diff options
Diffstat (limited to 'net/sched/cls_flower.c')
| -rw-r--r-- | net/sched/cls_flower.c | 923 |
1 files changed, 776 insertions, 147 deletions
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d32d4233d337..25bc57ee6ea1 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -16,20 +16,28 @@ #include <linux/in6.h> #include <linux/ip.h> #include <linux/mpls.h> +#include <linux/ppp_defs.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/ip.h> #include <net/flow_dissector.h> #include <net/geneve.h> #include <net/vxlan.h> #include <net/erspan.h> +#include <net/gtp.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> +#define TCA_FLOWER_KEY_CT_FLAGS_MAX \ + ((__TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) << 1) +#define TCA_FLOWER_KEY_CT_FLAGS_MASK \ + (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) + struct fl_flow_key { struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; @@ -56,14 +64,12 @@ struct fl_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; struct flow_dissector_key_enc_opts enc_opts; - union { - struct flow_dissector_key_ports tp; - struct { - struct flow_dissector_key_ports tp_min; - struct flow_dissector_key_ports tp_max; - }; - } tp_range; + struct flow_dissector_key_ports_range tp_range; struct flow_dissector_key_ct ct; + struct flow_dissector_key_hash hash; + struct flow_dissector_key_num_of_vlans num_of_vlans; + struct flow_dissector_key_pppoe pppoe; + struct flow_dissector_key_l2tpv3 l2tpv3; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -203,16 +209,16 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, struct fl_flow_key *key, struct fl_flow_key *mkey) { - __be16 min_mask, max_mask, min_val, max_val; + u16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_range.tp_min.dst); - max_mask = htons(filter->mask->key.tp_range.tp_max.dst); - min_val = htons(filter->key.tp_range.tp_min.dst); - max_val = htons(filter->key.tp_range.tp_max.dst); + min_mask = ntohs(filter->mask->key.tp_range.tp_min.dst); + max_mask = ntohs(filter->mask->key.tp_range.tp_max.dst); + min_val = ntohs(filter->key.tp_range.tp_min.dst); + max_val = ntohs(filter->key.tp_range.tp_max.dst); if (min_mask && max_mask) { - if (htons(key->tp_range.tp.dst) < min_val || - htons(key->tp_range.tp.dst) > max_val) + if (ntohs(key->tp_range.tp.dst) < min_val || + ntohs(key->tp_range.tp.dst) > max_val) return false; /* skb does not have min and max values */ @@ -226,16 +232,16 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, struct fl_flow_key *key, struct fl_flow_key *mkey) { - __be16 min_mask, max_mask, min_val, max_val; + u16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_range.tp_min.src); - max_mask = htons(filter->mask->key.tp_range.tp_max.src); - min_val = htons(filter->key.tp_range.tp_min.src); - max_val = htons(filter->key.tp_range.tp_max.src); + min_mask = ntohs(filter->mask->key.tp_range.tp_min.src); + max_mask = ntohs(filter->mask->key.tp_range.tp_max.src); + min_val = ntohs(filter->key.tp_range.tp_min.src); + max_val = ntohs(filter->key.tp_range.tp_max.src); if (min_mask && max_mask) { - if (htons(key->tp_range.tp.src) < min_val || - htons(key->tp_range.tp.src) > max_val) + if (ntohs(key->tp_range.tp.src) < min_val || + ntohs(key->tp_range.tp.src) > max_val) return false; /* skb does not have min and max values */ @@ -272,14 +278,16 @@ static struct cls_fl_filter *fl_lookup_range(struct fl_flow_mask *mask, return NULL; } -static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask, - struct fl_flow_key *mkey, - struct fl_flow_key *key) +static noinline_for_stack +struct cls_fl_filter *fl_mask_lookup(struct fl_flow_mask *mask, struct fl_flow_key *key) { + struct fl_flow_key mkey; + + fl_set_masked_key(&mkey, key, mask); if ((mask->flags & TCA_FLOWER_MASK_FLAGS_RANGE)) - return fl_lookup_range(mask, mkey, key); + return fl_lookup_range(mask, &mkey, key); - return __fl_lookup(mask, mkey); + return __fl_lookup(mask, &mkey); } static u16 fl_ct_info_to_flower_map[] = { @@ -288,9 +296,11 @@ static u16 fl_ct_info_to_flower_map[] = { [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_RELATED, [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED, + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_RELATED, + TCA_FLOWER_KEY_CT_FLAGS_RELATED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_NEW, }; @@ -299,7 +309,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_fl_head *head = rcu_dereference_bh(tp->root); - struct fl_flow_key skb_mkey; + bool post_ct = tc_skb_cb(skb)->post_ct; + u16 zone = tc_skb_cb(skb)->zone; struct fl_flow_key skb_key; struct fl_flow_mask *mask; struct cls_fl_filter *f; @@ -312,16 +323,17 