From 57f0f512b273f60d52568b8c6b77e17f5636edc0 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Wed, 5 Aug 2015 17:04:01 -0300 Subject: Initial import --- net/sched/act_bpf.c | 362 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 362 insertions(+) create mode 100644 net/sched/act_bpf.c (limited to 'net/sched/act_bpf.c') diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c new file mode 100644 index 000000000..dc6a2d324 --- /dev/null +++ b/net/sched/act_bpf.c @@ -0,0 +1,362 @@ +/* + * Copyright (c) 2015 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include + +#define BPF_TAB_MASK 15 +#define ACT_BPF_NAME_LEN 256 + +struct tcf_bpf_cfg { + struct bpf_prog *filter; + struct sock_filter *bpf_ops; + char *bpf_name; + u32 bpf_fd; + u16 bpf_num_ops; +}; + +static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, + struct tcf_result *res) +{ + struct tcf_bpf *prog = act->priv; + int action, filter_res; + + if (unlikely(!skb_mac_header_was_set(skb))) + return TC_ACT_UNSPEC; + + spin_lock(&prog->tcf_lock); + + prog->tcf_tm.lastuse = jiffies; + bstats_update(&prog->tcf_bstats, skb); + + /* Needed here for accessing maps. */ + rcu_read_lock(); + filter_res = BPF_PROG_RUN(prog->filter, skb); + rcu_read_unlock(); + + /* A BPF program may overwrite the default action opcode. + * Similarly as in cls_bpf, if filter_res == -1 we use the + * default action specified from tc. + * + * In case a different well-known TC_ACT opcode has been + * returned, it will overwrite the default one. + * + * For everything else that is unkown, TC_ACT_UNSPEC is + * returned. + */ + switch (filter_res) { + case TC_ACT_PIPE: + case TC_ACT_RECLASSIFY: + case TC_ACT_OK: + action = filter_res; + break; + case TC_ACT_SHOT: + action = filter_res; + prog->tcf_qstats.drops++; + break; + case TC_ACT_UNSPEC: + action = prog->tcf_action; + break; + default: + action = TC_ACT_UNSPEC; + break; + } + + spin_unlock(&prog->tcf_lock); + return action; +} + +static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog) +{ + return !prog->bpf_ops; +} + +static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, + struct sk_buff *skb) +{ + struct nlattr *nla; + + if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops)) + return -EMSGSIZE; + + nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops * + sizeof(struct sock_filter)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + + return 0; +} + +static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, + struct sk_buff *skb) +{ + if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd)) + return -EMSGSIZE; + + if (prog->bpf_name && + nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) + return -EMSGSIZE; + + return 0; +} + +static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, + int bind, int ref) +{ + unsigned char *tp = skb_tail_pointer(skb); + struct tcf_bpf *prog = act->priv; + struct tc_act_bpf opt = { + .index = prog->tcf_index, + .refcnt = prog->tcf_refcnt - ref, + .bindcnt = prog->tcf_bindcnt - bind, + .action = prog->tcf_action, + }; + struct tcf_t tm; + int ret; + + if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (tcf_bpf_is_ebpf(prog)) + ret = tcf_bpf_dump_ebpf_info(prog, skb); + else + ret = tcf_bpf_dump_bpf_info(prog, skb); + if (ret) + goto nla_put_failure; + + tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install); + tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse); + tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires); + + if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm)) + goto nla_put_failure; + + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, tp); + return -1; +} + +static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { + [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, + [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, + [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, + [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, + [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, + .