Added support for calling a subset of socket setsockopts from
BPF_PROG_TYPE_SOCKET_OPS programs. The code was duplicated rather
than making the changes to call the socket setsockopt function because
the changes required would have been larger.
The ops supported are:
SO_RCVBUF
SO_SNDBUF
SO_MAX_PACING_RATE
SO_PRIORITY
SO_RCVLOWAT
SO_MARK
Signed-off-by: Lawrence Brakmo <bra...@fb.com>
---
include/uapi/linux/bpf.h | 14 ++++++++-
net/core/filter.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++-
samples/bpf/bpf_helpers.h | 3 ++
3 files changed, 92 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b2af839..e229d61 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -495,6 +495,17 @@ union bpf_attr {
* Get the owner uid of the socket stored inside sk_buff.
* @skb: pointer to skb
* Return: uid of the socket owner on success or overflowuid if failed.
+ *
+ * int bpf_setsockopt(sk, level, optname, optval, optlen)
+ * Calls setsockopt. Not all opts are available, only those with
+ * integer optvals plus TCP_CONGESTION.
+ * Supported levels: SOL_SOCKET and IPROTO_TCP
+ * @sk: pointer to bpf_socket
+ * @level: SOL_SOCKET or IPROTO_TCP
+ * @optname: option name
+ * @optval: pointer to option value
+ * @optlen: length of optval in byes
+ * Return: 0 or negative error
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -544,7 +555,8 @@ union bpf_attr {
FN(xdp_adjust_head), \
FN(probe_read_str), \
FN(get_socket_cookie), \
- FN(get_socket_uid),
+ FN(get_socket_uid), \
+ FN(setsockopt),
/* 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 7b61690..6bc8d57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -54,6 +54,7 @@
#include <net/dst.h>
#include <net/sock_reuseport.h>
#include <net/busy_poll.h>
+#include <net/tcp.h>
/**
* sk_filter_trim_cap - run a packet through a socket filter
@@ -2653,6 +2654,69 @@ static const struct bpf_func_proto
bpf_get_socket_uid_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_5(bpf_setsockopt, struct bpf_socket_ops_kern *, bpf_socket,
+ int, level, int, optname, char *, optval, int, optlen)
+{
+ int val;
+ int ret = 0;
+ struct sock *sk = bpf_socket->sk;
+
+ if (bpf_socket->is_req_sock)
+ return -EINVAL;
+
+ if (level == SOL_SOCKET) {
+ // Only some socketops are supported
+ val = *((int *)optval);
+
+ switch (optname) {
+ case SO_RCVBUF:
+ sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+ sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+ break;
+ case SO_SNDBUF:
+ sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
+ sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+ break;
+ case SO_MAX_PACING_RATE:
+ sk->sk_max_pacing_rate = val;
+ sk->sk_pacing_rate = min(sk->sk_pacing_rate,
+ sk->sk_max_pacing_rate);
+ break;
+ case SO_PRIORITY:
+ sk->sk_priority = val;
+ break;
+ case SO_RCVLOWAT:
+ if (val < 0)
+ val = INT_MAX;
+ sk->sk_rcvlowat = val ? : 1;
+ break;
+ case SO_MARK:
+ sk->sk_mark = val;
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ } else if (level == SOL_TCP &&
+ bpf_socket->sk->sk_prot->setsockopt == tcp_setsockopt) {
+ // Place holder
+ ret = -EINVAL;
+ } else {
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_setsockopt_proto = {
+ .func = bpf_setsockopt,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+};
+
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
@@ -2808,6 +2872,17 @@ lwt_inout_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
+ socket_ops_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_setsockopt:
+ return &bpf_setsockopt_proto;
+ default:
+ return bpf_base_func_proto(func_id);
+ }
+}
+
+static const struct bpf_func_proto *
lwt_xmit_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
@@ -3523,7 +3598,7 @@ const struct bpf_verifier_ops cg_sock_prog_ops = {
};
const struct bpf_verifier_ops socket_ops_prog_ops = {
- .get_func_proto = bpf_base_func_proto,
+ .get_func_proto = socket_ops_func_proto,
.is_valid_access = socket_ops_is_valid_access,
.convert_ctx_access = socket_ops_convert_ctx_access,
};
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 51e567b..d7514c0 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -60,6 +60,9 @@ static unsigned long long (*bpf_get_prandom_u32)(void) =
(void *) BPF_FUNC_get_prandom_u32;
static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_head;
+static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
+ int optlen) =
+ (void *) BPF_FUNC_setsockopt;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
--
2.9.3
