From e6ac2450d6dee3121cd8bbf2907b78a68a8a353d Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 24 Mar 2021 18:51:42 -0700 Subject: bpf: Support bpf program calling kernel function This patch adds support to BPF verifier to allow bpf program calling kernel function directly. The use case included in this set is to allow bpf-tcp-cc to directly call some tcp-cc helper functions (e.g. "tcp_cong_avoid_ai()"). Those functions have already been used by some kernel tcp-cc implementations. This set will also allow the bpf-tcp-cc program to directly call the kernel tcp-cc implementation, For example, a bpf_dctcp may only want to implement its own dctcp_cwnd_event() and reuse other dctcp_*() directly from the kernel tcp_dctcp.c instead of reimplementing (or copy-and-pasting) them. The tcp-cc kernel functions mentioned above will be white listed for the struct_ops bpf-tcp-cc programs to use in a later patch. The white listed functions are not bounded to a fixed ABI contract. Those functions have already been used by the existing kernel tcp-cc. If any of them has changed, both in-tree and out-of-tree kernel tcp-cc implementations have to be changed. The same goes for the struct_ops bpf-tcp-cc programs which have to be adjusted accordingly. This patch is to make the required changes in the bpf verifier. First change is in btf.c, it adds a case in "btf_check_func_arg_match()". When the passed in "btf->kernel_btf == true", it means matching the verifier regs' states with a kernel function. This will handle the PTR_TO_BTF_ID reg. It also maps PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, and PTR_TO_TCP_SOCK to its kernel's btf_id. In the later libbpf patch, the insn calling a kernel function will look like: insn->code == (BPF_JMP | BPF_CALL) insn->src_reg == BPF_PSEUDO_KFUNC_CALL /* <- new in this patch */ insn->imm == func_btf_id /* btf_id of the running kernel */ [ For the future calling function-in-kernel-module support, an array of module btf_fds can be passed at the load time and insn->off can be used to index into this array. ] At the early stage of verifier, the verifier will collect all kernel function calls into "struct bpf_kfunc_desc". Those descriptors are stored in "prog->aux->kfunc_tab" and will be available to the JIT. Since this "add" operation is similar to the current "add_subprog()" and looking for the same insn->code, they are done together in the new "add_subprog_and_kfunc()". In the "do_check()" stage, the new "check_kfunc_call()" is added to verify the kernel function call instruction: 1. Ensure the kernel function can be used by a particular BPF_PROG_TYPE. A new bpf_verifier_ops "check_kfunc_call" is added to do that. The bpf-tcp-cc struct_ops program will implement this function in a later patch. 2. Call "btf_check_kfunc_args_match()" to ensure the regs can be used as the args of a kernel function. 3. Mark the regs' type, subreg_def, and zext_dst. At the later do_misc_fixups() stage, the new fixup_kfunc_call() will replace the insn->imm with the function address (relative to __bpf_call_base). If needed, the jit can find the btf_func_model by calling the new bpf_jit_find_kfunc_model(prog, insn). With the imm set to the function address, "bpftool prog dump xlated" will be able to display the kernel function calls the same way as it displays other bpf helper calls. gpl_compatible program is required to call kernel function. This feature currently requires JIT. The verifier selftests are adjusted because of the changes in the verbose log in add_subprog_and_kfunc(). Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210325015142.1544736-1-kafai@fb.com --- include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 008edc1dc8c1..598716742593 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1117,6 +1117,10 @@ enum bpf_link_type { * offset to another bpf function */ #define BPF_PSEUDO_CALL 1 +/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL, + * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel + */ +#define BPF_PSEUDO_KFUNC_CALL 2 /* flags for BPF_MAP_UPDATE_ELEM command */ enum { -- cgit v1.2.3 From a7ba4558e69a3c2ae4ca521f015832ef44799538 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 30 Mar 2021 19:32:30 -0700 Subject: sock_map: Introduce BPF_SK_SKB_VERDICT Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is confusing and more importantly we still want to distinguish them from user-space. So we can just reuse the stream verdict code but introduce a new type of eBPF program, skb_verdict. Users are not allowed to attach stream_verdict and skb_verdict programs to the same map. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210331023237.41094-10-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 2 ++ include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 1 + net/core/skmsg.c | 4 +++- net/core/sock_map.c | 28 ++++++++++++++++++++++++++++ tools/bpf/bpftool/common.c | 1 + tools/bpf/bpftool/prog.c | 1 + tools/include/uapi/linux/bpf.h | 1 + 8 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e7aba150539d..c83dbc2d81d9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,7 @@ struct sk_psock_progs { struct bpf_prog *msg_parser; struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; + struct bpf_prog *skb_verdict; }; enum sk_psock_state_bits { @@ -487,6 +488,7 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs) psock_set_prog(&progs->msg_parser, NULL); psock_set_prog(&progs->stream_parser, NULL); psock_set_prog(&progs->stream_verdict, NULL); + psock_set_prog(&progs->skb_verdict, NULL); } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 598716742593..49371eba98ba 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -957,6 +957,7 @@ enum bpf_attach_type { BPF_XDP_CPUMAP, BPF_SK_LOOKUP, BPF_XDP, + BPF_SK_SKB_VERDICT, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9603de81811a..6428634da57e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2948,6 +2948,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: + case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 656eceab73bc..a045812d7c78 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -697,7 +697,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) rcu_assign_sk_user_data(sk, NULL); if (psock->progs.stream_parser) sk_psock_stop_strp(sk, psock); - else if (psock->progs.stream_verdict) + else if (psock->progs.stream_verdict || psock->progs.skb_verdict) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); @@ -1024,6 +1024,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, } skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.stream_verdict); + if (!prog) + prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_dst_drop(skb); skb_bpf_redirect_clear(skb); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 42d797291d34..c2a0411e08a8 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -156,6 +156,8 @@ static void sock_map_del_link(struct sock *sk, strp_stop = true; if (psock->saved_data_ready && stab->progs.stream_verdict) verdict_stop = true; + if (psock->saved_data_ready && stab->progs.skb_verdict) + verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); } @@ -232,6 +234,7 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog *stream_verdict = NULL; struct bpf_prog *stream_parser = NULL; + struct bpf_prog *skb_verdict = NULL; struct bpf_prog *msg_parser = NULL; struct sk_psock *psock; int ret; @@ -268,6 +271,15 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) } } + skb_verdict = READ_ONCE(progs->skb_verdict); + if (skb_verdict) { + skb_verdict = bpf_prog_inc_not_zero(skb_verdict); + if (IS_ERR(skb_verdict)) { + ret = PTR_ERR(skb_verdict); + goto out_put_msg_parser; + } + } + no_progs: psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) { @@ -278,6 +290,9 @@ no_progs: if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || (stream_parser && READ_ONCE(psock->progs.stream_parser)) || + (skb_verdict && READ_ONCE(psock->progs.skb_verdict)) || + (skb_verdict && READ_ONCE(psock->progs.stream_verdict)) || + (stream_verdict && READ_ONCE(psock->progs.skb_verdict)) || (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; @@ -309,6 +324,9 @@ no_progs: } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { psock_set_prog(&psock->progs.stream_verdict, stream_verdict); sk_psock_start_verdict(sk,psock); + } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); return 0; @@ -317,6 +335,9 @@ out_unlock_drop: out_drop: sk_psock_put(sk, psock); out_progs: + if (skb_verdict) + bpf_prog_put(skb_verdict); +out_put_msg_parser: if (msg_parser) bpf_prog_put(msg_parser); out_put_stream_parser: @@ -1442,8 +1463,15 @@ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, break; #endif case BPF_SK_SKB_STREAM_VERDICT: + if (progs->skb_verdict) + return -EBUSY; pprog = &progs->stream_verdict; break; + case BPF_SK_SKB_VERDICT: + if (progs->stream_verdict) + return -EBUSY; + pprog = &progs->skb_verdict; + break; default: return -EOPNOTSUPP; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 65303664417e..1828bba19020 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -57,6 +57,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", [BPF_LIRC_MODE2] = "lirc_mode2", [BPF_FLOW_DISSECTOR] = "flow_dissector", diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f2b915b20546..3f067d2d7584 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -76,6 +76,7 @@ enum dump_mode { static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", + [BPF_SK_SKB_VERDICT] = "skb_verdict", [BPF_SK_MSG_VERDICT] = "msg_verdict", [BPF_FLOW_DISSECTOR] = "flow_dissector", [__MAX_BPF_ATTACH_TYPE] = NULL, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ab9f2233607c..69902603012c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -957,6 +957,7 @@ enum bpf_attach_type { BPF_XDP_CPUMAP, BPF_SK_LOOKUP, BPF_XDP, + BPF_SK_SKB_VERDICT, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3