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, +}; + +static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) +{ + struct sock_filter *bpf_ops; + struct sock_fprog_kern fprog_tmp; + struct bpf_prog *fp; + u16 bpf_size, bpf_num_ops; + int ret; + + bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); + if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) + return -EINVAL; + + bpf_size = bpf_num_ops * sizeof(*bpf_ops); + if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS])) + return -EINVAL; + + bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + if (bpf_ops == NULL) + return -ENOMEM; + + memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size); + + fprog_tmp.len = bpf_num_ops; + fprog_tmp.filter = bpf_ops; + + ret = bpf_prog_create(&fp, &fprog_tmp); + if (ret < 0) { + kfree(bpf_ops); + return ret; + } + + cfg->bpf_ops = bpf_ops; + cfg->bpf_num_ops = bpf_num_ops; + cfg->filter = fp; + + return 0; +} + +static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) +{ + struct bpf_prog *fp; + char *name = NULL; + u32 bpf_fd; + + bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]); + + fp = bpf_prog_get(bpf_fd); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + if (fp->type != BPF_PROG_TYPE_SCHED_ACT) { + bpf_prog_put(fp); + return -EINVAL; + } + + if (tb[TCA_ACT_BPF_NAME]) { + name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]), + nla_len(tb[TCA_ACT_BPF_NAME]), + GFP_KERNEL); + if (!name) { + bpf_prog_put(fp); + return -ENOMEM; + } + } + + cfg->bpf_fd = bpf_fd; + cfg->bpf_name = name; + cfg->filter = fp; + + return 0; +} + +static int tcf_bpf_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *act, + int replace, int bind) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tc_act_bpf *parm; + struct tcf_bpf *prog; + struct tcf_bpf_cfg cfg; + bool is_bpf, is_ebpf; + int ret; + + if (!nla) + return -EINVAL; + + ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy); + if (ret < 0) + return ret; + + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; + is_ebpf = tb[TCA_ACT_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || + !tb[TCA_ACT_BPF_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_ACT_BPF_PARMS]); + + memset(&cfg, 0, sizeof(cfg)); + + ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : + tcf_bpf_init_from_efd(tb, &cfg); + if (ret < 0) + return ret; + + if (!tcf_hash_check(parm->index, act, bind)) { + ret = tcf_hash_create(parm->index, est, act, + sizeof(*prog), bind); + if (ret < 0) + goto destroy_fp; + + ret = ACT_P_CREATED; + } else { + /* Don't override defaults. */ + if (bind) + goto destroy_fp; + + tcf_hash_release(act, bind); + if (!replace) { + ret = -EEXIST; + goto destroy_fp; + } + } + + prog = to_bpf(act); + spin_lock_bh(&prog->tcf_lock); + + prog->bpf_ops = cfg.bpf_ops; + prog->bpf_name = cfg.bpf_name; + + if (cfg.bpf_num_ops) + prog->bpf_num_ops = cfg.bpf_num_ops; + if (cfg.bpf_fd) + prog->bpf_fd = cfg.bpf_fd; + + prog->tcf_action = parm->action; + prog->filter = cfg.filter; + + spin_unlock_bh(&prog->tcf_lock); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(act); + + return ret; + +destroy_fp: + if (is_ebpf) + bpf_prog_put(cfg.filter); + else + bpf_prog_destroy(cfg.filter); + + kfree(cfg.bpf_ops); + kfree(cfg.bpf_name); + + return ret; +} + +static void tcf_bpf_cleanup(struct tc_action *act, int bind) +{ + const struct tcf_bpf *prog = act->priv; + + if (tcf_bpf_is_ebpf(prog)) + bpf_prog_put(prog->filter); + else + bpf_prog_destroy(prog->filter); +} + +static struct tc_action_ops act_bpf_ops __read_mostly = { + .kind = "bpf", + .type = TCA_ACT_BPF, + .owner = THIS_MODULE, + .act = tcf_bpf, + .dump = tcf_bpf_dump, + .cleanup = tcf_bpf_cleanup, + .init = tcf_bpf_init, +}; + +static int __init bpf_init_module(void) +{ + return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK); +} + +static void __exit bpf_cleanup_module(void) +{ + tcf_unregister_action(&act_bpf_ops); +} + +module_init(bpf_init_module); +module_exit(bpf_cleanup_module); + +MODULE_AUTHOR("Jiri Pirko "); +MODULE_DESCRIPTION("TC BPF based action"); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3-54-g00ecf