diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf.h | 128 | ||||
| -rw-r--r-- | include/linux/bpf_types.h | 9 | ||||
| -rw-r--r-- | include/linux/bpf_verifier.h | 10 | ||||
| -rw-r--r-- | include/linux/btf.h | 52 | ||||
| -rw-r--r-- | include/linux/filter.h | 12 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 13 | ||||
| -rw-r--r-- | include/net/sock.h | 2 | ||||
| -rw-r--r-- | include/net/tcp.h | 2 | ||||
| -rw-r--r-- | include/trace/events/xdp.h | 130 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 72 | ||||
| -rw-r--r-- | include/uapi/linux/btf.h | 6 |
11 files changed, 343 insertions, 93 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b14e51d56a82..a9687861fd7e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -17,6 +17,7 @@ #include <linux/u64_stats_sync.h> #include <linux/refcount.h> #include <linux/mutex.h> +#include <linux/module.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -43,6 +44,15 @@ struct bpf_map_ops { int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); + int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); + int (*map_lookup_and_delete_batch)(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); + int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); + int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); @@ -106,6 +116,7 @@ struct bpf_map { struct btf *btf; struct bpf_map_memory memory; char name[BPF_OBJ_NAME_LEN]; + u32 btf_vmlinux_value_type_id; bool unpriv_array; bool frozen; /* write-once; write-protected by freeze_mutex */ /* 22 bytes hole */ @@ -183,7 +194,8 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map) static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { - return map->btf && map->ops->map_seq_show_elem; + return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && + map->ops->map_seq_show_elem; } int map_check_no_btf(const struct bpf_map *map, @@ -349,6 +361,10 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); + int (*btf_struct_access)(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id); }; struct bpf_prog_offload_ops { @@ -437,7 +453,8 @@ struct btf_func_model { * 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, struct btf_func_model *m, u32 flags, +int arch_prepare_bpf_trampoline(void *image, void *image_end, + const struct btf_func_model *m, u32 flags, struct bpf_prog **fentry_progs, int fentry_cnt, struct bpf_prog **fexit_progs, int fexit_cnt, void *orig_call); @@ -448,7 +465,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, - BPF_TRAMP_MAX + BPF_TRAMP_MAX, + BPF_TRAMP_REPLACE, /* more than MAX */ }; struct bpf_trampoline { @@ -463,6 +481,11 @@ struct bpf_trampoline { void *addr; bool ftrace_managed; } func; + /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF + * program by replacing one of its functions. func.addr is the address + * of the function it replaced. + */ + struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ @@ -558,6 +581,7 @@ static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, #endif struct bpf_func_info_aux { + u16 linkage; bool unreliable; }; @@ -668,6 +692,73 @@ struct bpf_array_aux { struct work_struct work; }; +struct bpf_struct_ops_value; +struct btf_type; +struct btf_member; + +#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 +struct bpf_struct_ops { + const struct bpf_verifier_ops *verifier_ops; + int (*init)(struct btf *btf); + int (*check_member)(const struct btf_type *t, + const struct btf_member *member); + int (*init_member)(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata); + int (*reg)(void *kdata); + void (*unreg)(void *kdata); + const struct btf_type *type; + const struct btf_type *value_type; + const char *name; + struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; + u32 type_id; + u32 value_id; +}; + +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +#define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) +const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); +void bpf_struct_ops_init(struct btf *btf); +bool bpf_struct_ops_get(const void *kdata); +void bpf_struct_ops_put(const void *kdata); +int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, + void *value); +static inline bool bpf_try_module_get(const void *data, struct module *owner) +{ + if (owner == BPF_MODULE_OWNER) + return bpf_struct_ops_get(data); + else + return try_module_get(owner); +} +static inline void bpf_module_put(const void *data, struct module *owner) +{ + if (owner == BPF_MODULE_OWNER) + bpf_struct_ops_put(data); + else + module_put(owner); +} +#else +static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +{ + return NULL; +} +static inline void bpf_struct_ops_init(struct btf *btf) { } +static inline bool bpf_try_module_get(const void *data, struct module *owner) +{ + return try_module_get(owner); +} +static inline void bpf_module_put(const void *data, struct module *owner) +{ + module_put(owner); +} +static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, + void *key, + void *value) +{ + return -EINVAL; +} +#endif + struct bpf_array { struct bpf_map map; u32 elem_size; @@ -906,6 +997,15 @@ void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); +int generic_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); +int generic_map_update_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); +int generic_map_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); extern int sysctl_unprivileged_bpf_disabled; @@ -962,7 +1062,9 @@ struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_flush(void); +void __dev_flush(void); +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -1006,7 +1108,13 