[bpf-next PATCH v3 06/18] bpf: sockmap, add bpf_msg_apply_bytes() helper

[John Fastabend <john.fastabend@gmail.com>]

A single sendmsg or sendfile system call can contain multiple logical
messages that a BPF program may want to read and apply a verdict. But,
without an apply_bytes helper any verdict on the data applies to all
bytes in the sendmsg/sendfile. Alternatively, a BPF program may only
care to read the first N bytes of a msg. If the payload is large say
MB or even GB setting up and calling the BPF program repeatedly for
all bytes, even though the verdict is already known, creates
unnecessary overhead.

To allow BPF programs to control how many bytes a given verdict
applies to we implement a bpf_msg_apply_bytes() helper. When called
from within a BPF program this sets a counter, internal to the
BPF infrastructure, that applies the last verdict to the next N
bytes. If the N is smaller than the current data being processed
from a sendmsg/sendfile call, the first N bytes will be sent and
the BPF program will be re-run with start_data pointing to the N+1
byte. If N is larger than the current data being processed the
BPF verdict will be applied to multiple sendmsg/sendfile calls
until N bytes are consumed.

Note1 if a socket closes with apply_bytes counter non-zero this
is not a problem because data is not being buffered for N bytes
and is sent as its received.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
 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 ef52953..a557a2a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -791,7 +791,8 @@ struct bpf_stack_build_id {
 	FN(getsockopt),			\
 	FN(override_return),		\
 	FN(sock_ops_cb_flags_set),	\
-	FN(msg_redirect_map),
+	FN(msg_redirect_map),		\
+	FN(msg_apply_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 2b6c475..17d6775 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1928,6 +1928,20 @@ struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
 	.arg4_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg_buff *, msg, u32, bytes)
+{
+	msg->apply_bytes = bytes;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_apply_bytes_proto = {
+	.func           = bpf_msg_apply_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);
@@ -3634,6 +3648,8 @@ static const struct bpf_func_proto *sk_msg_func_proto(enum bpf_func_id func_id)
 	switch (func_id) {
 	case BPF_FUNC_msg_redirect_map:
 		return &bpf_msg_redirect_map_proto;
+	case BPF_FUNC_msg_apply_bytes:
+		return &bpf_msg_apply_bytes_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}