diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf.h | 94 | ||||
| -rw-r--r-- | include/linux/bpf_local_storage.h | 3 | ||||
| -rw-r--r-- | include/linux/bpf_lsm.h | 22 | ||||
| -rw-r--r-- | include/linux/bpf_types.h | 8 | ||||
| -rw-r--r-- | include/linux/bpf_verifier.h | 3 | ||||
| -rw-r--r-- | include/linux/filter.h | 31 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 5 | ||||
| -rw-r--r-- | include/linux/sched.h | 5 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 4 | ||||
| -rw-r--r-- | include/linux/skmsg.h | 82 | ||||
| -rw-r--r-- | include/net/tcp.h | 41 | ||||
| -rw-r--r-- | include/net/udp.h | 4 | ||||
| -rw-r--r-- | include/net/xdp_sock.h | 19 | ||||
| -rw-r--r-- | include/trace/events/xdp.h | 62 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 762 | ||||
| -rw-r--r-- | include/uapi/linux/btf.h | 5 |
16 files changed, 979 insertions, 171 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cccaef1088ea..a25730eaa148 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,6 +39,7 @@ struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; +struct bpf_func_state; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -117,6 +118,9 @@ struct bpf_map_ops { void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); + /* Misc helpers.*/ + int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags); + /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure * an inner map can be inserted to an outer map. @@ -129,6 +133,13 @@ struct bpf_map_ops { bool (*map_meta_equal)(const struct bpf_map *meta0, const struct bpf_map *meta1); + + int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee); + int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn, + void *callback_ctx, u64 flags); + /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; @@ -295,6 +306,8 @@ enum bpf_arg_type { ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ + ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ + ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ __BPF_ARG_TYPE_MAX, }; @@ -411,6 +424,8 @@ enum bpf_reg_type { PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ + PTR_TO_FUNC, /* reg points to a bpf program function */ + PTR_TO_MAP_KEY, /* reg points to a map element key */ }; /* The information passed from prog-specific *_is_valid_access @@ -506,6 +521,11 @@ enum bpf_cgroup_storage_type { */ #define MAX_BPF_FUNC_ARGS 12 +/* The maximum number of arguments passed through registers + * a single function may have. + */ +#define MAX_BPF_FUNC_REG_ARGS 5 + struct btf_func_model { u8 ret_size; u8 nr_args; @@ -1380,6 +1400,10 @@ void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); +int map_set_for_each_callback_args(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee); + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, @@ -1429,9 +1453,9 @@ struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ struct xdp_buff; struct sk_buff; +struct bpf_dtab_netdev; +struct bpf_cpu_map_entry; -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_flush(void); int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -1441,7 +1465,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); bool dev_map_can_have_prog(struct bpf_map *map); -struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -1470,6 +1493,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1499,6 +1525,7 @@ struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); +void bpf_task_storage_free(struct task_struct *task); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1568,17 +1595,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } -static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, - u32 key) -{ - return NULL; -} - -static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map, - u32 key) -{ - return NULL; -} static inline bool dev_map_can_have_prog(struct bpf_map *map) { return false; @@ -1590,6 +1606,7 @@ static inline void __dev_flush(void) struct xdp_buff; struct bpf_dtab_netdev; +struct bpf_cpu_map_entry; static inline int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, @@ -1614,12 +1631,6 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, return 0; } -static inline -struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) -{ - return NULL; -} - static inline void __cpu_map_flush(void) { } @@ -1670,6 +1681,13 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, return -ENOTSUPP; } +static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + static inline void bpf_map_put(struct bpf_map *map) { } @@ -1684,6 +1702,10 @@ bpf_base_func_proto(enum bpf_func_id func_id) { return NULL; } + +static inline void bpf_task_storage_free(struct task_struct *task) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -1768,22 +1790,24 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) } #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -#if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which); +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); + +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); #else -static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, - struct bpf_prog *old, u32 which) +static inline void bpf_sk_reuseport_detach(struct sock *sk) { - return -EOPNOTSUPP; } +#ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { @@ -1801,20 +1825,7 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } -#endif /* CONFIG_BPF_STREAM_PARSER */ -#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -void bpf_sk_reuseport_detach(struct sock *sk); -int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, - void *value); -int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags); -#else -static inline void bpf_sk_reuseport_detach(struct sock *sk) -{ -} - -#ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { @@ -1886,6 +1897,9 @@ extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; +extern const struct bpf_func_proto bpf_task_storage_get_proto; +extern const struct bpf_func_proto bpf_task_storage_delete_proto; +extern const struct bpf_func_proto bpf_for_each_map_elem_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index b2c9463f36a1..b902c580c48d 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -126,7 +126,8 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit); -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, + int __percpu *busy_counter); int bpf_local_storage_map_check_btf(const struct bpf_map *map, const struct btf *btf, diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 0d1c33ace398..479c101546ad 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -38,21 +38,9 @@ static inline struct bpf_storage_blob *bpf_inode( return inode->i_security + bpf_lsm_blob_sizes.lbs_inode; } -static inline struct bpf_storage_blob *bpf_task( - const struct task_struct *task) -{ - if (unlikely(!task->security)) - return NULL; - - return task->security + bpf_lsm_blob_sizes.lbs_task; -} - extern const struct bpf_func_proto bpf_inode_storage_get_proto; extern const struct bpf_func_proto bpf_inode_storage_delete_proto; -extern const struct bpf_func_proto bpf_task_storage_get_proto; -extern const struct bpf_func_proto bpf_task_storage_delete_proto; void bpf_inode_storage_free(struct inode *inode); -void bpf_task_storage_free(struct task_struct *task); #else /* !CONFIG_BPF_LSM */ @@ -73,20 +61,10 @@ static inline struct bpf_storage_blob *bpf_inode( return NULL; } -static inline struct bpf_storage_blob *bpf_task( - const struct task_struct *task) -{ - return NULL; -} - static inline void bpf_inode_storage_free(struct inode *inode) { } -static inline void bpf_task_storage_free(struct task_struct *task) -{ -} - #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 99f7fd657d87..f883f01a5061 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -103,19 +103,17 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) -#if defined(CONFIG_BPF_STREAM_PARSER) -BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) -#endif #ifdef CONFIG_BPF_LSM BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) #endif #ifdef CONFIG_INET +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 971b33aca13d..51c2ffa3d901 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -68,6 +68,8 @@ struct bpf_reg_state { unsigned long raw1; unsigned long raw2; } raw; + + u32 subprogno; /* for PTR_TO_FUNC */ }; /* For PTR_TO_PACKET, used to find other pointers with the same variable * offset, so they can share range knowledge. @@ -204,6 +206,7 @@ struct bpf_func_state { int acquired_refs; struct bpf_reference_state *refs; int allocated_stack; + bool in_callback_fn; struct bpf_stack_state *stack; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 3b00fc906ccd..b2b85b2cad8e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -646,7 +646,8 @@ struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; - struct bpf_map *map; + u32 map_id; + enum bpf_map_type map_type; u32 kern_flags; struct bpf_nh_params nh; }; @@ -1472,4 +1473,32 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags, + void *lookup_elem(struct bpf_map *map, u32 key)) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + /* Lower bits of the flags are used as return code on lookup failure */ + if (unlikely(flags > XDP_TX)) + return XDP_ABORTED; + + ri->tgt_value = lookup_elem(map, ifindex); + if (unlikely(!ri->tgt_value)) { + /* If the lookup fails we want to clear out the state in the + * redirect_info struct completely, so that if an eBPF program + * performs multiple lookups, the last one always takes + * precedence. + */ + ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ + ri->map_type = BPF_MAP_TYPE_UNSPEC; + return flags; + } + + ri->tgt_index = ifindex; + ri->map_id = map->id; + ri->map_type = map->map_type; + + return XDP_REDIRECT; +} + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b67ea89d5f2..b379d08a12ed 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1518,6 +1518,8 @@ struct net_device_ops { * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running + * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with + * skb_headlen(skb) == 0 (data starts from frag0) */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1551,6 +1553,7 @@ enum netdev_priv_flags { IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, + IFF_TX_SKB_NO_LINEAR = 1<<31, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1577,12 +1580,14 @@ enum netdev_priv_flags { #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED +#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM #define IFF_MACSEC IFF_MACSEC #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER #define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK +#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { diff --git a/include/linux/sched.h b/include/linux/sched.h index ef00bb22164c..e5b7d9054473 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -42,6 +42,7 @@ struct audit_context; struct backing_dev_info; struct bio_list; struct blk_plug; +struct bpf_local_storage; struct capture_control; struct cfs_rq; struct fs_struct; @@ -1351,6 +1352,10 @@ struct task_struct { /* Used by LSM modules for access restriction: */ void *security; #endif +#ifdef CONFIG_BPF_SYSCALL + /* Used by BPF task local storage */ + struct bpf_local_storage __rcu *bpf_storage; +#endif #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6d0a33d1c0db..0503c917d773 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -656,6 +656,7 @@ typedef unsigned char *sk_buff_data_t; * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) + * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on @@ -755,6 +756,9 @@ struct sk_buff { void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; +#ifdef CONFIG_NET_SOCK_MSG + unsigned long _sk_redir; +#endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 8edbbf5f2f93..6c09d94be2e9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -56,8 +56,8 @@ struct sk_msg { struct sk_psock_progs { struct bpf_prog *msg_parser; - struct bpf_prog *skb_parser; - struct bpf_prog *skb_verdict; + struct bpf_prog *stream_parser; + struct bpf_prog *stream_verdict; }; enum sk_psock_state_bits { @@ -70,12 +70,6 @@ struct sk_psock_link { void *link_raw; }; -struct sk_psock_parser { - struct strparser strp; - bool enabled; - void (*saved_data_ready)(struct sock *sk); -}; - struct sk_psock_work_state { struct sk_buff *skb; u32 len; @@ -90,7 +84,9 @@ struct sk_psock { u32 eval; struct sk_msg *cork; struct sk_psock_progs progs; - struct sk_psock_parser parser; +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) + struct strparser strp; +#endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; unsigned long state; @@ -100,6 +96,7 @@ struct sk_psock { void (*saved_unhash)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); + void (*saved_data_ready)(struct sock *sk); struct proto *sk_proto; struct sk_psock_work_state work_state; struct work_struct work; @@ -305,9 +302,25 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) struct sk_psock *sk_psock_init(struct sock *sk, int node); +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); +#else +static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) +{ + return -EOPNOTSUPP; +} + +static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) +{ +} + +static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) +{ +} +#endif + void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); @@ -327,8 +340,6 @@ static inline void sk_psock_free_link(struct sk_psock_link *link) struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); -void __sk_psock_purge_ingress_msg(struct sk_psock *psock); - static inline void sk_psock_cork_free(struct sk_psock *psock) { if (psock->cork) { @@ -389,7 +400,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk) return psock; } -void sk_psock_stop(struct sock *sk, struct sk_psock *psock); void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) @@ -400,8 +410,8 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { - if (psock->parser.enabled) - psock->parser.saved_data_ready(sk); + if (psock->saved_data_ready) + psock->saved_data_ready(sk); else sk->sk_data_ready(sk); } @@ -430,8 +440,8 @@ static inline int psock_replace_prog(struct bpf_prog **pprog, static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); - psock_set_prog(&progs->skb_parser, NULL); - psock_set_prog(&progs->skb_verdict, NULL); + psock_set_prog(&progs->stream_parser, NULL); + psock_set_prog(&progs->stream_verdict, NULL); } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); @@ -440,6 +450,44 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) { if (!psock) return false; - return psock->parser.enabled; + return !!psock->saved_data_ready; +} + +#if IS_ENABLED(CONFIG_NET_SOCK_MSG) + +/* We only have one bit so far. */ +#define BPF_F_PTR_MASK ~(BPF_F_INGRESS) + +static inline bool skb_bpf_ingress(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return sk_redir & BPF_F_INGRESS; +} + +static inline void skb_bpf_set_ingress(struct sk_buff *skb) +{ + skb->_sk_redir |= BPF_F_INGRESS; +} + +static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir, + bool ingress) +{ + skb->_sk_redir = (unsigned long)sk_redir; + if (ingress) + skb->_sk_redir |= BPF_F_INGRESS; +} + +static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return (struct sock *)(sk_redir & BPF_F_PTR_MASK); +} + +static inline void skb_bpf_redirect_clear(struct sk_buff *skb) +{ + skb->_sk_redir = 0; } +#endif /* CONFIG_NET_SOCK_MSG */ #endif /* _LINUX_SKMSG_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 963cd86d12dd..075de26f449d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -883,36 +883,11 @@ struct tcp_skb_cb { struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ - struct { - __u32 flags; - struct sock *sk_redir; - void *data_end; - } bpf; }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) -static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) -{ - TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); -} - -static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) -{ - return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; -} - -static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) -{ - return TCP_SKB_CB(skb)->bpf.sk_redir; -} - -static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) -{ - TCP_SKB_CB(skb)->bpf.sk_redir = NULL; -} - extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) @@ -2222,25 +2197,27 @@ void tcp_update_ulp(struct sock *sk, struct proto *p, __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) +#ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; -#ifdef CONFIG_BPF_STREAM_PARSER +#ifdef CONFIG_BPF_SYSCALL struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); -#else -static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) -{ -} -#endif /* CONFIG_BPF_STREAM_PARSER */ +#endif /* CONFIG_BPF_SYSCALL */ -#ifdef CONFIG_NET_SOCK_MSG int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) +static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ +} +#endif + #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, diff --git a/include/net/udp.h b/include/net/udp.h index a132a02b2f2c..d4d064c59232 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -515,9 +515,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, return segs; } -#ifdef CONFIG_BPF_STREAM_PARSER +#ifdef CONFIG_BPF_SYSCALL struct sk_psock; struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); -#endif /* BPF_STREAM_PARSER */ +#endif #endif /* _UDP_H */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index cc17bc957548..9c0722c6d7ac 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -80,19 +80,6 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); void __xsk_map_flush(void); -static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, - u32 key) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs; - - if (key >= map->max_entries) - return NULL; - - xs = READ_ONCE(m->xsk_map[key]); - return xs; -} - #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) @@ -109,12 +96,6 @@ static inline void __xsk_map_flush(void) { } -static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, - u32 key) -{ - return NULL; -} - #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 76a97176ab81..fcad3645a70b 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -86,19 +86,15 @@ struct _bpf_dtab_netdev { }; #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, const void *tgt, int err, - const struct bpf_map *map, u32 index), + enum bpf_map_type map_type, + u32 map_id, u32 index), - TP_ARGS(dev, xdp, tgt, err, map, index), + TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index), TP_STRUCT__entry( __field(int, prog_id) @@ -111,14 +107,22 @@ DECLARE_EVENT_CLASS(xdp_redirect_template, ), TP_fast_assign( + u32 ifindex = 0, map_index = index; + + if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex; + } else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { + ifindex = index; + map_index = 0; + } + __entry->prog_id = xdp->aux->id; __entry->act = XDP_REDIRECT; __entry->ifindex = dev->ifindex; __entry->err = err; - __entry->to_ifindex = map ? devmap_ifindex(tgt, map) : - index; - __entry->map_id = map ? map->id : 0; - __entry->map_index = map ? index : 0; + __entry->to_ifindex = ifindex; + __entry->map_id = map_id; + __entry->map_index = map_index; ), TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d" @@ -133,45 +137,49 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, - const struct bpf_map *map, u32 index), - TP_ARGS(dev, xdp, tgt, err, map, index) + enum bpf_map_type map_type, + u32 map_id, u32 index), + TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, - const struct bpf_map *map, u32 index), - TP_ARGS(dev, xdp, tgt, err, map, index) + enum bpf_map_type