diff mbox series

[bpf,08/11] bpf: Add sock_ops R/W access to tclass & sk_txhash

Message ID 20171219062200.372711-9-brakmo@fb.com
State Changes Requested, archived
Delegated to: BPF Maintainers
Headers show
Series bpf: more sock_ops callbacks | expand

Commit Message

Lawrence Brakmo Dec. 19, 2017, 6:21 a.m. UTC 
Adds direct R/W access to sk_txhash and access to tclass for ipv6 flows
through getsockopt and setsockopt. Sample usage for tclass:

  bpf_getsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, sizeof(v))

where skops is a pointer to the ctx (struct bpf_sock_ops).

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h |  1 +
 net/core/filter.c        | 47 ++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 47 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 19a0b1b..fe2b692 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -973,6 +973,7 @@  struct bpf_sock_ops {
 	__u32 data_segs_out;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__u32 sk_txhash;
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 2628077..5cb2b70 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3229,6 +3229,29 @@  BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			ret = -EINVAL;
 		}
 #ifdef CONFIG_INET
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (level == SOL_IPV6) {
+		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
+			return -EINVAL;
+
+		val = *((int *)optval);
+		/* Only some options are supported */
+		switch (optname) {
+		case IPV6_TCLASS:
+			if (val < -1 || val > 0xff) {
+				ret = -EINVAL;
+			} else {
+				struct ipv6_pinfo *np = inet6_sk(sk);
+
+				if (val == -1)
+					val = 0;
+				np->tclass = val;
+			}
+			break;
+		default:
+			ret = -EINVAL;
+		}
+#endif
 	} else if (level == SOL_TCP &&
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
@@ -3238,7 +3261,8 @@  BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false, reinit);
+			ret = tcp_set_congestion_control(sk, name, false,
+							 reinit);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
@@ -3304,6 +3328,22 @@  BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		} else {
 			goto err_clear;
 		}
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (level == SOL_IPV6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+
+		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
+			goto err_clear;
+
+		/* Only some options are supported */
+		switch (optname) {
+		case IPV6_TCLASS:
+			*((int *)optval) = (int)np->tclass;
+			break;
+		default:
+			goto err_clear;
+		}
+#endif
 	} else {
 		goto err_clear;
 	}
@@ -3843,6 +3883,7 @@  static bool sock_ops_is_valid_access(int off, int size,
 		case offsetof(struct bpf_sock_ops, op) ...
 		     offsetof(struct bpf_sock_ops, replylong[3]):
 		case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags):
+		case offsetof(struct bpf_sock_ops, sk_txhash):
 			break;
 		default:
 			return false;
@@ -4622,6 +4663,10 @@  static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_sock_ops, bytes_acked):
 		SOCK_OPS_GET_FIELD(bytes_acked, struct tcp_sock);
 		break;
+
+	case offsetof(struct bpf_sock_ops, sk_txhash):
+		SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, struct sock, type);
+		break;
 	}
 	return insn - insn_buf;
 }