diff options
34 files changed, 402 insertions, 348 deletions
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 5f896fcc074d..efbbfa770d66 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -92,6 +92,7 @@ enum nf_hook_ops_type { NF_HOOK_OP_UNDEFINED, NF_HOOK_OP_NF_TABLES, NF_HOOK_OP_BPF, + NF_HOOK_OP_NFT_FT, }; struct nf_hook_ops { diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index f39f688d7285..77c778d84d4c 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -51,21 +51,11 @@ static inline struct net_device *xt_in(const struct xt_action_param *par) return par->state->in; } -static inline const char *xt_inname(const struct xt_action_param *par) -{ - return par->state->in->name; -} - static inline struct net_device *xt_out(const struct xt_action_param *par) { return par->state->out; } -static inline const char *xt_outname(const struct xt_action_param *par) -{ - return par->state->out->name; -} - static inline unsigned int xt_hooknum(const struct xt_action_param *par) { return par->state->hook; diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index e55eedc84ed7..00506792a06d 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -59,6 +59,9 @@ extern int sysctl_nf_log_all_netns; int nf_log_register(u_int8_t pf, struct nf_logger *logger); void nf_log_unregister(struct nf_logger *logger); +/* Check if any logger is registered for a given protocol family. */ +bool nf_log_is_registered(u_int8_t pf); + int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger); void nf_log_unset(struct net *net, const struct nf_logger *logger); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5e49619ae49c..891e43a01bdc 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -459,19 +459,13 @@ struct nft_set_ext; * control plane functions. */ struct nft_set_ops { - bool (*lookup)(const struct net *net, + const struct nft_set_ext * (*lookup)(const struct net *net, const struct nft_set *set, + const u32 *key); + const struct nft_set_ext * (*update)(struct nft_set *set, const u32 *key, - const struct nft_set_ext **ext); - bool (*update)(struct nft_set *set, - const u32 *key, - struct nft_elem_priv * - (*new)(struct nft_set *, - const struct nft_expr *, - struct nft_regs *), const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_set_ext **ext); + struct nft_regs *regs); bool (*delete)(const struct nft_set *set, const u32 *key); @@ -1939,11 +1933,6 @@ static inline u64 nft_net_tstamp(const struct net *net) #define __NFT_REDUCE_READONLY 1UL #define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY -static inline bool nft_reduce_is_readonly(const struct nft_expr *expr) -{ - return expr->ops->reduce == NFT_REDUCE_READONLY; -} - void nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 len); void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len); diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 03b6165756fc..6c2f483d9828 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -94,34 +94,41 @@ extern const struct nft_set_type nft_set_pipapo_type; extern const struct nft_set_type nft_set_pipapo_avx2_type; #ifdef CONFIG_MITIGATION_RETPOLINE -bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); -bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); -bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); -bool nft_hash_lookup_fast(const struct net *net, - const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); -bool nft_hash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); -bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); +const struct nft_set_ext * +nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); +const struct nft_set_ext * +nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); +const struct nft_set_ext * +nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); +const struct nft_set_ext * +nft_hash_lookup_fast(const struct net *net, const struct nft_set *set, + const u32 *key); +const struct nft_set_ext * +nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); +const struct nft_set_ext * +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); #else -static inline bool +static inline const struct nft_set_ext * nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) + const u32 *key) { - return set->ops->lookup(net, set, key, ext); + return set->ops->lookup(net, set, key); } #endif /* called from nft_pipapo_avx2.c */ -bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); +const struct nft_set_ext * +nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); /* called from nft_set_pipapo.c */ -bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); +const struct nft_set_ext * +nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, + const u32 *key); void nft_counter_init_seqcount(void); @@ -181,4 +188,7 @@ void nft_objref_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_objref_map_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +struct nft_elem_priv *nft_dynset_new(struct nft_set *set, + const struct nft_expr *expr, + struct nft_regs *regs); #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h index 84a561a74b98..1a2c4d6424b5 100644 --- a/include/uapi/linux/netfilter/nfnetlink_hook.h +++ b/include/uapi/linux/netfilter/nfnetlink_hook.h @@ -61,10 +61,12 @@ enum nfnl_hook_chain_desc_attributes { * * @NFNL_HOOK_TYPE_NFTABLES: nf_tables base chain * @NFNL_HOOK_TYPE_BPF: bpf program + * @NFNL_HOOK_TYPE_NFT_FLOWTABLE: nf_tables flowtable */ enum nfnl_hook_chaintype { NFNL_HOOK_TYPE_NFTABLES = 0x1, NFNL_HOOK_TYPE_BPF, + NFNL_HOOK_TYPE_NFT_FLOWTABLE, }; /** diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index f16bbbbb9481..60f28e4fb5c0 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -42,8 +42,8 @@ config NF_CONNTRACK_BRIDGE # old sockopt interface and eval loop config BRIDGE_NF_EBTABLES_LEGACY tristate "Legacy EBTABLES support" - depends on BRIDGE && NETFILTER_XTABLES - default n + depends on BRIDGE && NETFILTER_XTABLES_LEGACY + default n help Legacy ebtables packet/frame classifier. This is not needed if you are using ebtables over nftables @@ -65,7 +65,7 @@ if BRIDGE_NF_EBTABLES # config BRIDGE_EBT_BROUTE tristate "ebt: broute table support" - select BRIDGE_NF_EBTABLES_LEGACY + depends on BRIDGE_NF_EBTABLES_LEGACY help The ebtables broute table is used to define rules that decide between bridging and routing frames, giving Linux the functionality of a @@ -76,7 +76,7 @@ config BRIDGE_EBT_BROUTE config BRIDGE_EBT_T_FILTER tristate "ebt: filter table support" - select BRIDGE_NF_EBTABLES_LEGACY + depends on BRIDGE_NF_EBTABLES_LEGACY help The ebtables filter table is used to define frame filtering rules at local input, forwarding and local output. See the man page for @@ -86,7 +86,7 @@ config BRIDGE_EBT_T_FILTER config BRIDGE_EBT_T_NAT tristate "ebt: nat table support" - select BRIDGE_NF_EBTABLES_LEGACY + depends on BRIDGE_NF_EBTABLES_LEGACY help The ebtables nat table is used to define rules that alter the MAC source address (MAC SNAT) or the MAC destination address (MAC DNAT). diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index ef8009281da5..2c438b140e88 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -13,8 +13,8 @@ config NF_DEFRAG_IPV4 # old sockopt interface and eval loop config IP_NF_IPTABLES_LEGACY tristate "Legacy IP tables support" - default n - select NETFILTER_XTABLES + depends on NETFILTER_XTABLES_LEGACY + default m if NETFILTER_XTABLES_LEGACY help iptables is a legacy packet classifier. This is not needed if you are using iptables over nftables @@ -182,8 +182,8 @@ config IP_NF_MATCH_TTL # `filter', generic and specific targets config IP_NF_FILTER tristate "Packet filtering" - default m if NETFILTER_ADVANCED=n - select IP_NF_IPTABLES_LEGACY + default m if NETFILTER_ADVANCED=n || IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -220,10 +220,10 @@ config IP_NF_TARGET_SYNPROXY config IP_NF_NAT tristate "iptables NAT support" depends on NF_CONNTRACK + depends on IP_NF_IPTABLES_LEGACY default m if NETFILTER_ADVANCED=n select NF_NAT select NETFILTER_XT_NAT - select IP_NF_IPTABLES_LEGACY help This enables the `nat' table in iptables. This allows masquerading, port forwarding and other forms of full Network Address Port @@ -263,8 +263,8 @@ endif # IP_NF_NAT # mangle + specific targets config IP_NF_MANGLE tristate "Packet mangling" - default m if NETFILTER_ADVANCED=n - select IP_NF_IPTABLES_LEGACY + default m if NETFILTER_ADVANCED=n || IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -299,7 +299,7 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - select IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -313,7 +313,7 @@ config IP_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED - select IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -325,8 +325,8 @@ endif # IP_NF_IPTABLES # ARP tables config IP_NF_ARPTABLES tristate "Legacy ARPTABLES support" - depends on NETFILTER_XTABLES - default n + depends on NETFILTER_XTABLES_LEGACY + default n help arptables is a legacy packet classifier. This is not needed if you are using arptables over nftables @@ -342,7 +342,7 @@ config IP_NF_ARPFILTER tristate "arptables-legacy packet filtering support" select IP_NF_ARPTABLES select NETFILTER_FAMILY_ARP - depends on NETFILTER_XTABLES + depends on NETFILTER_XTABLES_LEGACY help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index e087a8e97ba7..276860f65baa 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -9,9 +9,8 @@ menu "IPv6: Netfilter Configuration" # old sockopt interface and eval loop config IP6_NF_IPTABLES_LEGACY tristate "Legacy IP6 tables support" - depends on INET && IPV6 - select NETFILTER_XTABLES - default n + depends on INET && IPV6 && NETFILTER_XTABLES_LEGACY + default m if NETFILTER_XTABLES_LEGACY help ip6tables is a legacy packet classifier. This is not needed if you are using iptables over nftables @@ -196,8 +195,8 @@ config IP6_NF_TARGET_HL config IP6_NF_FILTER tristate "Packet filtering" - default m if NETFILTER_ADVANCED=n - select IP6_NF_IPTABLES_LEGACY + default m if NETFILTER_ADVANCED=n || IP6_NF_IPTABLES_LEGACY + depends on IP6_NF_IPTABLES_LEGACY tristate help Packet filtering defines a table `filter', which has a series of @@ -233,8 +232,8 @@ config IP6_NF_TARGET_SYNPROXY config IP6_NF_MANGLE tristate "Packet mangling" - default m if NETFILTER_ADVANCED=n - select IP6_NF_IPTABLES_LEGACY + default m if NETFILTER_ADVANCED=n || IP6_NF_IPTABLES_LEGACY + depends on IP6_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -244,7 +243,7 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' - select IP6_NF_IPTABLES_LEGACY + depends on IP6_NF_IPTABLES_LEGACY help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -258,7 +257,7 @@ config IP6_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED - select IP6_NF_IPTABLES_LEGACY + depends on IP6_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -269,8 +268,8 @@ config IP6_NF_NAT tristate "ip6tables NAT support" depends on NF_CONNTRACK depends on NETFILTER_ADVANCED + depends on IP6_NF_IPTABLES_LEGACY select NF_NAT - select IP6_NF_IPTABLES_LEGACY select NETFILTER_XT_NAT help This enables the `nat' table in ip6tables. This allows masquerading, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index ba60b48d7567..6cdc994fdc8a 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -758,6 +758,16 @@ config NETFILTER_XTABLES_COMPAT If unsure, say N. +config NETFILTER_XTABLES_LEGACY + bool "Netfilter legacy tables support" + depends on !PREEMPT_RT + help + Say Y here if you still require support for legacy tables. This is + required by the legacy tools (iptables-legacy) and is not needed if + you use iptables over nftables (iptables-nft). + Legacy support is not limited to IP, it also includes EBTABLES and + ARPTABLES. + comment "Xtables combined modules" config NETFILTER_XT_MARK diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 44b2ad695c15..965f3c8e5089 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -926,7 +926,7 @@ static void ip_vs_conn_expire(struct timer_list *t) void ip_vs_conn_expire_now(struct ip_vs_conn *cp) { /* Using mod_timer_pending will ensure the timer is not - * modified after the final del_timer in ip_vs_conn_expire. + * modified after the final timer_delete in ip_vs_conn_expire. */ if (timer_pending(&cp->timer) && time_after(cp->timer.expires, jiffies)) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2a90945aef89..344f88295976 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -136,8 +136,8 @@ static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2) } /* return true if we need to recompute hashes (in case hash table was resized) */ -static bool nf_conntrack_double_lock(struct net *net, unsigned int h1, - unsigned int h2, unsigned int sequence) +static bool nf_conntrack_double_lock(unsigned int h1, unsigned int h2, + unsigned int sequence) { h1 %= CONNTRACK_LOCKS; h2 %= CONNTRACK_LOCKS; @@ -613,7 +613,7 @@ static void __nf_ct_delete_from_lists(struct nf_conn *ct) reply_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); - } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + } while (nf_conntrack_double_lock(hash, reply_hash, sequence)); clean_from_lists(ct); nf_conntrack_double_unlock(hash, reply_hash); @@ -890,7 +890,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) reply_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); - } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + } while (nf_conntrack_double_lock(hash, reply_hash, sequence)); max_chainlen = MIN_CHAINLEN + get_random_u32_below(MAX_CHAINLEN); @@ -1234,7 +1234,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) reply_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); - } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + } while (nf_conntrack_double_lock(hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related * connections for unconfirmed conns. But packet copies and @@ -1673,7 +1673,11 @@ __nf_conntrack_alloc(struct net *net, if (!conntrack_gc_work.early_drop) conntrack_gc_work.early_drop = true; atomic_dec(&cnet->count); - net_warn_ratelimited("nf_conntrack: table full, dropping packet\n"); + if (net == &init_net) + net_warn_ratelimited("nf_conntrack: table full, dropping packet\n"); + else + net_warn_ratelimited("nf_conntrack: table full in netns %u, dropping packet\n", + net->ns.inum); return ERR_PTR(-ENOMEM); } } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 829f60496008..9b8b10a85233 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -14,6 +14,7 @@ #include <linux/sysctl.h> #endif +#include <net/netfilter/nf_log.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_l4proto.h> @@ -555,6 +556,29 @@ nf_conntrack_hash_sysctl(const struct ctl_table *table, int write, return ret; } +static int +nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, i; + + ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); + if (ret < 0 || !write) + return ret; + + if (*(u8 *)table->data == 0) + return ret; + + /* Load nf_log_syslog only if no logger is currently registered */ + for (i = 0; i < NFPROTO_NUMPROTO; i++) { + if (nf_log_is_registered(i)) + return ret; + } + request_module("%s", "nf_log_syslog"); + + return ret; +} + static struct ctl_table_header *nf_ct_netfilter_header; enum nf_ct_sysctl_index { @@ -651,7 +675,7 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = nf_conntrack_log_invalid_sysctl, }, [NF_SYSCTL_CT_EXPECT_MAX] = { .procname = "nf_conntrack_expect_max", diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 6dd0de33eebd..74cef8bf554c 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -125,6 +125,32 @@ void nf_log_unregister(struct nf_logger *logger) } EXPORT_SYMBOL(nf_log_unregister); +/** + * nf_log_is_registered - Check if any logger is registered for a given + * protocol family. + * + * @pf: Protocol family + * + * Returns: true if at least one logger is active for @pf, false otherwise. + */ +bool nf_log_is_registered(u_int8_t pf) +{ + int i; + + if (pf >= NFPROTO_NUMPROTO) { + WARN_ON_ONCE(1); + return false; + } + + for (i = 0; i < NF_LOG_TYPE_MAX; i++) { + if (rcu_access_pointer(loggers[pf][i])) + return true; + } + + return false; +} +EXPORT_SYMBOL(nf_log_is_registered); + int nf_log_bind_pf(struct net *net, u_int8_t pf, const struct nf_logger *logger) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 04795af6e586..13d0ed9d1895 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8895,11 +8895,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, list_for_each_entry(hook, &flowtable_hook->list, list) { list_for_each_entry(ops, &hook->ops_list, list) { - ops->pf = NFPROTO_NETDEV; - ops->hooknum = flowtable_hook->num; - ops->priority = flowtable_hook->priority; - ops->priv = &flowtable->data; - ops->hook = flowtable->data.type->hook; + ops->pf = NFPROTO_NETDEV; + ops->hooknum = flowtable_hook->num; + ops->priority = flowtable_hook->priority; + ops->priv = &flowtable->data; + ops->hook = flowtable->data.type->hook; + ops->hook_ops_type = NF_HOOK_OP_NFT_FT; } } @@ -9727,12 +9728,13 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev, if (!ops) return 1; - ops->pf = NFPROTO_NETDEV; - ops->hooknum = flowtable->hooknum; - ops->priority = flowtable->data.priority; - ops->priv = &flowtable->data; - ops->hook = flowtable->data.type->hook; - ops->dev = dev; + ops->pf = NFPROTO_NETDEV; + ops->hooknum = flowtable->hooknum; + ops->priority = flowtable->data.priority; + ops->priv = &flowtable->data; + ops->hook = flowtable->data.type->hook; + ops->hook_ops_type = NF_HOOK_OP_NFT_FT; + ops->dev = dev; if (nft_register_flowtable_ops(dev_net(dev), flowtable, ops)) { kfree(ops); diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index ade8ee1988b1..92d869317cba 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -109,13 +109,30 @@ cancel_nest: return -EMSGSIZE; } +static int nfnl_hook_put_nft_info_desc(struct sk_buff *nlskb, const char *tname, + const char *name, u8 family) +{ + struct nlattr *nest; + + nest = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC); + if (!nest || + nla_put_string(nlskb, NFNLA_CHAIN_TABLE, tname) || + nla_put_string(nlskb, NFNLA_CHAIN_NAME, name) || + nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, family)) { + nla_nest_cancel(nlskb, nest); + return -EMSGSIZE; + } + nla_nest_end(nlskb, nest); + return 0; +} + static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, const struct nfnl_dump_hook_data *ctx, unsigned int seq, struct nft_chain *chain) { struct net *net = sock_net(nlskb->sk); - struct nlattr *nest, *nest2; + struct nlattr *nest; int ret = 0; if (WARN_ON_ONCE(!chain)) @@ -128,29 +145,47 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, if (!nest) return -EMSGSIZE; - nest2 = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC); - if (!nest2) - goto cancel_nest; + ret = nfnl_hook_put_nft_info_desc(nlskb, chain->table->name, + chain->name, chain->table->family); + if (ret) { + nla_nest_cancel(nlskb, nest); + return ret; + } - ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name); - if (ret) - goto cancel_nest; + nla_nest_end(nlskb, nest); + return 0; +} - ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name); - if (ret) - goto cancel_nest; +static int nfnl_hook_put_nft_ft_info(struct sk_buff *nlskb, + const struct nfnl_dump_hook_data *ctx, + unsigned int seq, + struct nf_flowtable *nf_ft) +{ + struct nft_flowtable *ft = + container_of(nf_ft, struct nft_flowtable, data); + struct net *net = sock_net(nlskb->sk); + struct nlattr *nest; + int ret = 0; - ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family); - if (ret) - goto cancel_nest; + if (WARN_ON_ONCE(!nf_ft)) + return 0; - nla_nest_end(nlskb, nest2); - nla_nest_end(nlskb, nest); - return ret; + if (!nft_is_active(net, ft)) + return 0; -cancel_nest: - nla_nest_cancel(nlskb, nest); - return -EMSGSIZE; + nest = nfnl_start_info_type(nlskb, NFNL_HOOK_TYPE_NFT_FLOWTABLE); + if (!nest) + return -EMSGSIZE; + + ret = nfnl_hook_put_nft_info_desc(nlskb, ft->table->name, + ft->name, ft->table->family); + if (ret) { + nla_nest_cancel(nlskb, nest); + return ret; + } + + nla_nest_end(nlskb, nest); + return 0; } static int nfnl_hook_dump_one(struct sk_buff *nlskb, @@ -220,6 +255,9 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, case NF_HOOK_OP_BPF: ret = nfnl_hook_put_bpf_prog_info(nlskb, ctx, seq, ops->priv); break; + case NF_HOOK_OP_NFT_FT: + ret = nfnl_hook_put_nft_ft_info(nlskb, ctx, seq, ops->priv); + break; case NF_HOOK_OP_UNDEFINED: break; default: diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 88922e0e8e83..7807d8129664 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -44,9 +44,9 @@ static int nft_dynset_expr_setup(const struct nft_dynset *priv, return 0; } -static struct nft_elem_priv *nft_dynset_new(struct nft_set *set, - const struct nft_expr *expr, - struct nft_regs *regs) +struct nft_elem_priv *nft_dynset_new(struct nft_set *set, + const struct nft_expr *expr, + struct nft_regs *regs) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set_ext *ext; @@ -91,8 +91,8 @@ void nft_dynset_eval(const struct nft_expr *expr, return; } - if (set->ops->update(set, ®s->data[priv->sreg_key], nft_dynset_new, - expr, regs, &ext)) { + ext = set->ops->update(set, ®s->data[priv->sreg_key], expr, regs); + if (ext) { if (priv->op == NFT_DYNSET_OP_UPDATE && nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && READ_ONCE(nft_set_ext_timeout(ext)->timeout) != 0) { diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 63ef832b8aa7..40c602ffbcba 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -25,32 +25,33 @@ struct nft_lookup { }; #ifdef CONFIG_MITIGATION_RETPOLINE -bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { if (set->ops == &nft_set_hash_fast_type.ops) - return nft_hash_lookup_fast(net, set, key, ext); + return nft_hash_lookup_fast(net, set, key); if (set->ops == &nft_set_hash_type.ops) - return nft_hash_lookup(net, set, key, ext); + return nft_hash_lookup(net, set, key); if (set->ops == &nft_set_rhash_type.ops) - return nft_rhash_lookup(net, set, key, ext); + return nft_rhash_lookup(net, set, key); if (set->ops == &nft_set_bitmap_type.ops) - return nft_bitmap_lookup(net, set, key, ext); + return nft_bitmap_lookup(net, set, key); if (set->ops == &nft_set_pipapo_type.ops) - return nft_pipapo_lookup(net, set, key, ext); + return nft_pipapo_lookup(net, set, key); #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) if (set->ops == &nft_set_pipapo_avx2_type.ops) - return nft_pipapo_avx2_lookup(net, set, key, ext); + return nft_pipapo_avx2_lookup(net, set, key); #endif if (set->ops == &nft_set_rbtree_type.ops) - return nft_rbtree_lookup(net, set, key, ext); + return nft_rbtree_lookup(net, set, key); WARN_ON_ONCE(1); - return set->ops->lookup(net, set, key, ext); + return set->ops->lookup(net, set, key); } EXPORT_SYMBOL_GPL(nft_set_do_lookup); #endif @@ -61,12 +62,12 @@ void nft_lookup_eval(const struct nft_expr *expr, { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; - const struct nft_set_ext *ext = NULL; const struct net *net = nft_net(pkt); + const struct nft_set_ext *ext; bool found; - found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext) ^ - priv->invert; + ext = nft_set_do_lookup(net, set, ®s->data[priv->sreg]); + found = !!ext ^ priv->invert; if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 09da7a3f9f96..8ee66a86c3bc 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -111,10 +111,9 @@ void nft_objref_map_eval(const struct nft_expr *expr, struct net *net = nft_net(pkt); const struct nft_set_ext *ext; struct nft_object *obj; - bool found; - found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext); - if (!found) { + ext = nft_set_do_lookup(net, set, ®s->data[priv->sreg]); + if (!ext) { ext = nft_set_catchall_lookup(net, set); if (!ext) { regs->verdict.code = NFT_BREAK; diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 12390d2e994f..c24c922f895d 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -75,16 +75,21 @@ nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask) } INDIRECT_CALLABLE_SCOPE -bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { const struct nft_bitmap *priv = nft_set_priv(set); + static const struct nft_set_ext found; u8 genmask = nft_genmask_cur(net); u32 idx, off; nft_bitmap_location(set, key, &idx, &off); - return nft_bitmap_active(priv->bitmap, idx, off, genmask); + if (nft_bitmap_active(priv->bitmap, idx, off, genmask)) + return &found; + + return NULL; } static struct nft_bitmap_elem * diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index abb0c8ec6371..266d0c637225 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -81,8 +81,9 @@ static const struct rhashtable_params nft_rhash_params = { }; INDIRECT_CALLABLE_SCOPE -bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { struct nft_rhash *priv = nft_set_priv(set); const struct nft_rhash_elem *he; @@ -95,9 +96,9 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); if (he != NULL) - *ext = &he->ext; + return &he->ext; - return !!he; + return NULL; } static struct nft_elem_priv * @@ -120,14 +121,9 @@ nft_rhash_get(const struct net *net, const struct nft_set *set, return ERR_PTR(-ENOENT); } -static bool nft_rhash_update(struct nft_set *set, const u32 *key, - struct nft_elem_priv * - (*new)(struct nft_set *, - const struct nft_expr *, - struct nft_regs *regs), - const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_set_ext **ext) +static const struct nft_set_ext * +nft_rhash_update(struct nft_set *set, const u32 *key, + const struct nft_expr *expr, struct nft_regs *regs) { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he, *prev; @@ -143,7 +139,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, if (he != NULL) goto out; - elem_priv = new(set, expr, regs); + elem_priv = nft_dynset_new(set, expr, regs); if (!elem_priv) goto err1; @@ -161,14 +157,13 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, } out: - *ext = &he->ext; - return true; + return &he->ext; err2: nft_set_elem_destroy(set, &he->priv, true); atomic_dec(&set->nelems); err1: - return false; + return NULL; } static int nft_rhash_insert(const struct net *net, const struct nft_set *set, @@ -507,8 +502,9 @@ struct nft_hash_elem { }; INDIRECT_CALLABLE_SCOPE -bool nft_hash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -519,12 +515,10 @@ bool nft_hash_lookup(const struct net *net, const struct nft_set *set, hash = reciprocal_scale(hash, priv->buckets); hlist_for_each_entry_rcu(he, &priv->table[hash], node) { if (!memcmp(nft_set_ext_key(&he->ext), key, set->klen) && - nft_set_elem_active(&he->ext, genmask)) { - *ext = &he->ext; - return true; - } + nft_set_elem_active(&he->ext, genmask)) + return &he->ext; } - return false; + return NULL; } static struct nft_elem_priv * @@ -547,9 +541,9 @@ nft_hash_get(const struct net *net, const struct nft_set *set, } INDIRECT_CALLABLE_SCOPE -bool nft_hash_lookup_fast(const struct net *net, - const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_hash_lookup_fast(const struct net *net, const struct nft_set *set, + const u32 *key) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -562,12 +556,10 @@ bool nft_hash_lookup_fast(const struct net *net, hlist_for_each_entry_rcu(he, &priv->table[hash], node) { k2 = *(u32 *)nft_set_ext_key(&he->ext)->data; if (k1 == k2 && - nft_set_elem_active(&he->ext, genmask)) { - *ext = &he->ext; - return true; - } + nft_set_elem_active(&he->ext, genmask)) + return &he->ext; } - return false; + return NULL; } static u32 nft_jhash(const struct nft_set *set, const struct nft_hash *priv, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index c5855069bdab..1a19649c2851 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -397,34 +397,36 @@ int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, } /** - * nft_pipapo_lookup() - Lookup function - * @net: Network namespace - * @set: nftables API set representation - * @key: nftables API element representation containing key data - * @ext: nftables API extension pointer, filled with matching reference + * pipapo_get() - Get matching element reference given key data + * @m: storage containing the set elements + * @data: Key data to be matched against existing elements + * @genmask: If set, check that element is active in given genmask + * @tstamp: timestamp to check for expired elements * * For more details, see DOC: Theory of Operation. * - * Return: true on match, false otherwise. + * This is the main lookup function. It matches key data against either + * the working match set or the uncommitted copy, depending on what the + * caller passed to us. + * nft_pipapo_get (lookup from userspace/control plane) and nft_pipapo_lookup + * (datapath lookup) pass the active copy. + * The insertion path will pass the uncommitted working copy. + * + * Return: pointer to &struct nft_pipapo_elem on match, NULL otherwise. */ -bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m, + const u8 *data, u8 genmask, + u64 tstamp) { - struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; - u8 genmask = nft_genmask_cur(net); - const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; - const u8 *rp = (const u8 *)key; bool map_index; int i; local_bh_disable(); - m = rcu_dereference(priv->match); - - if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) + if (unlikely(!raw_cpu_ptr(m->scratch))) goto out; scratch = *raw_cpu_ptr(m->scratch); @@ -444,12 +446,12 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, * packet bytes value, then AND bucket value */ if (likely(f->bb == 8)) - pipapo_and_field_buckets_8bit(f, res_map, rp); + pipapo_and_field_buckets_8bit(f, res_map, data); else - pipapo_and_field_buckets_4bit(f, res_map, rp); + pipapo_and_field_buckets_4bit(f, res_map, data); NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4; - rp += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f); + data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f); /* Now populate the bitmap for the next field, unless this is * the last field, in which case return the matched 'ext' @@ -465,13 +467,15 @@ next_match: scratch->map_index = map_index; local_bh_enable(); - return false; + return NULL; } if (last) { - *ext = &f->mt[b].e->ext; - if (unlikely(nft_set_elem_expired(*ext) || - !nft_set_elem_active(*ext, genmask))) + struct nft_pipapo_elem *e; + + e = f->mt[b].e; + if (unlikely(__nft_set_elem_expired(&e->ext, tstamp) || + !nft_set_elem_active(&e->ext, genmask))) goto next_match; /* Last field: we're just returning the key without @@ -481,8 +485,7 @@ next_match: */ scratch->map_index = map_index; local_bh_enable(); - - return true; + return e; } /* Swap bitmap indices: res_map is the initial bitmap for the @@ -492,112 +495,38 @@ next_match: map_index = !map_index; swap(res_map, fill_map); - rp += NFT_PIPAPO_GROUPS_PADDING(f); + data += NFT_PIPAPO_GROUPS_PADDING(f); } out: local_bh_enable(); - return false; + return NULL; } /** - * pipapo_get() - Get matching element reference given key data + * nft_pipapo_lookup() - Dataplane fronted for main lookup function * @net: Network namespace * @set: nftables API set representation - * @m: storage containing active/existing elements - * @data: Key data to be matched against existing elements - * @genmask: If set, check that element is active in given genmask - * @tstamp: timestamp to check for expired elements - * @gfp: the type of memory to allocate (see kmalloc). + * @key: pointer to nft registers containing key data * - * This is essentially the same as the lookup function, except that it matches - * key data against the uncommitted copy and doesn't use preallocated maps for - * bitmap results. + * This function is called from the data path. It will search for + * an element matching the given key in the current active copy. * - * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise. + * Return: ntables API extension pointer or NULL if no match. */ -static struct nft_pipapo_elem *pipapo_get(const struct net *net, - const struct nft_set *set, - const struct nft_pipapo_match *m, - const u8 *data, u8 genmask, - u64 tstamp, gfp_t gfp) +const struct nft_set_ext * +nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { - struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); - unsigned long *res_map, *fill_map = NULL; - const struct nft_pipapo_field *f; - int i; - - if (m->bsize_max == 0) - return ret; - - res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), gfp); - if (!res_map) { - ret = ERR_PTR(-ENOMEM); - goto out; - } - - fill_map = kcalloc(m->bsize_max, sizeof(*res_map), gfp); - if (!fill_map) { - ret = ERR_PTR(-ENOMEM); - goto out; - } - - pipapo_resmap_init(m, res_map); - - nft_pipapo_for_each_field(f, i, m) { - bool last = i == m->field_count - 1; - int b; - - /* For each bit group: select lookup table bucket depending on - * packet bytes value, then AND bucket value - */ - if (f->bb == 8) - pipapo_and_field_buckets_8bit(f, res_map, data); - else if (f->bb == 4) - pipapo_and_field_buckets_4bit(f, res_map, data); - else - BUG(); - - data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f); - - /* Now populate the bitmap for the next field, unless this is - * the last field, in which case return the matched 'ext' - * pointer if any. - * - * Now res_map contains the matching bitmap, and fill_map is the - * bitmap for the next field. - */ -next_match: - b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, - last); - if (b < 0) - goto out; - - if (last) { - if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) - goto next_match; - if ((genmask && - !nft_set_elem_active(&f->mt[b].e->ext, genmask))) - goto next_match; - - ret = f->mt[b].e; - goto out; - } - - data += NFT_PIPAPO_GROUPS_PADDING(f); + struct nft_pipapo *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + const struct nft_pipapo_match *m; + const struct nft_pipapo_elem *e; - /* Swap bitmap indices: fill_map will be the initial bitmap for - * the next field (i.e. the new res_map), and res_map is - * guaranteed to be all-zeroes at this point, ready to be filled - * according to the next mapping table. - */ - swap(res_map, fill_map); - } + m = rcu_dereference(priv->match); + e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64()); -out: - kfree(fill_map); - kfree(res_map); - return ret; + return e ? &e->ext : NULL; } /** @@ -606,6 +535,11 @@ out: * @set: nftables API set representation * @elem: nftables API element representation containing key data * @flags: Unused + * + * This function is called from the control plane path under + * RCU read lock. + * + * Return: set element private pointer or ERR_PTR(-ENOENT). */ static struct nft_elem_priv * nft_pipapo_get(const struct net *net, const struct nft_set *set, @@ -615,11 +549,10 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set, struct nft_pipapo_match *m = rcu_dereference(priv->match); struct nft_pipapo_elem *e; - e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data, - nft_genmask_cur(net), get_jiffies_64(), - GFP_ATOMIC); - if (IS_ERR(e)) - return ERR_CAST(e); + e = pipapo_get(m, (const u8 *)elem->key.val.data, + nft_genmask_cur(net), get_jiffies_64()); + if (!e) + return ERR_PTR(-ENOENT); return &e->priv; } @@ -1219,7 +1152,7 @@ static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int c mem = s; mem -= s->align_off; - kfree(mem); + kvfree(mem); } /** @@ -1240,10 +1173,9 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, void *scratch_aligned; u32 align_off; #endif - scratch = kzalloc_node(struct_size(scratch, map, - bsize_max * 2) + - NFT_PIPAPO_ALIGN_HEADROOM, - GFP_KERNEL_ACCOUNT, cpu_to_node(i)); + scratch = kvzalloc_node(struct_size(scratch, map, bsize_max * 2) + + NFT_PIPAPO_ALIGN_HEADROOM, + GFP_KERNEL_ACCOUNT, cpu_to_node(i)); if (!scratch) { /* On failure, there's no need to undo previous * allocations: this means that some scratch maps have @@ -1345,8 +1277,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, m, start, genmask, tstamp, GFP_KERNEL); - if (!IS_ERR(dup)) { + dup = pipapo_get(m, start, genmask, tstamp); + if (dup) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1365,15 +1297,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, return -ENOTEMPTY; } - if (PTR_ERR(dup) == -ENOENT) { - /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, m, end, nft_genmask_next(net), tstamp, - GFP_KERNEL); - } - - if (PTR_ERR(dup) != -ENOENT) { - if (IS_ERR(dup)) - return PTR_ERR(dup); + /* Look for partially overlapping entries */ + dup = pipapo_get(m, end, nft_genmask_next(net), tstamp); + if (dup) { *elem_priv = &dup->priv; return -ENOTEMPTY; } @@ -1914,9 +1840,9 @@ nft_pipapo_deactivate(const struct net *net, const struct nft_set *set, if (!m) return NULL; - e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data, - nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL); - if (IS_ERR(e)) + e = pipapo_get(m, (const u8 *)elem->key.val.data, + nft_genmask_next(net), nft_net_tstamp(net)); + if (!e) return NULL; nft_set_elem_change_active(net, set, &e->ext); diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index be7c16c79f71..db5d367e43c4 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1137,7 +1137,6 @@ static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, uns * @net: Network namespace * @set: nftables API set representation * @key: nftables API element representation containing key data - * @ext: nftables API extension pointer, filled with matching reference * * For more details, see DOC: Theory of Operation in nft_set_pipapo.c. * @@ -1146,8 +1145,9 @@ static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, uns * * Return: true on match, false otherwise. */ -bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_scratch *scratch; @@ -1155,17 +1155,18 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; + const struct nft_set_ext *ext; unsigned long *res, *fill; bool map_index; - int i, ret = 0; + int i; local_bh_disable(); if (unlikely(!irq_fpu_usable())) { - bool fallback_res = nft_pipapo_lookup(net, set, key, ext); + ext = nft_pipapo_lookup(net, set, key); local_bh_enable(); - return fallback_res; + return ext; } m = rcu_dereference(priv->match); @@ -1182,7 +1183,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, if (unlikely(!scratch)) { kernel_fpu_end(); local_bh_enable(); - return false; + return NULL; } map_index = scratch->map_index; @@ -1197,6 +1198,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, next_match: nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1, first = !i; + int ret = 0; #define NFT_SET_PIPAPO_AVX2_LOOKUP(b, n) \ (ret = nft_pipapo_avx2_lookup_##b##b_##n(res, fill, f, \ @@ -1244,10 +1246,10 @@ next_match: goto out; if (last) { - *ext = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(*ext) || - !nft_set_elem_active(*ext, genmask))) { - ret = 0; + ext = &f->mt[ret].e->ext; + if (unlikely(nft_set_elem_expired(ext) || + !nft_set_elem_active(ext, genmask))) { + ext = NULL; goto next_match; } @@ -1264,5 +1266,5 @@ out: kernel_fpu_end(); local_bh_enable(); - return ret >= 0; + return ext; } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 2e8ef16ff191..938a257c069e 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -52,9 +52,9 @@ static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) return nft_set_elem_expired(&rbe->ext); } -static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext, - unsigned int seq) +static const struct nft_set_ext * +__nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, unsigned int seq) { struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; @@ -65,7 +65,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) - return false; + return NULL; rbe = rb_entry(parent, struct nft_rbtree_elem, node); @@ -87,50 +87,48 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set } if (nft_rbtree_elem_expired(rbe)) - return false; + return NULL; if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) - return false; + return NULL; parent = rcu_dereference_raw(parent->rb_left); interval = NULL; continue; } - *ext = &rbe->ext; - return true; + return &rbe->ext; } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_rbtree_elem_expired(interval) && - nft_rbtree_interval_start(interval)) { - *ext = &interval->ext; - return true; - } + nft_rbtree_interval_start(interval)) + return &interval->ext; - return false; + return NULL; } INDIRECT_CALLABLE_SCOPE -bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +const struct nft_set_ext * +nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); - bool ret; + const struct nft_set_ext *ext; - ret = __nft_rbtree_lookup(net, set, key, ext, seq); - if (ret || !read_seqcount_retry(&priv->count, seq)) - return ret; + ext = __nft_rbtree_lookup(net, set, key, seq); + if (ext || !read_seqcount_retry(&priv->count, seq)) + return ext; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); - ret = __nft_rbtree_lookup(net, set, key, ext, seq); + ext = __nft_rbtree_lookup(net, set, key, seq); read_unlock_bh(&priv->lock); - return ret; + return ext; } static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 709840612f0d..90b7630421c4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1317,12 +1317,13 @@ void xt_compat_unlock(u_int8_t af) EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif -DEFINE_PER_CPU(seqcount_t, xt_recseq); -EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); - struct static_key xt_tee_enabled __read_mostly; EXPORT_SYMBOL_GPL(xt_tee_enabled); +#ifdef CONFIG_NETFILTER_XTABLES_LEGACY +DEFINE_PER_CPU(seqcount_t, xt_recseq); +EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); + static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; @@ -1514,6 +1515,7 @@ void *xt_unregister_table(struct xt_table *table) return private; } EXPORT_SYMBOL_GPL(xt_unregister_table); +#endif #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) @@ -1897,6 +1899,7 @@ void xt_proto_fini(struct