Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit b13d8807 authored by Lawrence Brakmo's avatar Lawrence Brakmo Committed by Alexei Starovoitov
Browse files

bpf: Adds field bpf_sock_ops_cb_flags to tcp_sock 



Adds field bpf_sock_ops_cb_flags to tcp_sock and bpf_sock_ops. Its primary
use is to determine if there should be calls to sock_ops bpf program at
various points in the TCP code. The field is initialized to zero,
disabling the calls. A sock_ops BPF program can set it, per connection and
as necessary, when the connection is established.

It also adds support for reading and writting the field within a
sock_ops BPF program. Reading is done by accessing the field directly.
However, writing is done through the helper function
bpf_sock_ops_cb_flags_set, in order to return an error if a BPF program
is trying to set a callback that is not supported in the current kernel
(i.e. running an older kernel). The helper function returns 0 if it was
able to set all of the bits set in the argument, a positive number
containing the bits that could not be set, or -EINVAL if the socket is
not a full TCP socket.

Examples of where one could call the bpf program:

1) When RTO fires
2) When a packet is retransmitted
3) When the connection terminates
4) When a packet is sent
5) When a packet is received

Signed-off-by: default avatarLawrence Brakmo <brakmo@fb.com>
Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
parent de525be2

include/linux/tcp.h

+11 −0
Original line number Diff line number Diff line
@@ -335,6 +335,17 @@ struct tcp_sock { 


	int			linger2;





/* Sock_ops bpf program related variables */

#ifdef CONFIG_BPF

	u8	bpf_sock_ops_cb_flags;  /* Control calling BPF programs

					 * values defined in uapi/linux/tcp.h

					 */

#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG)

#else

#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0

#endif



/* Receiver side RTT estimation */

	struct {

		u32	rtt_us;

include/uapi/linux/bpf.h

+16 −1
Original line number Diff line number Diff line
@@ -642,6 +642,14 @@ union bpf_attr { 
 *     @optlen: length of optval in bytes

 *     Return: 0 or negative error

 *

 * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)

 *     Set callback flags for sock_ops

 *     @bpf_sock_ops: pointer to bpf_sock_ops_kern struct

 *     @flags: flags value

 *     Return: 0 for no error

 *             -EINVAL if there is no full tcp socket

 *             bits in flags that are not supported by current kernel

 *

 * int bpf_skb_adjust_room(skb, len_diff, mode, flags)

 *     Grow or shrink room in sk_buff.

 *     @skb: pointer to skb
@@ -748,7 +756,8 @@ union bpf_attr { 
	FN(perf_event_read_value),	\

	FN(perf_prog_read_value),	\

	FN(getsockopt),			\

	FN(override_return),

	FN(override_return),		\

	FN(sock_ops_cb_flags_set),



/* integer value in 'imm' field of BPF_CALL instruction selects which helper

 * function eBPF program intends to call
@@ -969,8 +978,14 @@ struct bpf_sock_ops { 
				 */

	__u32 snd_cwnd;

	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */

	__u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */

};



/* Definitions for bpf_sock_ops_cb_flags */

#define BPF_SOCK_OPS_ALL_CB_FLAGS       0		/* Mask of all currently

							 * supported cb flags

							 */



/* List of known BPF sock_ops operators.

 * New entries can only be added at the end

 */

net/core/filter.c

+34 −0
Original line number Diff line number Diff line
@@ -3328,6 +3328,33 @@ static const struct bpf_func_proto bpf_getsockopt_proto = { 
	.arg5_type	= ARG_CONST_SIZE,

};



BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,

	   int, argval)

{

	struct sock *sk = bpf_sock->sk;

	int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;



	if (!sk_fullsock(sk))

		return -EINVAL;



#ifdef CONFIG_INET

	if (val)

		tcp_sk(sk)->bpf_sock_ops_cb_flags = val;



	return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS);

#else

	return -EINVAL;

#endif

}



static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = {

	.func		= bpf_sock_ops_cb_flags_set,

	.gpl_only	= false,

	.ret_type	= RET_INTEGER,

	.arg1_type	= ARG_PTR_TO_CTX,

	.arg2_type	= ARG_ANYTHING,

};



static const struct bpf_func_proto *

bpf_base_func_proto(enum bpf_func_id func_id)

{
@@ -3510,6 +3537,8 @@ static const struct bpf_func_proto * 
		return &bpf_setsockopt_proto;

	case BPF_FUNC_getsockopt:

		return &bpf_getsockopt_proto;

	case BPF_FUNC_sock_ops_cb_flags_set:

		return &bpf_sock_ops_cb_flags_set_proto;

	case BPF_FUNC_sock_map_update:

		return &bpf_sock_map_update_proto;

	default:
@@ -4546,6 +4575,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, 
	case offsetof(struct bpf_sock_ops, srtt_us):

		SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);

		break;



	case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags):

		SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags,

				   struct tcp_sock);

		break;

	}

	return insn - insn_buf;

}