bpf: Support GET_FD_BY_ID and GET_NEXT_ID for bpf_link

Add support to look up bpf_link by ID and iterate over all existing bpf_links
in the system. GET_FD_BY_ID code handles not-yet-ready bpf_link by checking
that its ID hasn't been set to non-zero value yet. Setting bpf_link's ID is
done as the very last step in finalizing bpf_link, together with installing
FD. This approach allows users of bpf_link in kernel code to not worry about
races between user-space and kernel code that hasn't finished attaching and
initializing bpf_link.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200429001614.1544-4-andriin@fb.com

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6121aa4..7e6541f 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -113,6 +113,8 @@ enum bpf_cmd {
        BPF_MAP_DELETE_BATCH,
        BPF_LINK_CREATE,
        BPF_LINK_UPDATE,
+       BPF_LINK_GET_FD_BY_ID,
+       BPF_LINK_GET_NEXT_ID,
 };
 
 enum bpf_map_type {

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5439e05..1c213a7 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3713,6 +3713,48 @@ out_put_link:
        return ret;
 }
 
+static int bpf_link_inc_not_zero(struct bpf_link *link)
+{
+       return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT;
+}
+
+#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
+
+static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
+{
+       struct bpf_link *link;
+       u32 id = attr->link_id;
+       int fd, err;
+
+       if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID))
+               return -EINVAL;
+
+       if (!capable(CAP_SYS_ADMIN))
+               return -EPERM;
+
+       spin_lock_bh(&link_idr_lock);
+       link = idr_find(&link_idr, id);
+       /* before link is "settled", ID is 0, pretend it doesn't exist yet */
+       if (link) {
+               if (link->id)
+                       err = bpf_link_inc_not_zero(link);
+               else
+                       err = -EAGAIN;
+       } else {
+               err = -ENOENT;
+       }
+       spin_unlock_bh(&link_idr_lock);
+
+       if (err)
+               return err;
+
+       fd = bpf_link_new_fd(link);
+       if (fd < 0)
+               bpf_link_put(link);
+
+       return fd;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
        union bpf_attr attr;
@@ -3830,6 +3872,13 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
        case BPF_LINK_UPDATE:
                err = link_update(&attr);
                break;
+       case BPF_LINK_GET_FD_BY_ID:
+               err = bpf_link_get_fd_by_id(&attr);
+               break;
+       case BPF_LINK_GET_NEXT_ID:
+               err = bpf_obj_get_next_id(&attr, uattr,
+                                         &link_idr, &link_idr_lock);
+               break;
        default:
                err = -EINVAL;
                break;