summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf-cgroup.h18
-rw-r--r--include/linux/bpf_types.h1
-rw-r--r--include/linux/filter.h9
-rw-r--r--include/net/tcp.h66
-rw-r--r--include/uapi/linux/bpf.h68
5 files changed, 160 insertions, 2 deletions
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index c970a25d2a49..360c082e885c 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -7,6 +7,7 @@
struct sock;
struct cgroup;
struct sk_buff;
+struct bpf_sock_ops_kern;
#ifdef CONFIG_CGROUP_BPF
@@ -42,6 +43,10 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
int __cgroup_bpf_run_filter_sk(struct sock *sk,
enum bpf_attach_type type);
+int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
+ struct bpf_sock_ops_kern *sock_ops,
+ enum bpf_attach_type type);
+
/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
({ \
@@ -75,6 +80,18 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
__ret; \
})
+#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled && (sock_ops)->sk) { \
+ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \
+ if (sk_fullsock(__sk)) \
+ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \
+ sock_ops, \
+ BPF_CGROUP_SOCK_OPS); \
+ } \
+ __ret; \
+})
#else
struct cgroup_bpf {};
@@ -85,6 +102,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#endif /* CONFIG_CGROUP_BPF */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 03bf223f18be..3d137c33d664 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -10,6 +10,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops)
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops)
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops)
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops)
#endif
#ifdef CONFIG_BPF_EVENTS
BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1fa26dc562ce..738f8b14f025 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -898,4 +898,13 @@ static inline int bpf_tell_extensions(void)
return SKF_AD_MAX;
}
+struct bpf_sock_ops_kern {
+ struct sock *sk;
+ u32 op;
+ union {
+ u32 reply;
+ u32 replylong[4];
+ };
+};
+
#endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d0751b79d99c..70483296157f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -46,6 +46,10 @@
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/bpf-cgroup.h>
+
extern struct inet_hashinfo tcp_hashinfo;
extern struct percpu_counter tcp_orphan_count;
@@ -1000,7 +1004,9 @@ void tcp_get_default_congestion_control(char *name);
void tcp_get_available_congestion_control(char *buf, size_t len);
void tcp_get_allowed_congestion_control(char *buf, size_t len);
int tcp_set_allowed_congestion_control(char *allowed);
-int tcp_set_congestion_control(struct sock *sk, const char *name);
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load);
+void tcp_reinit_congestion_control(struct sock *sk,
+ const struct tcp_congestion_ops *ca);
u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
@@ -2021,4 +2027,62 @@ int tcp_set_ulp(struct sock *sk, const char *name);
void tcp_get_available_ulp(char *buf, size_t len);
void tcp_cleanup_ulp(struct sock *sk);
+/* Call BPF_SOCK_OPS program that returns an int. If the return value
+ * is < 0, then the BPF op failed (for example if the loaded BPF
+ * program does not support the chosen operation or there is no BPF
+ * program loaded).
+ */
+#ifdef CONFIG_BPF
+static inline int tcp_call_bpf(struct sock *sk, int op)
+{
+ struct bpf_sock_ops_kern sock_ops;
+ int ret;
+
+ if (sk_fullsock(sk))
+ sock_owned_by_me(sk);
+
+ memset(&sock_ops, 0, sizeof(sock_ops));
+ sock_ops.sk = sk;
+ sock_ops.op = op;
+
+ ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+ if (ret == 0)
+ ret = sock_ops.reply;
+ else
+ ret = -1;
+ return ret;
+}
+#else
+static inline int tcp_call_bpf(struct sock *sk, int op)
+{
+ return -EPERM;
+}
+#endif
+
+static inline u32 tcp_timeout_init(struct sock *sk)
+{
+ int timeout;
+
+ timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+
+ if (timeout <= 0)
+ timeout = TCP_TIMEOUT_INIT;
+ return timeout;
+}
+
+static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
+{
+ int rwnd;
+
+ rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
+
+ if (rwnd < 0)
+ rwnd = 0;
+ return rwnd;
+}
+
+static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
+{
+ return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
+}
#endif /* _TCP_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f94b48b168dc..a6a91e5e96fc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -120,12 +120,14 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LWT_IN,
BPF_PROG_TYPE_LWT_OUT,
BPF_PROG_TYPE_LWT_XMIT,
+ BPF_PROG_TYPE_SOCK_OPS,
};
enum bpf_attach_type {
BPF_CGROUP_INET_INGRESS,
BPF_CGROUP_INET_EGRESS,
BPF_CGROUP_INET_SOCK_CREATE,
+ BPF_CGROUP_SOCK_OPS,
__MAX_BPF_ATTACH_TYPE
};
@@ -518,6 +520,17 @@ union bpf_attr {
* Set full skb->hash.
* @skb: pointer to skb
* @hash: hash to set
+ *
+ * int bpf_setsockopt(bpf_socket, 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
+ * @bpf_socket: 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), \
@@ -568,7 +581,8 @@ union bpf_attr {
FN(probe_read_str), \
FN(get_socket_cookie), \
FN(get_socket_uid), \
- FN(set_hash),
+ FN(set_hash), \
+ FN(setsockopt),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -720,4 +734,56 @@ struct bpf_map_info {
__u32 map_flags;
} __attribute__((aligned(8)));
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+ __u32 op;
+ union {
+ __u32 reply;
+ __u32 replylong[4];
+ };
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+ BPF_SOCK_OPS_VOID,
+ BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or
+ * -1 if default value should be used
+ */
+ BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized
+ * window (in packets) or -1 if default
+ * value should be used
+ */
+ BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an
+ * active connection is initialized
+ */
+ BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an
+ * active connection is
+ * established
+ */
+ BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a
+ * passive connection is
+ * established
+ */
+ BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control
+ * needs ECN
+ */
+};
+
+#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
+
#endif /* _UAPI__LINUX_BPF_H__ */
generated by cgit v1.2.3-71-gd317 (git 2.46.0) at 2026-01-05 22:37:36 +0000