diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf.h | 33 | ||||
| -rw-r--r-- | include/linux/if_macvlan.h | 3 | ||||
| -rw-r--r-- | include/linux/mlx5/qp.h | 7 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 2 | ||||
| -rw-r--r-- | include/linux/netfilter/x_tables.h | 7 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 1 | ||||
| -rw-r--r-- | include/linux/usermode_driver.h | 1 | ||||
| -rw-r--r-- | include/net/dst.h | 11 | ||||
| -rw-r--r-- | include/net/inet_connection_sock.h | 2 | ||||
| -rw-r--r-- | include/net/netfilter/nf_tables.h | 3 | ||||
| -rw-r--r-- | include/net/nexthop.h | 24 | ||||
| -rw-r--r-- | include/net/red.h | 12 | ||||
| -rw-r--r-- | include/net/rtnetlink.h | 2 | ||||
| -rw-r--r-- | include/net/sock.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 16 | ||||
| -rw-r--r-- | include/uapi/linux/psample.h | 5 |
16 files changed, 104 insertions, 27 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cccaef1088ea..3625f019767d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -21,6 +21,7 @@ #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> +#include <linux/percpu-refcount.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -556,7 +557,8 @@ struct bpf_tramp_progs { * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ -int arch_prepare_bpf_trampoline(void *image, void *image_end, +struct bpf_tramp_image; +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call); @@ -565,6 +567,8 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); +void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); +void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); struct bpf_ksym { unsigned long start; @@ -583,6 +587,18 @@ enum bpf_tramp_prog_type { BPF_TRAMP_REPLACE, /* more than MAX */ }; +struct bpf_tramp_image { + void *image; + struct bpf_ksym ksym; + struct percpu_ref pcref; + void *ip_after_call; + void *ip_epilogue; + union { + struct rcu_head rcu; + struct work_struct work; + }; +}; + struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; @@ -605,9 +621,8 @@ struct bpf_trampoline { /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ - void *image; + struct bpf_tramp_image *cur_image; u64 selector; - struct bpf_ksym ksym; }; struct bpf_attach_target_info { @@ -691,6 +706,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); +int bpf_jit_charge_modmem(u32 pages); +void bpf_jit_uncharge_modmem(u32 pages); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -787,7 +804,6 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; - enum bpf_tramp_prog_type trampoline_prog_type; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -1093,7 +1109,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, _ret; \ }) -#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ +#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \ ({ \ struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ @@ -1106,7 +1122,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, goto _out; \ _item = &_array->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ + if (set_cg_storage) \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ _ret &= func(_prog, ctx); \ _item++; \ } \ @@ -1153,10 +1170,10 @@ _out: \ }) #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, false) + __BPF_PROG_RUN_ARRAY(array, ctx, func, false, true) #define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, true) + __BPF_PROG_RUN_ARRAY(array, ctx, func, true, false) #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 96556c64c95d..10c94a3936ca 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -43,13 +43,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, if (likely(success)) { struct vlan_pcpu_stats *pcpu_stats; - pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); + pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); pcpu_stats->rx_packets++; pcpu_stats->rx_bytes += len; if (multicast) pcpu_stats->rx_multicast++; u64_stats_update_end(&pcpu_stats->syncp); + put_cpu_ptr(vlan->pcpu_stats); } else { this_cpu_inc(vlan->pcpu_stats->rx_errors); } diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index d75ef8aa8fac..b7deb790f257 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -547,4 +547,11 @@ static inline const char *mlx5_qp_state_str(int state) } } +static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev) +{ + return !MLX5_CAP_ROCE(dev, qp_ts_format) ? + MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; +} + #endif /* MLX5_QP_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b67ea89d5f2..87a5d186faff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -360,6 +360,7 @@ enum { NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ + NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ }; enum { @@ -372,6 +373,7 @@ enum { NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), + NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), }; enum gro_result { diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 8ebb64193757..8ec48466410a 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -227,7 +227,7 @@ struct xt_table { unsigned int valid_hooks; /* Man behind the curtain... */ - struct xt_table_info __rcu *private; + struct xt_table_info *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -376,7 +376,7 @@ static inline unsigned int xt_write_recseq_begin(void) * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); - smp_wmb(); + smp_mb(); return addend; } @@ -448,9 +448,6 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); -struct xt_table_info -*xt_table_get_private_protected(const struct xt_table *table); - #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6d0a33d1c0db..f2c9ee71cb2c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -285,6 +285,7 @@ struct nf_bridge_info { struct tc_skb_ext { __u32 chain; __u16 mru; + bool post_ct; }; #endif diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index 073a9e0ec07d..ad970416260d 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -14,5 +14,6 @@ struct umd_info { int umd_load_blob(struct umd_info *info, const void *data, size_t len); int umd_unload_blob(struct umd_info *info); int fork_usermode_driver(struct umd_info *info); +void umd_cleanup_helper(struct umd_info *info); #endif /* __LINUX_USERMODE_DRIVER_H__ */ diff --git a/include/net/dst.h b/include/net/dst.h index 26f134ad3a25..75b1e734e9c2 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -550,4 +550,15 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, bool confirm_neigh); +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); +unsigned int dst_blackhole_mtu(const struct dst_entry *dst); + #endif /* _NET_DST_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 10a625760de9..3c8c59471bc1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; } -void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fdec57d862b7..5aaced6bf13e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1536,6 +1536,7 @@ struct nft_trans_flowtable { struct nft_flowtable *flowtable; bool update; struct list_head hook_list; + u32 flags; }; #define nft_trans_flowtable(trans) \ @@ -1544,6 +1545,8 @@ struct nft_trans_flowtable { (((struct nft_trans_flowtable *)trans->data)->update) #define nft_trans_flowtable_hooks(trans) \ (((struct nft_trans_flowtable *)trans->data)->hook_list) +#define nft_trans_flowtable_flags(trans) \ + (((struct nft_trans_flowtable *)trans->data)->flags) int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7bc057aee40b..a10a319d7eb2 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -410,6 +410,7 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); +/* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; @@ -430,6 +431,29 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } +/* Variant of nexthop_fib6_nh(). + * Caller should either hold rcu_read_lock_bh(), or RTNL. + */ +static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) +{ + struct nh_info *nhi; + + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp); + nh = nexthop_mpath_select(nh_grp, 0); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_bh_rtnl(nh->nh_info); + if (nhi->family == AF_INET6) + return &nhi->fib6_nh; + + return NULL; +} + static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/include/net/red.h b/include/net/red.h index 932f0d79d60c..0b39eff1d50a 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -168,7 +168,8 @@ static inline void red_set_vars(struct red_vars *v) v->qcount = -1; } -static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log) +static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, + u8 Scell_log, u8 *stab) { if (fls(qth_min) + Wlog > 32) return false; @@ -178,6 +179,13 @@ static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_ return false; if (qth_max < qth_min) return false; + if (stab) { + int i; + + for (i = 0; i < RED_STAB_SIZE; i++) + if (stab[i] >= 32) + return false; + } return true; } @@ -287,7 +295,7 @@ static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms int shift; /* - * The problem: ideally, average length queue recalcultion should + * The problem: ideally, average length queue recalculation should * be done over constant clock intervals. This is too expensive, so * that the calculation is driven by outgoing packets. * When the queue is idle we have to model this clock by hand. diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index e2091bb2b3a8..4da61c950e93 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -33,6 +33,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * * @list: Used internally * @kind: Identifier + * @netns_refund: Physical device, move to init_net on netns exit * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -64,6 +65,7 @@ struct rtnl_link_ops { size_t priv_size; void (*setup)(struct net_device *dev); + bool netns_refund; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], diff --git a/include/net/sock.h b/include/net/sock.h index 636810ddcd9b..0b6266fd6bf6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -936,7 +936,7 @@ static inline void sk_acceptq_added(struct sock *sk) static inline bool sk_acceptq_is_full(const struct sock *sk) { - return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); + return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); } /* diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 79c893310492..4ba4ef0ff63a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3850,7 +3850,7 @@ union bpf_attr { * * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) * Description - * Check ctx packet size against exceeding MTU of net device (based + * Check packet size against exceeding MTU of net device (based * on *ifindex*). This helper will likely be used in combination * with helpers that adjust/change the packet size. * @@ -3867,6 +3867,14 @@ union bpf_attr { * against the current net device. This is practical if this isn't * used prior to redirect. * + * On input *mtu_len* must be a valid pointer, else verifier will + * reject BPF program. If the value *mtu_len* is initialized to + * zero then the ctx packet size is use. When value *mtu_len* is + * provided as input this specify the L3 length that the MTU check + * is done against. Remember XDP and TC length operate at L2, but + * this value is L3 as this correlate to MTU and IP-header tot_len + * values which are L3 (similar behavior as bpf_fib_lookup). + * * The Linux kernel route table can configure MTUs on a more * specific per route level, which is not provided by this helper. * For route level MTU checks use the **bpf_fib_lookup**\ () @@ -3891,11 +3899,9 @@ union bpf_attr { * * On return *mtu_len* pointer contains the MTU value of the net * device. Remember the net device configured MTU is the L3 size, - * which is returned here and XDP and TX length operate at L2. + * which is returned here and XDP and TC length operate at L2. * Helper take this into account for you, but remember when using - * MTU value in your BPF-code. On input *mtu_len* must be a valid - * pointer and be initialized (to zero), else verifier will reject - * BPF program. + * MTU value in your BPF-code. * * Return * * 0 on success, and populate MTU value in *mtu_len* pointer. diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index aea26ab1431c..bff5032c98df 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -3,7 +3,6 @@ #define __UAPI_PSAMPLE_H enum { - /* sampled packet metadata */ PSAMPLE_ATTR_IIFINDEX, PSAMPLE_ATTR_OIFINDEX, PSAMPLE_ATTR_ORIGSIZE, @@ -11,10 +10,8 @@ enum { PSAMPLE_ATTR_GROUP_SEQ, PSAMPLE_ATTR_SAMPLE_RATE, PSAMPLE_ATTR_DATA, - PSAMPLE_ATTR_TUNNEL, - - /* commands attributes */ PSAMPLE_ATTR_GROUP_REFCOUNT, + PSAMPLE_ATTR_TUNNEL, __PSAMPLE_ATTR_MAX }; |