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, - ARRAY_SIZE(fl_ct_info_to_flower_map)); - skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); - - fl_set_masked_key(&skb_mkey, &skb_key, mask); + ARRAY_SIZE(fl_ct_info_to_flower_map), + post_ct, zone); + skb_flow_dissect_hash(skb, &mask->dissector, &skb_key); + skb_flow_dissect(skb, &mask->dissector, &skb_key, + FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP); - f = fl_lookup(mask, &skb_mkey, &skb_key); + f = fl_mask_lookup(mask, &skb_key); if (f && !tc_skip_sw(f->flags)) { *res = f->res; return tcf_exts_exec(skb, &f->exts, res); @@ -450,20 +462,17 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.rule->match.key = &f->mkey; cls_flower.classid = f->res.classid; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, - rtnl_held); + err = tc_setup_offload_action(&cls_flower.rule->action, &f->exts, + cls_flower.common.extack); if (err) { kfree(cls_flower.rule); - if (skip_sw) { - NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); - return err; - } - return 0; + + return skip_sw ? err : 0; } err = tc_setup_cb_add(block, tp, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw, &f->flags, &f->in_hw_count, rtnl_held); - tc_cleanup_flow_action(&cls_flower.rule->action); + tc_cleanup_offload_action(&cls_flower.rule->action); kfree(cls_flower.rule); if (err) { @@ -491,9 +500,12 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, rtnl_held); - tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, - cls_flower.stats.pkts, - cls_flower.stats.lastused); + tcf_exts_hw_stats_update(&f->exts, cls_flower.stats.bytes, + cls_flower.stats.pkts, + cls_flower.stats.drops, + cls_flower.stats.lastused, + cls_flower.stats.used_hw_stats, + cls_flower.stats.used_hw_stats_valid); } static void __fl_put(struct cls_fl_filter *f) @@ -667,6 +679,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_BOS] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_TC] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_LABEL] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_MPLS_OPTS] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_TCP_FLAGS] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_TCP_FLAGS_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_IP_TOS] = { .type = NLA_U8 }, @@ -682,8 +695,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED }, - [TCA_FLOWER_KEY_CT_STATE] = { .type = NLA_U16 }, - [TCA_FLOWER_KEY_CT_STATE_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_CT_STATE] = + NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK), + [TCA_FLOWER_KEY_CT_STATE_MASK] = + NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK), [TCA_FLOWER_KEY_CT_ZONE] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_CT_ZONE_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_CT_MARK] = { .type = NLA_U32 }, @@ -693,6 +708,13 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, [TCA_FLOWER_FLAGS] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_HASH] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_HASH_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_NUM_OF_VLANS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 }, + }; static const struct nla_policy @@ -702,6 +724,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -725,6 +748,21 @@ erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, }; +static const struct nla_policy +gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_GTP_QFI] = { .type = NLA_U8 }, +}; + +static const struct nla_policy +mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { + [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_TC] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 }, +}; + static void fl_set_key_val(struct nlattr **tb, void *val, int val_type, void *mask, int mask_type, int len) @@ -739,7 +777,8 @@ static void fl_set_key_val(struct nlattr **tb, } static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, - struct fl_flow_key *mask) + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) { fl_set_key_val(tb, &key->tp_range.tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst, @@ -754,48 +793,219 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); - if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && - htons(key->tp_range.tp_max.dst) <= - htons(key->tp_range.tp_min.dst)) || - (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && - htons(key->tp_range.tp_max.src) <= - htons(key->tp_range.tp_min.src))) + if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && + ntohs(key->tp_range.tp_max.dst) <= + ntohs(key->tp_range.tp_min.dst)) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_PORT_DST_MIN], + "Invalid destination port range (min must be strictly smaller than max)"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && + ntohs(key->tp_range.tp_max.src) <= + ntohs(key->tp_range.tp_min.src)) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_PORT_SRC_MIN], + "Invalid source port range (min must be strictly smaller than max)"); return -EINVAL; + } + + return 0; +} + +static int fl_set_key_mpls_lse(const struct nlattr *nla_lse, + struct flow_dissector_key_mpls *key_val, + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1]; + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_val; + u8 lse_index; + u8 depth; + int err; + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX, nla_lse, + mpls_stack_entry_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]) { + NL_SET_ERR_MSG(extack, "Missing MPLS option \"depth\""); + return -EINVAL; + } + + depth = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]); + + /* LSE depth starts at 1, for consistency with terminology used by + * RFC 3031 (section 3.9), where depth 0 refers to unlabeled packets. + */ + if (depth < 1 || depth > FLOW_DIS_MPLS_MAX) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH], + "Invalid MPLS depth"); + return -EINVAL; + } + lse_index = depth - 1; + + dissector_set_mpls_lse(key_val, lse_index); + dissector_set_mpls_lse(key_mask, lse_index); + + lse_val = &key_val->ls[lse_index]; + lse_mask = &key_mask->ls[lse_index]; + + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]) { + lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]); + lse_mask->mpls_ttl = MPLS_TTL_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]) { + u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]); + + if (bos & ~MPLS_BOS_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS], + "Bottom Of Stack (BOS) must be 0 or 1"); + return -EINVAL; + } + lse_val->mpls_bos = bos; + lse_mask->mpls_bos = MPLS_BOS_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]) { + u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]); + + if (tc & ~MPLS_TC_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC], + "Traffic Class (TC) must be between 0 and 7"); + return -EINVAL; + } + lse_val->mpls_tc = tc; + lse_mask->mpls_tc = MPLS_TC_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]) { + u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]); + + if (label & ~MPLS_LABEL_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL], + "Label must be between 0 and 1048575"); + return -EINVAL; + } + lse_val->mpls_label = label; + lse_mask->mpls_label = MPLS_LABEL_MASK; + } + + return 0; +} + +static int fl_set_key_mpls_opts(const struct nlattr *nla_mpls_opts, + struct flow_dissector_key_mpls *key_val, + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *nla_lse; + int rem; + int err; + + if (!(nla_mpls_opts->nla_type & NLA_F_NESTED)) { + NL_SET_ERR_MSG_ATTR(extack, nla_mpls_opts, + "NLA_F_NESTED is missing"); + return -EINVAL; + } + + nla_for_each_nested(nla_lse, nla_mpls_opts, rem) { + if (nla_type(nla_lse) != TCA_FLOWER_KEY_MPLS_OPTS_LSE) { + NL_SET_ERR_MSG_ATTR(extack, nla_lse, + "Invalid MPLS option type"); + return -EINVAL; + } + + err = fl_set_key_mpls_lse(nla_lse, key_val, key_mask, extack); + if (err < 0) + return err; + } + if (rem) { + NL_SET_ERR_MSG(extack, + "Bytes leftover after parsing MPLS options"); + return -EINVAL; + } return 0; } static int fl_set_key_mpls(struct nlattr **tb, struct flow_dissector_key_mpls *key_val, - struct flow_dissector_key_mpls *key_mask) -{ + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_val; + + if (tb[TCA_FLOWER_KEY_MPLS_OPTS]) { + if (tb[TCA_FLOWER_KEY_MPLS_TTL] || + tb[TCA_FLOWER_KEY_MPLS_BOS] || + tb[TCA_FLOWER_KEY_MPLS_TC] || + tb[TCA_FLOWER_KEY_MPLS_LABEL]) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPTS], + "MPLS label, Traffic Class, Bottom Of Stack and Time To Live must be encapsulated in the MPLS options attribute"); + return -EBADMSG; + } + + return fl_set_key_mpls_opts(tb[TCA_FLOWER_KEY_MPLS_OPTS], + key_val, key_mask, extack); + } + + lse_val = &key_val->ls[0]; + lse_mask = &key_mask->ls[0]; + if (tb[TCA_FLOWER_KEY_MPLS_TTL]) { - key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]); - key_mask->mpls_ttl = MPLS_TTL_MASK; + lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]); + lse_mask->mpls_ttl = MPLS_TTL_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } if (tb[TCA_FLOWER_KEY_MPLS_BOS]) { u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]); - if (bos & ~MPLS_BOS_MASK) + if (bos & ~MPLS_BOS_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_BOS], + "Bottom Of Stack (BOS) must be 0 or 1"); return -EINVAL; - key_val->mpls_bos = bos; - key_mask->mpls_bos = MPLS_BOS_MASK; + } + lse_val->mpls_bos = bos; + lse_mask->mpls_bos = MPLS_BOS_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } if (tb[TCA_FLOWER_KEY_MPLS_TC]) { u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]); - if (tc & ~MPLS_TC_MASK) + if (tc & ~MPLS_TC_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_TC], + "Traffic Class (TC) must be between 0 and 7"); return -EINVAL; - key_val->mpls_tc = tc; - key_mask->mpls_tc = MPLS_TC_MASK; + } + lse_val->mpls_tc = tc; + lse_mask->mpls_tc = MPLS_TC_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) { u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]); - if (label & ~MPLS_LABEL_MASK) + if (label & ~MPLS_LABEL_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_LABEL], + "Label must be between 0 and 1048575"); return -EINVAL; - key_val->mpls_label = label; - key_mask->mpls_label = MPLS_LABEL_MASK; + } + lse_val->mpls_label = label; + lse_mask->mpls_label = MPLS_LABEL_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } return 0; } @@ -803,6 +1013,7 @@ static int fl_set_key_mpls(struct nlattr **tb, static void fl_set_key_vlan(struct nlattr **tb, __be16 ethertype, int vlan_id_key, int vlan_prio_key, + int vlan_next_eth_type_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { @@ -819,8 +1030,59 @@ static void fl_set_key_vlan(struct nlattr **tb, VLAN_PRIORITY_MASK; key_mask->vlan_priority = VLAN_PRIORITY_MASK; } - key_val->vlan_tpid = ethertype; - key_mask->vlan_tpid = cpu_to_be16(~0); + if (ethertype) { + key_val->vlan_tpid = ethertype; + key_mask->vlan_tpid = cpu_to_be16(~0); + } + if (tb[vlan_next_eth_type_key]) { + key_val->vlan_eth_type = + nla_get_be16(tb[vlan_next_eth_type_key]); + key_mask->vlan_eth_type = cpu_to_be16(~0); + } +} + +static void fl_set_key_pppoe(struct nlattr **tb, + struct flow_dissector_key_pppoe *key_val, + struct flow_dissector_key_pppoe *key_mask, + struct fl_flow_key *key, + struct fl_flow_key *mask) +{ + /* key_val::type must be set to ETH_P_PPP_SES + * because ETH_P_PPP_SES was stored in basic.n_proto + * which might get overwritten by ppp_proto + * or might be set to 0, the role of key_val::type + * is simmilar to vlan_key::tpid + */ + key_val->type = htons(ETH_P_PPP_SES); + key_mask->type = cpu_to_be16(~0); + + if (tb[TCA_FLOWER_KEY_PPPOE_SID]) { + key_val->session_id = + nla_get_be16(tb[TCA_FLOWER_KEY_PPPOE_SID]); + key_mask->session_id = cpu_to_be16(~0); + } + if (tb[TCA_FLOWER_KEY_PPP_PROTO]) { + key_val->ppp_proto = + nla_get_be16(tb[TCA_FLOWER_KEY_PPP_PROTO]); + key_mask->ppp_proto = cpu_to_be16(~0); + + if (key_val->ppp_proto == htons(PPP_IP)) { + key->basic.n_proto = htons(ETH_P_IP); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_IPV6)) { + key->basic.n_proto = htons(ETH_P_IPV6); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_MPLS_UC)) { + key->basic.n_proto = htons(ETH_P_MPLS_UC); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_MPLS_MC)) { + key->basic.n_proto = htons(ETH_P_MPLS_MC); + mask->basic.n_proto = cpu_to_be16(~0); + } + } else { + key->basic.n_proto = 0; + mask->basic.n_proto = cpu_to_be16(0); + } } static void fl_set_key_flag(u32 flower_key, u32 flower_mask, @@ -834,17 +1096,19 @@ static void fl_set_key_flag(u32 flower_key, u32 flower_mask, } } -static int fl_set_key_flags(struct nlattr **tb, - u32 *flags_key, u32 *flags_mask) +static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key, + u32 *flags_mask, struct netlink_ext_ack *extack) { u32 key, mask; /* mask is mandatory for flags */ - if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) + if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) { + NL_SET_ERR_MSG(extack, "Missing flags mask"); return -EINVAL; + } - key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS])); - mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); + key = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS])); + mask = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); *flags_key = 0; *flags_mask = 0; @@ -985,8 +1249,10 @@ static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key, return -EINVAL; } - if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) + if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; + } return sizeof(*md); } @@ -1031,6 +1297,7 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, } if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]; + memset(&md->u, 0x00, sizeof(md->u)); md->u.index = nla_get_be32(nla); } } else if (md->version == 2) { @@ -1055,6 +1322,49 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, return sizeof(*md); } +static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1]; + struct gtp_pdu_session_info *sinfo; + u8 len = key->enc_opts.len; + int err; + + sinfo = (struct gtp_pdu_session_info *)&key->enc_opts.data[len]; + memset(sinfo, 0xff, option_len); + + if (!depth) + return sizeof(*sinfo); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GTP) { + NL_SET_ERR_MSG_MOD(extack, "Non-gtp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GTP_MAX, nla, + gtp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && + (!tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI])) { + NL_SET_ERR_MSG_MOD(extack, + "Missing tunnel key gtp option pdu type or qfi"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]) + sinfo->pdu_type = + nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]) + sinfo->qfi = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]); + + return sizeof(*sinfo); +} + static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1079,6 +1389,10 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); + if (!nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "Invalid nested attribute for masks"); + return -EINVAL; + } } nla_for_each_attr(nla_opt_key, nla_enc_key, @@ -1114,9 +1428,6 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); return -EINVAL; } - - if (msk_depth) - nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); break; case TCA_FLOWER_KEY_ENC_OPTS_VXLAN: if (key->enc_opts.dst_opt_type) { @@ -1147,9 +1458,6 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); return -EINVAL; } - - if (msk_depth) - nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); break; case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN: if (key->enc_opts.dst_opt_type) { @@ -1180,14 +1488,86 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); return -EINVAL; } + break; + case TCA_FLOWER_KEY_ENC_OPTS_GTP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, + "Duplicate type for gtp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + option_len = fl_set_gtp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; - if (msk_depth) - nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + option_len = fl_set_gtp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, + "Key and mask miss aligned"); + return -EINVAL; + } break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); return -EINVAL; } + + if (!msk_depth) + continue; + + if (!nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "A mask attribute is invalid"); + return -EINVAL; + } + nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + } + + return 0; +} + +static int fl_validate_ct_state(u16 state, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + if (state && !(state & TCA_FLOWER_KEY_CT_FLAGS_TRACKED)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "no trk, so no other flag can be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and est are mutually exclusive"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_INVALID && + state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "when inv is set, only trk may be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_REPLY) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and rpl are mutually exclusive"); + return -EINVAL; } return 0; @@ -1199,6 +1579,8 @@ static int fl_set_key_ct(struct nlattr **tb, struct netlink_ext_ack *extack) { if (tb[TCA_FLOWER_KEY_CT_STATE]) { + int err; + if (!IS_ENABLED(CONFIG_NF_CONNTRACK)) { NL_SET_ERR_MSG(extack, "Conntrack isn't enabled"); return -EOPNOTSUPP; @@ -1206,6 +1588,13 @@ static int fl_set_key_ct(struct nlattr **tb, fl_set_key_val(tb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE, &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK, sizeof(key->ct_state)); + + err = fl_validate_ct_state(key->ct_state & mask->ct_state, + tb[TCA_FLOWER_KEY_CT_STATE_MASK], + extack); + if (err) + return err; + } if (tb[TCA_FLOWER_KEY_CT_ZONE]) { if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) { @@ -1238,6 +1627,26 @@ static int fl_set_key_ct(struct nlattr **tb, return 0; } +static bool is_vlan_key(struct nlattr *tb, __be16 *ethertype, + struct fl_flow_key *key, struct fl_flow_key *mask, + int vthresh) +{ + const bool good_num_of_vlans = key->num_of_vlans.num_of_vlans > vthresh; + + if (!tb) { + *ethertype = 0; + return good_num_of_vlans; + } + + *ethertype = nla_get_be16(tb); + if (good_num_of_vlans || eth_type_vlan(*ethertype)) + return true; + + key->basic.n_proto = *ethertype; + mask->basic.n_proto = cpu_to_be16(~0); + return false; +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1259,38 +1668,36 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); - - if (tb[TCA_FLOWER_KEY_ETH_TYPE]) { - ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]); - - if (eth_type_vlan(ethertype)) { - fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, - TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, - &mask->vlan); - - if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) { - ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]); - if (eth_type_vlan(ethertype)) { - fl_set_key_vlan(tb, ethertype, - TCA_FLOWER_KEY_CVLAN_ID, - TCA_FLOWER_KEY_CVLAN_PRIO, - &key->cvlan, &mask->cvlan); - fl_set_key_val(tb, &key->basic.n_proto, - TCA_FLOWER_KEY_CVLAN_ETH_TYPE, - &mask->basic.n_proto, - TCA_FLOWER_UNSPEC, - sizeof(key->basic.n_proto)); - } else { - key->basic.n_proto = ethertype; - mask->basic.n_proto = cpu_to_be16(~0); - } - } - } else { - key->basic.n_proto = ethertype; - mask->basic.n_proto = cpu_to_be16(~0); + fl_set_key_val(tb, &key->num_of_vlans, + TCA_FLOWER_KEY_NUM_OF_VLANS, + &mask->num_of_vlans, + TCA_FLOWER_UNSPEC, + sizeof(key->num_of_vlans)); + + if (is_vlan_key(tb[TCA_FLOWER_KEY_ETH_TYPE], ðertype, key, mask, 0)) { + fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &key->vlan, &mask->vlan); + + if (is_vlan_key(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE], + ðertype, key, mask, 1)) { + fl_set_key_vlan(tb, ethertype, + TCA_FLOWER_KEY_CVLAN_ID, + TCA_FLOWER_KEY_CVLAN_PRIO, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + &key->cvlan, &mask->cvlan); + fl_set_key_val(tb, &key->basic.n_proto, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + &mask->basic.n_proto, + TCA_FLOWER_UNSPEC, + sizeof(key->basic.n_proto)); } } + if (key->basic.n_proto == htons(ETH_P_PPP_SES)) + fl_set_key_pppoe(tb, &key->pppoe, &mask->pppoe, key, mask); + if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, @@ -1365,7 +1772,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, sizeof(key->icmp.code)); } else if (key->basic.n_proto == htons(ETH_P_MPLS_UC) || key->basic.n_proto == htons(ETH_P_MPLS_MC)) { - ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls); + ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls, extack); if (ret) return ret; } else if (key->basic.n_proto == htons(ETH_P_ARP) || @@ -1385,12 +1792,17 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA, mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK, sizeof(key->arp.tha)); + } else if (key->basic.ip_proto == IPPROTO_L2TP) { + fl_set_key_val(tb, &key->l2tpv3.session_id, + TCA_FLOWER_KEY_L2TPV3_SID, + &mask->l2tpv3.session_id, TCA_FLOWER_UNSPEC, + sizeof(key->l2tpv3.session_id)); } if (key->basic.ip_proto == IPPROTO_TCP || key->basic.ip_proto == IPPROTO_UDP || key->basic.ip_proto == IPPROTO_SCTP) { - ret = fl_set_key_port_range(tb, key, mask); + ret = fl_set_key_port_range(tb, key, mask, extack); if (ret) return ret; } @@ -1441,6 +1853,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip); + fl_set_key_val(tb, &key->hash.hash, TCA_FLOWER_KEY_HASH, + &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK, + sizeof(key->hash.hash)); + if (tb[TCA_FLOWER_KEY_ENC_OPTS]) { ret = fl_set_enc_opt(tb, key, mask, extack); if (ret) @@ -1452,7 +1868,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb, return ret; if (tb[TCA_FLOWER_KEY_FLAGS]) - ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags); + ret = fl_set_key_flags(tb, &key->control.flags, + &mask->control.flags, extack); return ret; } @@ -1554,6 +1971,14 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_CT, ct); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_HASH, hash); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_NUM_OF_VLANS, num_of_vlans); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PPPOE, pppoe); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3); skb_flow_dissector_init(dissector, keys, cnt); } @@ -1657,23 +2082,24 @@ errout_cleanup: static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct cls_fl_filter *f, struct fl_flow_mask *mask, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr, - struct fl_flow_tmplt *tmplt, bool rtnl_held, + struct nlattr *est, + struct fl_flow_tmplt *tmplt, + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, rtnl_held, - extack); + err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags, + fl_flags, extack); if (err < 0) return err; if (tb[TCA_FLOWER_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - if (!rtnl_held) + if (flags & TCA_ACT_FLAGS_NO_RTNL) rtnl_lock(); tcf_bind_filter(tp, &f->res, base); - if (!rtnl_held) + if (flags & TCA_ACT_FLAGS_NO_RTNL) rtnl_unlock(); } @@ -1717,10 +2143,11 @@ static int fl_ht_insert_unique(struct cls_fl_filter *fnew, static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct cls_fl_head *head = fl_head_dereference(tp); + bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); struct cls_fl_filter *fold = *arg; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; @@ -1776,8 +2203,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } } - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, - tp->chain->tmplt_priv, rtnl_held, extack); + err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], + tp->chain->tmplt_priv, flags, fnew->flags, + extack); if (err) goto errout; @@ -1930,18 +2358,24 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, arg->count = arg->skip; + rcu_read_lock(); idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { /* don't return filters that are being deleted */ if (!refcount_inc_not_zero(&f->refcnt)) continue; + rcu_read_unlock(); + if (arg->fn(tp, f, arg) < 0) { __fl_put(f); arg->stop = 1; + rcu_read_lock(); break; } __fl_put(f); arg->count++; + rcu_read_lock(); } + rcu_read_unlock(); arg->cookie = id; } @@ -2001,12 +2435,11 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, cls_flower.rule->match.mask = &f->mask->key; cls_flower.rule->match.key = &f->mkey; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, - true); + err = tc_setup_offload_action(&cls_flower.rule->action, &f->exts, + cls_flower.common.extack); if (err) { kfree(cls_flower.rule); if (tc_skip_sw(f->flags)) { - NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); __fl_put(f); return err; } @@ -2019,7 +2452,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, TC_SETUP_CLSFLOWER, &cls_flower, cb_priv, &f->flags, &f->in_hw_count); - tc_cleanup_flow_action(&cls_flower.rule->action); + tc_cleanup_offload_action(&cls_flower.rule->action); kfree(cls_flower.rule); if (err) { @@ -2192,35 +2625,132 @@ static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, return 0; } +static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb, + struct flow_dissector_key_mpls *mpls_key, + struct flow_dissector_key_mpls *mpls_mask, + u8 lse_index) +{ + struct flow_dissector_mpls_lse *lse_mask = &mpls_mask->ls[lse_index]; + struct flow_dissector_mpls_lse *lse_key = &mpls_key->ls[lse_index]; + int err; + + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH, + lse_index + 1); + if (err) + return err; + + if (lse_mask->mpls_ttl) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL, + lse_key->mpls_ttl); + if (err) + return err; + } + if (lse_mask->mpls_bos) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS, + lse_key->mpls_bos); + if (err) + return err; + } + if (lse_mask->mpls_tc) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TC, + lse_key->mpls_tc); + if (err) + return err; + } + if (lse_mask->mpls_label) { + err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + lse_key->mpls_label); + if (err) + return err; + } + + return 0; +} + +static int fl_dump_key_mpls_opts(struct sk_buff *skb, + struct flow_dissector_key_mpls *mpls_key, + struct flow_dissector_key_mpls *mpls_mask) +{ + struct nlattr *opts; + struct nlattr *lse; + u8 lse_index; + int err; + + opts = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS); + if (!opts) + return -EMSGSIZE; + + for (lse_index = 0; lse_index < FLOW_DIS_MPLS_MAX; lse_index++) { + if (!(mpls_mask->used_lses & 1 << lse_index)) + continue; + + lse = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS_LSE); + if (!lse) { + err = -EMSGSIZE; + goto err_opts; + } + + err = fl_dump_key_mpls_opt_lse(skb, mpls_key, mpls_mask, + lse_index); + if (err) + goto err_opts_lse; + nla_nest_end(skb, lse); + } + nla_nest_end(skb, opts); + + return 0; + +err_opts_lse: + nla_nest_cancel(skb, lse); +err_opts: + nla_nest_cancel(skb, opts); + + return err; +} + static int fl_dump_key_mpls(struct sk_buff *skb, struct flow_dissector_key_mpls *mpls_key, struct flow_dissector_key_mpls *mpls_mask) { + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_key; int err; - if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask))) + if (!mpls_mask->used_lses) return 0; - if (mpls_mask->mpls_ttl) { + + lse_mask = &mpls_mask->ls[0]; + lse_key = &mpls_key->ls[0]; + + /* For backward compatibility, don't use the MPLS nested attributes if + * the rule can be expressed using the old attributes. + */ + if (mpls_mask->used_lses & ~1 || + (!lse_mask->mpls_ttl && !lse_mask->mpls_bos && + !lse_mask->mpls_tc && !lse_mask->mpls_label)) + return fl_dump_key_mpls_opts(skb, mpls_key, mpls_mask); + + if (lse_mask->mpls_ttl) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL, - mpls_key->mpls_ttl); + lse_key->mpls_ttl); if (err) return err; } - if (mpls_mask->mpls_tc) { + if (lse_mask->mpls_tc) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TC, - mpls_key->mpls_tc); + lse_key->mpls_tc); if (err) return err; } - if (mpls_mask->mpls_label) { + if (lse_mask->mpls_label) { err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_LABEL, - mpls_key->mpls_label); + lse_key->mpls_label); if (err) return err; } - if (mpls_mask->mpls_bos) { + if (lse_mask->mpls_bos) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_BOS, - mpls_key->mpls_bos); + lse_key->mpls_bos); if (err) return err; } @@ -2395,6 +2925,34 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_gtp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) + +{ + struct gtp_pdu_session_info *session_info; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GTP); + if (!nest) + goto nla_put_failure; + + session_info = (struct gtp_pdu_session_info *)&enc_opts->data[0]; + + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE, + session_info->pdu_type)) + goto nla_put_failure; + + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, session_info->qfi)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int fl_dump_key_ct(struct sk_buff *skb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask) @@ -2458,6 +3016,11 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, if (err) goto nla_put_failure; break; + case TUNNEL_GTP_OPT: + err = fl_dump_key_gtp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; default: goto nla_put_failure; } @@ -2504,6 +3067,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, sizeof(key->basic.n_proto))) goto nla_put_failure; + if (mask->num_of_vlans.num_of_vlans) { + if (nla_put_u8(skb, TCA_FLOWER_KEY_NUM_OF_VLANS, key->num_of_vlans.num_of_vlans)) + goto nla_put_failure; + } + if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls)) goto nla_put_failure; @@ -2520,13 +3088,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (mask->basic.n_proto) { - if (mask->cvlan.vlan_tpid) { + if (mask->cvlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, key->basic.n_proto)) goto nla_put_failure; - } else if (mask->vlan.vlan_tpid) { + } else if (mask->vlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, - key->basic.n_proto)) + key->vlan.vlan_eth_type)) goto nla_put_failure; } } @@ -2539,6 +3107,17 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, fl_dump_key_ip(skb, false, &key->ip, &mask->ip))) goto nla_put_failure; + if (mask->pppoe.session_id) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_PPPOE_SID, + key->pppoe.session_id)) + goto nla_put_failure; + } + if (mask->basic.n_proto && mask->pppoe.ppp_proto) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_PPP_PROTO, + key->pppoe.ppp_proto)) + goto nla_put_failure; + } + if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, @@ -2626,6 +3205,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK, sizeof(key->arp.tha)))) goto nla_put_failure; + else if (key->basic.ip_proto == IPPROTO_L2TP && + fl_dump_key_val(skb, &key->l2tpv3.session_id, + TCA_FLOWER_KEY_L2TPV3_SID, + &mask->l2tpv3.session_id, + TCA_FLOWER_UNSPEC, + sizeof(key->l2tpv3.session_id))) + goto nla_put_failure; if ((key->basic.ip_proto == IPPROTO_TCP || key->basic.ip_proto == IPPROTO_UDP || @@ -2678,6 +3264,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) goto nla_put_failure; + if (fl_dump_key_val(skb, &key->hash.hash, TCA_FLOWER_KEY_HASH, + &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK, + sizeof(key->hash.hash))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -2742,6 +3333,48 @@ nla_put_failure: return -1; } +static int fl_terse_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) +{ + struct cls_fl_filter *f = fh; + struct nlattr *nest; + bool skip_hw; + + if (!f) + return skb->len; + + t->tcm_handle = f->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + spin_lock(&tp->lock); + + skip_hw = tc_skip_hw(f->flags); + + if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) + goto nla_put_failure_locked; + + spin_unlock(&tp->lock); + + if (!skip_hw) + fl_hw_update_stats(tp, f, rtnl_held); + + if (tcf_exts_terse_dump(skb, &f->exts)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + return skb->len; + +nla_put_failure_locked: + spin_unlock(&tp->lock); +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv) { struct fl_flow_tmplt *tmplt = tmplt_priv; @@ -2772,12 +3405,7 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q, { struct cls_fl_filter *f = fh; - if (f && f->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &f->res, base); - else - __tcf_unbind_filter(q, &f->res); - } + tc_cls_bind_class(classid, cl, q, &f->res, base); } static bool fl_delete_empty(struct tcf_proto *tp) @@ -2806,6 +3434,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .hw_add = fl_hw_add, .hw_del = fl_hw_del, .dump = fl_dump, + .terse_dump = fl_terse_dump, .bind_class = fl_bind_class, .tmplt_create = fl_tmplt_create, .tmplt_destroy = fl_tmplt_destroy, |