bpf, sockmap: add skb_adjust_room to pop bytes off ingress payload

This implements a new helper skb_adjust_room() so users can push/pop
extra bytes from a BPF_SK_SKB_STREAM_VERDICT program.

Some protocols may include headers and other information that we may
not want to include when doing a redirect from a BPF_SK_SKB_STREAM_VERDICT
program. One use case is to redirect TLS packets into a receive socket
that doesn't expect TLS data. In TLS case the first 13B or so contain the
protocol header. With KTLS the payload is decrypted so we should be able
to redirect this to a receiving socket, but the receiving socket may not
be expecting to receive a TLS header and discard the data. Using the
above helper we can pop the header off and put an appropriate header on
the payload. This allows for creating a proxy between protocols without
extra hops through the stack or userspace.

So in order to fix this case add skb_adjust_room() so users can strip the
header. After this the user can strip the header and an unmodified receiver
thread will work correctly when data is redirected into the ingress path
of a sock.

Signed-off-by: John Fastabend <[email protected]>

Author: jrfastab

net/core/filter.c

@@ -76,6 +76,7 @@
 #include <net/bpf_sk_storage.h>
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
+#include <net/tls.h>
 
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -3218,6 +3219,53 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 			  SKB_MAX_ALLOC;
 }
 
+BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
+	   u32, mode, u64, flags)
+{
+	unsigned int len_diff_abs = abs(len_diff);
+	bool shrink = len_diff < 0;
+	int ret = 0;
+
+	if (unlikely(flags))
+		return -EINVAL;
+	if (unlikely(len_diff_abs > 0xfffU))
+		return -EFAULT;
+
+	if (!shrink) {
+		unsigned int grow = len_diff;
+
+		ret = skb_cow(skb, grow);
+		if (likely(!ret)) {
+			__skb_push(skb, len_diff_abs);
+			memset(skb->data, 0, len_diff_abs);
+		}
+	} else {
+		/* skb_ensure_writable() is not needed here, as we're
+		 * already working on an uncloned skb.
+		 */
+		if (unlikely(!pskb_may_pull(skb, len_diff_abs)))
+			return -ENOMEM;
+		__skb_pull(skb, len_diff_abs);
+	}
+	bpf_compute_data_end_sk_skb(skb);
+	if (tls_sw_has_ctx_rx(skb->sk)) {
+		struct strp_msg *rxm = strp_msg(skb);
+
+		rxm->full_len += len_diff;
+	}
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_adjust_room_proto = {
+	.func		= sk_skb_adjust_room,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	   u32, mode, u64, flags)
 {
@@ -6484,6 +6532,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_change_tail ||
 	    func == sk_skb_change_tail ||
 	    func == bpf_skb_adjust_room ||
+	    func == sk_skb_adjust_room ||
 	    func == bpf_skb_pull_data ||
 	    func == sk_skb_pull_data ||
 	    func == bpf_clone_redirect ||
@@ -6951,6 +7000,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &sk_skb_change_tail_proto;
 	case BPF_FUNC_skb_change_head:
 		return &sk_skb_change_head_proto;
+	case BPF_FUNC_skb_adjust_room:
+		return &sk_skb_adjust_room_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid: