bpf: sockmap, add msg_cork_bytes() helper

In the case where we need a specific number of bytes before a
verdict can be assigned, even if the data spans multiple sendmsg
or sendfile calls. The BPF program may use msg_cork_bytes().

The extreme case is a user can call sendmsg repeatedly with
1-byte msg segments. Obviously, this is bad for performance but
is still valid. If the BPF program needs N bytes to validate
a header it can use msg_cork_bytes to specify N bytes and the
BPF program will not be called again until N bytes have been
accumulated. The infrastructure will attempt to coalesce data
if possible so in many cases (most my use cases at least) the
data will be in a single scatterlist element with data pointers
pointing to start/end of the element. However, this is dependent
on available memory so is not guaranteed. So BPF programs must
validate data pointer ranges, but this is the case anyways to
convince the verifier the accesses are valid.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a557a2a5d72d1abf9e0d1d9e99a758e0ecfcfc37..1765cfb16c998d9cbfa824dd3f108478a02d516b 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -792,7 +792,8 @@ union bpf_attr {
        FN(override_return),            \
        FN(sock_ops_cb_flags_set),      \
        FN(msg_redirect_map),           \
-       FN(msg_apply_bytes),
+       FN(msg_apply_bytes),            \
+       FN(msg_cork_bytes),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

diff --git a/net/core/filter.c b/net/core/filter.c
index 17d6775f54318138c5544ee6473904769ef6318d..0c9daf6ee555449e8a3219ee5e4d87984ef1dd01 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1942,6 +1942,20 @@ static const struct bpf_func_proto bpf_msg_apply_bytes_proto = {
        .arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg_buff *, msg, u32, bytes)
+{
+       msg->cork_bytes = bytes;
+       return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
+       .func           = bpf_msg_cork_bytes,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_CTX,
+       .arg2_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
        return task_get_classid(skb);
@@ -3650,6 +3664,8 @@ static const struct bpf_func_proto *sk_msg_func_proto(enum bpf_func_id func_id)
                return &bpf_msg_redirect_map_proto;
        case BPF_FUNC_msg_apply_bytes:
                return &bpf_msg_apply_bytes_proto;
+       case BPF_FUNC_msg_cork_bytes:
+               return &bpf_msg_cork_bytes_proto;
        default:
                return bpf_base_func_proto(func_id);
        }