEX(targets_mutex);
@@ -93,3 +98,60 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) 


	return supported;

}



static void bpf_iter_link_release(struct bpf_link *link)

{

}



static void bpf_iter_link_dealloc(struct bpf_link *link)

{

	struct bpf_iter_link *iter_link =

		container_of(link, struct bpf_iter_link, link);



	kfree(iter_link);

}



static const struct bpf_link_ops bpf_iter_link_lops = {

	.release = bpf_iter_link_release,

	.dealloc = bpf_iter_link_dealloc,

};



int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)

{

	struct bpf_link_primer link_primer;

	struct bpf_iter_target_info *tinfo;

	struct bpf_iter_link *link;

	bool existed = false;

	u32 prog_btf_id;

	int err;



	if (attr->link_create.target_fd || attr->link_create.flags)

		return -EINVAL;



	prog_btf_id = prog->aux->attach_btf_id;

	mutex_lock(&targets_mutex);

	list_for_each_entry(tinfo, &targets, list) {

		if (tinfo->btf_id == prog_btf_id) {

			existed = true;

			break;

		}

	}

	mutex_unlock(&targets_mutex);

	if (!existed)

		return -ENOENT;



	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);

	if (!link)

		return -ENOMEM;



	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog);

	link->tinfo = tinfo;



	err  = bpf_link_prime(&link->link, &link_primer);

	if (err) {

		kfree(link);

		return err;

	}



	return bpf_link_settle(&link_primer);

}

kernel/bpf/syscall.c

+14 −0
Original line number Diff line number Diff line
@@ -2729,6 +2729,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) 
	case BPF_CGROUP_GETSOCKOPT:

	case BPF_CGROUP_SETSOCKOPT:

		return BPF_PROG_TYPE_CGROUP_SOCKOPT;

	case BPF_TRACE_ITER:

		return BPF_PROG_TYPE_TRACING;

	default:

		return BPF_PROG_TYPE_UNSPEC;

	}
@@ -3729,6 +3731,15 @@ err_put: 
	return err;

}



static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)

{

	if (attr->link_create.attach_type == BPF_TRACE_ITER &&

	    prog->expected_attach_type == BPF_TRACE_ITER)

		return bpf_iter_link_attach(attr, prog);



	return -EINVAL;

}



#define BPF_LINK_CREATE_LAST_FIELD link_create.flags

static int link_create(union bpf_attr *attr)

{
@@ -3765,6 +3776,9 @@ static int link_create(union bpf_attr *attr) 
	case BPF_PROG_TYPE_CGROUP_SOCKOPT:

		ret = cgroup_bpf_link_attach(attr, prog);

		break;

	case BPF_PROG_TYPE_TRACING:

		ret = tracing_bpf_link_attach(attr, prog);

		break;

	default:

		ret = -EINVAL;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE