bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data

This implements a BPF ULP layer to allow policy enforcement and
monitoring at the socket layer. In order to support this a new
program type BPF_PROG_TYPE_SK_MSG is used to run the policy at
the sendmsg/sendpage hook. To attach the policy to sockets a
sockmap is used with a new program attach type BPF_SK_MSG_VERDICT.

Similar to previous sockmap usages when a sock is added to a
sockmap, via a map update, if the map contains a BPF_SK_MSG_VERDICT
program type attached then the BPF ULP layer is created on the
socket and the attached BPF_PROG_TYPE_SK_MSG program is run for
every msg in sendmsg case and page/offset in sendpage case.

BPF_PROG_TYPE_SK_MSG Semantics/API:

BPF_PROG_TYPE_SK_MSG supports only two return codes SK_PASS and
SK_DROP. Returning SK_DROP free's the copied data in the sendmsg
case and in the sendpage case leaves the data untouched. Both cases
return -EACESS to the user. Returning SK_PASS will allow the msg to
be sent.

In the sendmsg case data is copied into kernel space buffers before
running the BPF program. The kernel space buffers are stored in a
scatterlist object where each element is a kernel memory buffer.
Some effort is made to coalesce data from the sendmsg call here.
For example a sendmsg call with many one byte iov entries will
likely be pushed into a single entry. The BPF program is run with
data pointers (start/end) pointing to the first sg element.

In the sendpage case data is not copied. We opt not to copy the
data by default here, because the BPF infrastructure does not
know what bytes will be needed nor when they will be needed. So
copying all bytes may be wasteful. Because of this the initial
start/end data pointers are (0,0). Meaning no data can be read or
written. This avoids reading data that may be modified by the
user. A new helper is added later in this series if reading and
writing the data is needed. The helper call will do a copy by
default so that the page is exclusively owned by the BPF call.

The verdict from the BPF_PROG_TYPE_SK_MSG applies to the entire msg
in the sendmsg() case and the entire page/offset in the sendpage case.
This avoids ambiguity on how to handle mixed return codes in the
sendmsg case. Again a helper is added later in the series if
a verdict needs to apply to multiple system calls and/or only
a subpart of the currently being processed message.

The helper msg_redirect_map() can be used to select the socket to
send the data on. This is used similar to existing redirect use
cases. This allows policy to redirect msgs.

Pseudo code simple example:

The basic logic to attach a program to a socket is as follows,

  // load the programs
  bpf_prog_load(SOCKMAP_TCP_MSG_PROG, BPF_PROG_TYPE_SK_MSG,
		&obj, &msg_prog);

  // lookup the sockmap
  bpf_map_msg = bpf_object__find_map_by_name(obj, "my_sock_map");

  // get fd for sockmap
  map_fd_msg = bpf_map__fd(bpf_map_msg);

  // attach program to sockmap
  bpf_prog_attach(msg_prog, map_fd_msg, BPF_SK_MSG_VERDICT, 0);

Adding sockets to the map is done in the normal way,

  // Add a socket 'fd' to sockmap at location 'i'
  bpf_map_update_elem(map_fd_msg, &i, fd, BPF_ANY);

After the above any socket attached to "my_sock_map", in this case
'fd', will run the BPF msg verdict program (msg_prog) on every
sendmsg and sendpage system call.

For a complete example see BPF selftests or sockmap samples.

Implementation notes:

It seemed the simplest, to me at least, to use a refcnt to ensure
psock is not lost across the sendmsg copy into the sg, the bpf program
running on the data in sg_data, and the final pass to the TCP stack.
Some performance testing may show a better method to do this and avoid
the refcnt cost, but for now use the simpler method.

Another item that will come after basic support is in place is
supporting MSG_MORE flag. At the moment we call sendpages even if
the MSG_MORE flag is set. An enhancement would be to collect the
pages into a larger scatterlist and pass down the stack. Notice that
bpf_tcp_sendmsg() could support this with some additional state saved
across sendmsg calls. I built the code to support this without having
to do refactoring work. Other features TBD include ZEROCOPY and the
TCP_RECV_QUEUE/TCP_NO_QUEUE support. This will follow initial series
shortly.

Future work could improve size limits on the scatterlist rings used
here. Currently, we use MAX_SKB_FRAGS simply because this was being
used already in the TLS case. Future work could extend the kernel sk
APIs to tune this depending on workload. This is a trade-off
between memory usage and throughput performance.

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>

1 files changed, 106 insertions, 0 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 33edfa8372fd..2b6c47597eab 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1890,6 +1890,44 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
+	   struct bpf_map *, map, u32, key, u64, flags)
+{
+	/* If user passes invalid input drop the packet. */
+	if (unlikely(flags))
+		return SK_DROP;
+
+	msg->key = key;
+	msg->flags = flags;
+	msg->map = map;
+
+	return SK_PASS;
+}
+
+struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
+{
+	struct sock *sk = NULL;
+
+	if (msg->map) {
+		sk = __sock_map_lookup_elem(msg->map, msg->key);
+
+		msg->key = 0;
+		msg->map = NULL;
+	}
+
+	return sk;
+}
+
+static const struct bpf_func_proto bpf_msg_redirect_map_proto = {
+	.func           = bpf_msg_redirect_map,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -3591,6 +3629,16 @@ static const struct bpf_func_proto *
 	}
 }
 
+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;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+}
+
 static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -3980,6 +4028,32 @@ static bool sk_skb_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, info);
 }
 
+static bool sk_msg_is_valid_access(int off, int size,
+				   enum bpf_access_type type,
+				   struct bpf_insn_access_aux *info)
+{
+	if (type == BPF_WRITE)
+		return false;
+
+	switch (off) {
+	case offsetof(struct sk_msg_md, data):
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case offsetof(struct sk_msg_md, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
+	if (off < 0 || off >= sizeof(struct sk_msg_md))
+		return false;
+	if (off % size != 0)
+		return false;
+	if (size != sizeof(__u64))
+		return false;
+
+	return true;
+}
+
 static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 				  const struct bpf_insn *si,
 				  struct bpf_insn *insn_buf,
@@ -4778,6 +4852,29 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
+static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
+				     const struct bpf_insn *si,
+				     struct bpf_insn *insn_buf,
+				     struct bpf_prog *prog, u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct sk_msg_md, data):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg_buff, data));
+		break;
+	case offsetof(struct sk_msg_md, data_end):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data_end),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg_buff, data_end));
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
 const struct bpf_verifier_ops sk_filter_verifier_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
@@ -4868,6 +4965,15 @@ const struct bpf_verifier_ops sk_skb_verifier_ops = {
 const struct bpf_prog_ops sk_skb_prog_ops = {
 };
 
+const struct bpf_verifier_ops sk_msg_verifier_ops = {
+	.get_func_proto		= sk_msg_func_proto,
+	.is_valid_access	= sk_msg_is_valid_access,
+	.convert_ctx_access	= sk_msg_convert_ctx_access,
+};
+
+const struct bpf_prog_ops sk_msg_prog_ops = {
+};
+
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;