From b73042b8a28e2603ac178295ab96c876ba5a97a1 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Thu, 25 Jan 2018 16:14:08 -0800 Subject: [PATCH] bpf: Add write access to tcp_sock and sock fields This patch adds a macro, SOCK_OPS_SET_FIELD, for writing to struct tcp_sock or struct sock fields. This required adding a new field "temp" to struct bpf_sock_ops_kern for temporary storage that is used by sock_ops_convert_ctx_access. It is used to store and recover the contents of a register, so the register can be used to store the address of the sk. Since we cannot overwrite the dst_reg because it contains the pointer to ctx, nor the src_reg since it contains the value we want to store, we need an extra register to contain the address of the sk. Also adds the macro SOCK_OPS_GET_OR_SET_FIELD that calls one of the GET or SET macros depending on the value of the TYPE field. Signed-off-by: Lawrence Brakmo Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 9 ++++++++ include/net/tcp.h | 2 +- net/core/filter.c | 48 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 58 insertions(+), 1 deletion(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index 425056c7f96c..daa5a676335f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1007,6 +1007,15 @@ struct bpf_sock_ops_kern { u32 replylong[4]; }; u32 is_fullsock; + u64 temp; /* temp and everything after is not + * initialized to 0 before calling + * the BPF program. New fields that + * should be initialized to 0 should + * be inserted before temp. + * temp is scratch storage used by + * sock_ops_convert_ctx_access + * as temporary storage of a register. + */ }; #endif /* __LINUX_FILTER_H__ */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 5a1d26a18599..6092eaff61cf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2011,7 +2011,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op) struct bpf_sock_ops_kern sock_ops; int ret; - memset(&sock_ops, 0, sizeof(sock_ops)); + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; sock_owned_by_me(sk); diff --git a/net/core/filter.c b/net/core/filter.c index dbb6d2f60680..c356ec02b1a5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4491,6 +4491,54 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, offsetof(OBJ, OBJ_FIELD)); \ } while (0) +/* Helper macro for adding write access to tcp_sock or sock fields. + * The macro is called with two registers, dst_reg which contains a pointer + * to ctx (context) and src_reg which contains the value that should be + * stored. However, we need an additional register since we cannot overwrite + * dst_reg because it may be used later in the program. + * Instead we "borrow" one of the other register. We first save its value + * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore + * it at the end of the macro. + */ +#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ + do { \ + int reg = BPF_REG_9; \ + BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ + FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + reg, si->dst_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + reg, si->dst_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD), \ + reg, si->src_reg, \ + offsetof(OBJ, OBJ_FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } while (0) + +#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ + do { \ + if (TYPE == BPF_WRITE) \ + SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ + else \ + SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ + } while (0) + case offsetof(struct bpf_sock_ops, snd_cwnd): SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock); break;