diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf-cgroup.h | 25 | ||||
| -rw-r--r-- | include/linux/filter.h | 4 | ||||
| -rw-r--r-- | include/net/tcp.h | 49 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 300 |
4 files changed, 377 insertions, 1 deletions
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 64f367044e25..2f98d2fce62e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) +/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a + * fullsock and its parent fullsock cannot be traced by + * sk_to_full_sk(). + * + * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. + * Its listener-sk is not attached to the rsk_listener. + * In this case, the caller holds the listener-sk (unlocked), + * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with + * the listener-sk such that the cgroup-bpf-progs of the + * listener-sk will be run. + * + * Regardless of syncookie mode or not, + * calling bpf_setsockopt on listener-sk will not make sense anyway, + * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. + */ +#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + __ret; \ +}) + #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ diff --git a/include/linux/filter.h b/include/linux/filter.h index c427dfa5f908..995625950cc1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1241,8 +1241,12 @@ struct bpf_sock_ops_kern { u32 reply; u32 replylong[4]; }; + struct sk_buff *syn_skb; + struct sk_buff *skb; + void *skb_data_end; u8 op; u8 is_fullsock; + u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that diff --git a/include/net/tcp.h b/include/net/tcp.h index 3e768a6b8264..1f967b4e22f6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2235,6 +2235,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#ifdef CONFIG_CGROUP_BPF +/* Copy the listen sk's HDR_OPT_CB flags to its child. + * + * During 3-Way-HandShake, the synack is usually sent from + * the listen sk with the HDR_OPT_CB flags set so that + * bpf-prog will be called to write the BPF hdr option. + * + * In fastopen, the child sk is used to send synack instead + * of the listen sk. Thus, inheriting the HDR_OPT_CB flags + * from the listen sk gives the bpf-prog a chance to write + * BPF hdr option in the synack pkt during fastopen. + * + * Both fastopen and non-fastopen child will inherit the + * HDR_OPT_CB flags to keep the bpf-prog having a consistent + * behavior when deciding to clear this cb flags (or not) + * during the PASSIVE_ESTABLISHED_CB. + * + * In the future, other cb flags could be inherited here also. + */ +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ + tcp_sk(child)->bpf_sock_ops_cb_flags = + tcp_sk(sk)->bpf_sock_ops_cb_flags & + (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ + skops->skb = skb; + skops->skb_data_end = skb->data + end_offset; +} +#else +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ +} +#endif + /* 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 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 18d0e128bc3c..f67ec5d9e57d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3395,6 +3395,120 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (BPF_PROG_TYPE_SOCK_OPS). + * + * If *flags* is 0, it will search the option from the + * sock_ops->skb_data. The comment in "struct bpf_sock_ops" + * has details on what skb_data contains under different + * sock_ops->op. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the searchby_res should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * >0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. + * + * **-EINVAL** If param is invalid + * + * **-ENOMSG** The option is not found + * + * **-ENOENT** No syn packet available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used + * + * **-ENOSPC** Not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** Cannot parse the header options in the packet + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid + * + * **-ENOSPC** Not enough space in the header. + * Nothing has been written + * + * **-EEXIST** The option has already existed + * + * **-EFAULT** Cannot parse the existing header options + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by bpf_store_hdr_opt() later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * If bpf_reserve_hdr_opt() is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * BPF_SOCK_OPS_HDR_OPT_LEN_CB. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if param is invalid + * + * **-ENOSPC** Not enough space in the header. + * + * **-EPERM** This helper cannot be used under the + * current sock_ops->op. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3653,9 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4165,6 +4282,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4173,8 +4320,48 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), - BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, @@ -4233,6 +4420,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4262,6 +4506,60 @@ enum { TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { |