From 91843d540a139eb8070bcff8aa10089164436deb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sun, 18 Mar 2018 12:57:20 -0700 Subject: [PATCH] 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 Acked-by: David S. Miller Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 3 ++- net/core/filter.c | 16 ++++++++++++++++ 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a557a2a5d72d..1765cfb16c99 100644 --- 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 17d6775f5431..0c9daf6ee555 100644 --- 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); }