net *net, u_int8_t af) } EXPORT_SYMBOL_GPL(xt_proto_fini); +#ifdef CONFIG_NETFILTER_XTABLES_LEGACY /** * xt_percpu_counter_alloc - allocate x_tables rule counter * @@ -1951,6 +1954,7 @@ void xt_percpu_counter_free(struct xt_counters *counters) free_percpu((void __percpu *)pcnt); } EXPORT_SYMBOL_GPL(xt_percpu_counter_free); +#endif static int __net_init xt_net_init(struct net *net) { @@ -1983,8 +1987,10 @@ static int __init xt_init(void) unsigned int i; int rv; - for_each_possible_cpu(i) { - seqcount_init(&per_cpu(xt_recseq, i)); + if (IS_ENABLED(CONFIG_NETFILTER_XTABLES_LEGACY)) { + for_each_possible_cpu(i) { + seqcount_init(&per_cpu(xt_recseq, i)); + } } xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 7c6bf1c16813..0ca1cdfc4095 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -38,8 +38,8 @@ nfacct_mt_checkentry(const struct xt_mtchk_param *par) nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { - pr_info_ratelimited("accounting object `%s' does not exists\n", - info->name); + pr_info_ratelimited("accounting object `%.*s' does not exist\n", + NFACCT_NAME_MAX, info->name); return -ENOENT; } info->nfacct = nfacct; diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f74e1ea0ad3b..521836776733 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -97,6 +97,7 @@ CONFIG_NF_TABLES_NETDEV=y CONFIG_NF_TABLES_IPV4=y CONFIG_NF_TABLES_IPV6=y CONFIG_NETFILTER_INGRESS=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NF_FLOW_TABLE=y CONFIG_NF_FLOW_TABLE_INET=y CONFIG_NETFILTER_NETLINK=y diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common index b1f40857307d..38c51158adf8 100644 --- a/tools/testing/selftests/hid/config.common +++ b/tools/testing/selftests/hid/config.common @@ -135,6 +135,7 @@ CONFIG_NET_EMATCH=y CONFIG_NETFILTER_NETLINK_LOG=y CONFIG_NETFILTER_NETLINK_QUEUE=y CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=y CONFIG_NETFILTER_XT_MATCH_BPF=y CONFIG_NETFILTER_XT_MATCH_COMMENT=y diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3cfef5153823..c24417d0047b 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -30,16 +30,25 @@ CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NF_CONNTRACK=m CONFIG_IPV6_MROUTE=y CONFIG_IPV6_SIT=y CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_RAW=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_NAT=m CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IPV6_GRE=m CONFIG_IPV6_SEG6_LWTUNNEL=y @@ -57,6 +66,8 @@ CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_NAT=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_TARGET_HL=m +CONFIG_NETFILTER_XT_NAT=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GACT=m diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 4f80014cae49..968d440c03fe 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -13,6 +13,7 @@ CONFIG_NETFILTER_NETLINK=m CONFIG_NF_TABLES=m CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XTABLES=m +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_BPF=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m @@ -25,6 +26,7 @@ CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index 363646f4fefe..79d5b33966ba 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -1,6 +1,8 @@ CONFIG_AUDIT=y CONFIG_BPF_SYSCALL=y CONFIG_BRIDGE=m +CONFIG_NETFILTER_XTABLES_LEGACY=y +CONFIG_BRIDGE_NF_EBTABLES_LEGACY=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_IP=m CONFIG_BRIDGE_EBT_REDIRECT=m @@ -14,7 +16,10 @@ CONFIG_INET_ESP=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RPFILTER=m CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_FILTER=m CONFIG_IP6_NF_FILTER=m CONFIG_IP_NF_RAW=m @@ -92,4 +97,4 @@ CONFIG_XFRM_STATISTICS=y CONFIG_NET_PKTGEN=m CONFIG_TUN=m CONFIG_INET_DIAG=m -CONFIG_SCTP_DIAG=m +CONFIG_INET_SCTP_DIAG=m diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh index 6af2ea3ad6b8..9c9d5b38ab71 100755 --- a/tools/testing/selftests/net/netfilter/ipvs.sh +++ b/tools/testing/selftests/net/netfilter/ipvs.sh @@ -151,7 +151,7 @@ test_nat() { test_tun() { ip netns exec "${ns0}" ip route add "${vip_v4}" via "${gip_v4}" dev br0 - ip netns exec "${ns1}" modprobe -q ipip + modprobe -q ipip ip netns exec "${ns1}" ip link set tunl0 up ip netns exec "${ns1}" sysctl -qw net.ipv4.ip_forward=0 ip netns exec "${ns1}" sysctl -qw net.ipv4.conf.all.send_redirects=0 @@ -160,10 +160,10 @@ test_tun() { ip netns exec "${ns1}" ipvsadm -a -i -t "${vip_v4}:${port}" -r ${rip_v4}:${port} ip netns exec "${ns1}" ip addr add ${vip_v4}/32 dev lo:1 - ip netns exec "${ns2}" modprobe -q ipip ip netns exec "${ns2}" ip link set tunl0 up ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1 ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2 + ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.tunl0.rp_filter=0 ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1 test_service diff --git a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh index 5ff7be9daeee..c0fffaa6dbd9 100755 --- a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh +++ b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh @@ -10,6 +10,8 @@ source lib.sh checktool "nft --version" "run test without nft tool" checktool "iperf3 --version" "run test without iperf3 tool" +read kernel_tainted < /proc/sys/kernel/tainted + # how many seconds to torture the kernel? # default to 80% of max run time but don't exceed 48s TEST_RUNTIME=$((${kselftest_timeout:-60} * 8 / 10)) @@ -135,7 +137,8 @@ else wait fi -[[ $(</proc/sys/kernel/tainted) -eq 0 ]] || { + +[[ $kernel_tainted -eq 0 && $(</proc/sys/kernel/tainted) -ne 0 ]] && { echo "FAIL: Kernel is tainted!" exit $ksft_fail } diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index f314d3789f17..0a5381717e9f 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -16,9 +16,13 @@ CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=y CONFIG_NF_NAT=y CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y CONFIG_NETFILTER_XT_MARK=y +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_MANGLE=y |