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); -int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); +struct bpf_reg_state; +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs); +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *reg); +int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, + struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); @@ -1071,7 +1179,7 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map return NULL; } -static inline void __dev_map_flush(void) +static inline void __dev_flush(void) { } @@ -1079,6 +1187,13 @@ struct xdp_buff; struct bpf_dtab_netdev; static inline +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} + +static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx) { @@ -1299,6 +1414,7 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; +extern const struct bpf_func_proto bpf_jiffies64_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 93740b3614d7..c81d4ece79a4 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -65,6 +65,12 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, struct sk_reuseport_md, struct sk_reuseport_kern) #endif +#if defined(CONFIG_BPF_JIT) +BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops, + void *, void *) +BPF_PROG_TYPE(BPF_PROG_TYPE_EXT, bpf_extension, + void *, void *) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) @@ -105,3 +111,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) +#if defined(CONFIG_BPF_JIT) +BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) +#endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 26e40de9ef55..5406e6e96585 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -304,11 +304,13 @@ struct bpf_insn_aux_data { u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ - bool seen; /* this insn was processed by the verifier */ + u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ - bool prune_point; + + /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ + bool prune_point; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -379,6 +381,7 @@ struct bpf_verifier_env { int *insn_stack; int cur_stack; } cfg; + u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ u32 prev_insn_processed, insn_processed; @@ -428,4 +431,7 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); +int check_ctx_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno); + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 79d4abc2556a..5c1ea99b480f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -7,6 +7,8 @@ #include <linux/types.h> #include <uapi/linux/btf.h> +#define BTF_TYPE_EMIT(type) ((void)(type *)0) + struct btf; struct btf_member; struct btf_type; @@ -53,6 +55,22 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); +s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); +const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, + u32 id, u32 *res_id); +const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, + u32 id, u32 *res_id); +const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, + u32 id, u32 *res_id); +const struct btf_type * +btf_resolve_size(const struct btf *btf, const struct btf_type *type, + u32 *type_size, const struct btf_type **elem_type, + u32 *total_nelems); + +#define for_each_member(i, struct_type, member) \ + for (i = 0, member = btf_type_member(struct_type); \ + i < btf_type_vlen(struct_type); \ + i++, member++) static inline bool btf_type_is_ptr(const struct btf_type *t) { @@ -84,6 +102,40 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; } +static inline u16 btf_type_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline u16 btf_func_linkage(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_type_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) +{ + return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) + : member->offset; +} + +static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) +{ + return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) + : 0; +} + +static inline const struct btf_member *btf_type_member(const struct btf_type *t) +{ + return (const struct btf_member *)(t + 1); +} + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); diff --git a/include/linux/filter.h b/include/linux/filter.h index 70e6dd960bca..f349e2c0884c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -843,6 +843,8 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); +const struct bpf_func_proto * +bpf_base_func_proto(enum bpf_func_id func_id); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); @@ -916,7 +918,7 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd, return 0; } -/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the +/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. @@ -927,7 +929,13 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); -void xdp_do_flush_map(void); +void xdp_do_flush(void); + +/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as + * it is no longer only flushing maps. Keep this define for compatibility + * until all drivers are updated - do not use xdp_do_flush_map() in new code! + */ +#define xdp_do_flush_map xdp_do_flush void bpf_warn_invalid_xdp_action(u32 act); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2741aa35bec6..5ec3537fbdb1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -876,6 +876,7 @@ enum bpf_netdev_command { struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; +struct xdp_dev_bulk_queue; struct netdev_bpf { enum bpf_netdev_command command; @@ -1986,12 +1987,10 @@ struct net_device { unsigned int num_tx_queues; unsigned int real_num_tx_queues; struct Qdisc *qdisc; -#ifdef CONFIG_NET_SCHED - DECLARE_HASHTABLE (qdisc_hash, 4); -#endif