bpf: add MAP_LOOKUP_AND_DELETE_ELEM syscall

The previous patch implemented a bpf queue/stack maps that
provided the peek/pop/push functions.  There is not a direct
relationship between those functions and the current maps
syscalls, hence a new MAP_LOOKUP_AND_DELETE_ELEM syscall is added,
this is mapped to the pop operation in the queue/stack maps
and it is still to implement in other kind of maps.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 70082cb626b43283dab7ec28c5f495c3c9cf36eb..a2fb333290dccf128ee607651e5df58ca4abb4ac 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -103,6 +103,7 @@ enum bpf_cmd {
        BPF_BTF_LOAD,
        BPF_BTF_GET_FD_BY_ID,
        BPF_TASK_FD_QUERY,
+       BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1617407f9ee591f5416114efae2329ff1cde9a38..49ae64a2656282126f38e6d7518fc94cb035e672 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -999,6 +999,69 @@ static int map_get_next_key(union bpf_attr *attr)
        return err;
 }
 
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+
+static int map_lookup_and_delete_elem(union bpf_attr *attr)
+{
+       void __user *ukey = u64_to_user_ptr(attr->key);
+       void __user *uvalue = u64_to_user_ptr(attr->value);
+       int ufd = attr->map_fd;
+       struct bpf_map *map;
+       void *key, *value, *ptr;
+       u32 value_size;
+       struct fd f;
+       int err;
+
+       if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
+               return -EINVAL;
+
+       f = fdget(ufd);
+       map = __bpf_map_get(f);
+       if (IS_ERR(map))
+               return PTR_ERR(map);
+
+       if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+               err = -EPERM;
+               goto err_put;
+       }
+
+       key = __bpf_copy_key(ukey, map->key_size);
+       if (IS_ERR(key)) {
+               err = PTR_ERR(key);
+               goto err_put;
+       }
+
+       value_size = map->value_size;
+
+       err = -ENOMEM;
+       value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+       if (!value)
+               goto free_key;
+
+       if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+           map->map_type == BPF_MAP_TYPE_STACK) {
+               err = map->ops->map_pop_elem(map, value);
+       } else {
+               err = -ENOTSUPP;
+       }
+
+       if (err)
+               goto free_value;
+
+       if (copy_to_user(uvalue, value, value_size) != 0)
+               goto free_value;
+
+       err = 0;
+
+free_value:
+       kfree(value);
+free_key:
+       kfree(key);
+err_put:
+       fdput(f);
+       return err;
+}
+
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name) \
        [_id] = & _name ## _prog_ops,
@@ -2472,6 +2535,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
        case BPF_TASK_FD_QUERY:
                err = bpf_task_fd_query(&attr, uattr);
                break;
+       case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
+               err = map_lookup_and_delete_elem(&attr);
+               break;
        default:
                err = -EINVAL;
                break;