unsigned int tx_queue_len; spinlock_t tx_global_lock; - int watchdog_timeo; + + struct xdp_dev_bulk_queue __percpu *xdp_bulkq; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_cpus_map; @@ -2001,11 +2000,15 @@ struct net_device { struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NET_SCHED + DECLARE_HASHTABLE (qdisc_hash, 4); +#endif /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; + int watchdog_timeo; - int __percpu *pcpu_refcnt; struct list_head todo_list; + int __percpu *pcpu_refcnt; struct list_head link_watch_list; diff --git a/include/net/sock.h b/include/net/sock.h index 432ff73d20f3..02162b0378f7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2597,4 +2597,6 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) return false; } +void sock_def_readable(struct sock *sk); + #endif /* _SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 2869d28ed5d8..a5ea27df3c2b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1019,6 +1019,7 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NON_RESTRICTED 0x1 /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN 0x2 +#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; @@ -1113,6 +1114,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; +struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca); #ifdef CONFIG_INET diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index a7378bcd9928..b95d65e8c628 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -79,14 +79,26 @@ TRACE_EVENT(xdp_bulk_tx, __entry->sent, __entry->drops, __entry->err) ); +#ifndef __DEVMAP_OBJ_TYPE +#define __DEVMAP_OBJ_TYPE +struct _bpf_dtab_netdev { + struct net_device *dev; +}; +#endif /* __DEVMAP_OBJ_TYPE */ + +#define devmap_ifindex(tgt, map) \ + (((map->map_type == BPF_MAP_TYPE_DEVMAP || \ + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \ + ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0) + DECLARE_EVENT_CLASS(xdp_redirect_template, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, - int to_ifindex, int err, - const struct bpf_map *map, u32 map_index), + const void *tgt, int err, + const struct bpf_map *map, u32 index), - TP_ARGS(dev, xdp, to_ifindex, err, map, map_index), + TP_ARGS(dev, xdp, tgt, err, map, index), TP_STRUCT__entry( __field(int, prog_id) @@ -103,90 +115,65 @@ DECLARE_EVENT_CLASS(xdp_redirect_template, __entry->act = XDP_REDIRECT; __entry->ifindex = dev->ifindex; __entry->err = err; - __entry->to_ifindex = to_ifindex; + __entry->to_ifindex = map ? devmap_ifindex(tgt, map) : + index; __entry->map_id = map ? map->id : 0; - __entry->map_index = map_index; + __entry->map_index = map ? index : 0; ), - TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d", + TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d" + " map_id=%d map_index=%d", __entry->prog_id, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->ifindex, __entry->to_ifindex, - __entry->err) + __entry->err, __entry->map_id, __entry->map_index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, - int to_ifindex, int err, - const struct bpf_map *map, u32 map_index), - TP_ARGS(dev, xdp, to_ifindex, err, map, map_index) + const void *tgt, int err, + const struct bpf_map *map, u32 index), + TP_ARGS(dev, xdp, tgt, err, map, index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, - int to_ifindex, int err, - const struct bpf_map *map, u32 map_index), - TP_ARGS(dev, xdp, to_ifindex, err, map, map_index) + const void *tgt, int err, + const struct bpf_map *map, u32 index), + TP_ARGS(dev, xdp, tgt, err, map, index) ); #define _trace_xdp_redirect(dev, xdp, to) \ - trace_xdp_redirect(dev, xdp, to, 0, NULL, 0); + trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to); #define _trace_xdp_redirect_err(dev, xdp, to, err) \ - trace_xdp_redirect_err(dev, xdp, to, err, NULL, 0); + trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to); -DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map, +#define _trace_xdp_redirect_map(dev, xdp, to, map, index) \ + trace_xdp_redirect(dev, xdp, to, 0, map, index); + +#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err) \ + trace_xdp_redirect_err(dev, xdp, to, err, map, index); + +/* not used anymore, but kept around so as not to break old programs */ +DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, - int to_ifindex, int err, - const struct bpf_map *map, u32 map_index), - TP_ARGS(dev, xdp, to_ifindex, err, map, map_index), - TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d" - " map_id=%d map_index=%d", - __entry->prog_id, - __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), - __entry->ifindex, __entry->to_ifindex, - __entry->err, - __entry->map_id, __entry->map_index) + const void *tgt, int err, + const struct bpf_map *map, u32 index), + TP_ARGS(dev, xdp, tgt, err, map, index) ); -DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err, +DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, - int to_ifindex, int err, - const struct bpf_map *map, u32 map_index), - TP_ARGS(dev, xdp, to_ifindex, err, map, map_index), - TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d" - " map_id=%d map_index=%d", - __entry->prog_id, - __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), - __entry->ifindex, __entry->to_ifindex, - __entry->err, - __entry->map_id, __entry->map_index) + const void *tgt, int err, + const struct bpf_map *map, u32 index), + TP_ARGS(dev, xdp, tgt, err, map, index) ); -#ifndef __DEVMAP_OBJ_TYPE -#define __DEVMAP_OBJ_TYPE -struct _bpf_dtab_netdev { - struct net_device *dev; -}; -#endif /* __DEVMAP_OBJ_TYPE */ - -#define devmap_ifindex(fwd, map) \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP || \ - map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \ - ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) - -#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ - trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ - 0, map, idx) - -#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \ - trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \ - err, map, idx) - TRACE_EVENT(xdp_cpumap_kthread, TP_PROTO(int map_id, unsigned int processed, unsigned int drops, @@ -259,43 +246,38 @@ TRACE_EVENT(xdp_cpumap_enqueue, TRACE_EVENT(xdp_devmap_xmit, - TP_PROTO(const struct bpf_map *map, u32 map_index, - int sent, int drops, - const struct net_device *from_dev, - const struct net_device *to_dev, int err), + TP_PROTO(const struct net_device *from_dev, + const struct net_device *to_dev, + int sent, int drops, int err), - TP_ARGS(map, map_index, sent, drops, from_dev, to_dev, err), + TP_ARGS(from_dev, to_dev, sent, drops, err), TP_STRUCT__entry( - __field(int, map_id) + __field(int, from_ifindex) __field(u32, act) - __field(u32, map_index) + __field(int, to_ifindex) __field(int, drops) __field(int, sent) - __field(int, from_ifindex) - __field(int, to_ifindex) __field(int, err) ), TP_fast_assign( - __entry->map_id = map->id; + __entry->from_ifindex = from_dev->ifindex; __entry->act = XDP_REDIRECT; - __entry->map_index = map_index; + __entry->to_ifindex = to_dev->ifindex; __entry->drops = drops; __entry->sent = sent; - __entry->from_ifindex = from_dev->ifindex; - __entry->to_ifindex = to_dev->ifindex; __entry->err = err; ), TP_printk("ndo_xdp_xmit" - " map_id=%d map_index=%d action=%s" + " from_ifindex=%d to_ifindex=%d action=%s" " sent=%d drops=%d" - " from_ifindex=%d to_ifindex=%d err=%d", - __entry->map_id, __entry->map_index, + " err=%d", + __entry->from_ifindex, __entry->to_ifindex, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), __entry->sent, __entry->drops, - __entry->from_ifindex, __entry->to_ifindex, __entry->err) + __entry->err) ); /* Expect users already include <net/xdp.h>, but not xdp_priv.h */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7df436da542d..f1d74a2bd234 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -107,6 +107,10 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, }; enum bpf_map_type { @@ -136,6 +140,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, + BPF_MAP_TYPE_STRUCT_OPS, }; /* Note that tracing related programs such as @@ -174,6 +179,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_PROG_TYPE_TRACING, + BPF_PROG_TYPE_STRUCT_OPS, + BPF_PROG_TYPE_EXT, }; enum bpf_attach_type { @@ -357,7 +364,12 @@ enum bpf_attach_type { /* Enable memory-mapping BPF map */ #define BPF_F_MMAPABLE (1U << 10) -/* flags for BPF_PROG_QUERY */ +/* Flags for BPF_PROG_QUERY. */ + +/* Query effective (directly attached + inherited from ancestor cgroups) + * programs that will be executed for events within a cgroup. + * attach_flags with this flag are returned only for directly attached programs. + */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) enum bpf_stack_build_id_status { @@ -397,6 +409,10 @@ union bpf_attr { __u32 btf_fd; /* fd pointing to a BTF type data */ __u32 btf_key_type_id; /* BTF type_id of the key */ __u32 btf_value_type_id; /* BTF type_id of the value */ + __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel- + * struct stored as the + * map value + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -409,6 +425,23 @@ union bpf_attr { __u64 flags; }; + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + struct { /* anonymous struct used by BPF_PROG_LOAD command */ __u32 prog_type; /* one of enum bpf_prog_type */ __u32 insn_cnt; @@ -2703,7 +2736,8 @@ union bpf_attr { * * int bpf_send_signal(u32 sig) * Description - * Send signal *sig* to the current task. + * Send signal *sig* to the process of the current task. + * The signal may be delivered to any of this process's threads. * Return * 0 on success or successfully queued. * @@ -2831,6 +2865,33 @@ union bpf_attr { * Return * On success, the strictly positive length of the string, including * the trailing NUL character. On error, a negative value. + * + * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt) + * Description + * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock. + * *rcv_nxt* is the ack_seq to be sent out. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_send_signal_thread(u32 sig) + * Description + * Send signal *sig* to the thread corresponding to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * u64 bpf_jiffies64(void) + * Description + * Obtain the 64bit jiffies + * Return + * The 64 bit jiffies */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2948,7 +3009,10 @@ union bpf_attr { FN(probe_read_user), \ FN(probe_read_kernel), \ FN(probe_read_user_str), \ - FN(probe_read_kernel_str), + FN(probe_read_kernel_str), \ + FN(tcp_send_ack), \ + FN(send_signal_thread), \ + FN(jiffies64), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3349,7 +3413,7 @@ struct bpf_map_info { __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; - __u32 :32; + __u32 btf_vmlinux_value_type_id; __u64 netns_dev; __u64 netns_ino; __u32 btf_id; diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 1a2898c482ee..5a667107ad2c 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -146,6 +146,12 @@ enum { BTF_VAR_GLOBAL_EXTERN = 2, }; +enum btf_func_linkage { + BTF_FUNC_STATIC = 0, + BTF_FUNC_GLOBAL = 1, + BTF_FUNC_EXTERN = 2, +}; + /* BTF_KIND_VAR is followed by a single "struct btf_var" to describe * additional information related to the variable such as its linkage. */ |