map_type, + u32 map_id, u32 index), + TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); -#define _trace_xdp_redirect(dev, xdp, to) \ - trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to) +#define _trace_xdp_redirect(dev, xdp, to) \ + trace_xdp_redirect(dev, xdp, NULL, 0, BPF_MAP_TYPE_UNSPEC, INT_MAX, to) -#define _trace_xdp_redirect_err(dev, xdp, to, err) \ - trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to) +#define _trace_xdp_redirect_err(dev, xdp, to, err) \ + trace_xdp_redirect_err(dev, xdp, NULL, err, BPF_MAP_TYPE_UNSPEC, INT_MAX, to) -#define _trace_xdp_redirect_map(dev, xdp, to, map, index) \ - trace_xdp_redirect(dev, xdp, to, 0, map, index) +#define _trace_xdp_redirect_map(dev, xdp, to, map_type, map_id, index) \ + trace_xdp_redirect(dev, xdp, to, 0, map_type, map_id, index) -#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err) \ - trace_xdp_redirect_err(dev, xdp, to, err, map, index) +#define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \ + trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, 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, const void *tgt, int err, - const struct bpf_map *map, u32 index), - TP_ARGS(dev, xdp, tgt, err, map, index) + enum bpf_map_type map_type, + u32 map_id, u32 index), + TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err, TP_PROTO(const struct net_device *dev, const struct bpf_prog *xdp, const void *tgt, int err, - const struct bpf_map *map, u32 index), - TP_ARGS(dev, xdp, tgt, err, map, index) + enum bpf_map_type map_type, + u32 map_id, u32 index), + TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index) ); TRACE_EVENT(xdp_cpumap_kthread, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 79c893310492..2d3036e292a9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -93,7 +93,717 @@ union bpf_iter_link_info { } map; }; -/* BPF syscall commands, see bpf(2) man-page for details. */ +/* BPF syscall commands, see bpf(2) man-page for more details. */ +/** + * DOC: eBPF Syscall Preamble + * + * The operation to be performed by the **bpf**\ () system call is determined + * by the *cmd* argument. Each operation takes an accompanying argument, + * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see + * below). The size argument is the size of the union pointed to by *attr*. + */ +/** + * DOC: eBPF Syscall Commands + * + * BPF_MAP_CREATE + * Description + * Create a map and return a file descriptor that refers to the + * map. The close-on-exec file descriptor flag (see **fcntl**\ (2)) + * is automatically enabled for the new file descriptor. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_MAP_CREATE** will delete the map (but see NOTES). + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_MAP_LOOKUP_ELEM + * Description + * Look up an element with a given *key* in the map referred to + * by the file descriptor *map_fd*. + * + * The *flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_UPDATE_ELEM + * Description + * Create or update an element (key/value pair) in a specified map. + * + * The *flags* argument should be specified as one of the + * following: + * + * **BPF_ANY** + * Create a new element or update an existing element. + * **BPF_NOEXIST** + * Create a new element only if it did not exist. + * **BPF_EXIST** + * Update an existing element. + * **BPF_F_LOCK** + * Update a spin_lock-ed map element. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, + * **E2BIG**, **EEXIST**, or **ENOENT**. + * + * **E2BIG** + * The number of elements in the map reached the + * *max_entries* limit specified at map creation time. + * **EEXIST** + * If *flags* specifies **BPF_NOEXIST** and the element + * with *key* already exists in the map. + * **ENOENT** + * If *flags* specifies **BPF_EXIST** and the element with + * *key* does not exist in the map. + * + * BPF_MAP_DELETE_ELEM + * Description + * Look up and delete an element by key in a specified map. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_GET_NEXT_KEY + * Description + * Look up an element by key in a specified map and return the key + * of the next element. Can be used to iterate over all elements + * in the map. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * The following cases can be used to iterate over all elements of + * the map: + * + * * If *key* is not found, the operation returns zero and sets + * the *next_key* pointer to the key of the first element. + * * If *key* is found, the operation returns zero and sets the + * *next_key* pointer to the key of the next element. + * * If *key* is the last element, returns -1 and *errno* is set + * to **ENOENT**. + * + * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or + * **EINVAL** on error. + * + * BPF_PROG_LOAD + * Description + * Verify and load an eBPF program, returning a new file + * descriptor associated with the program. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES). + * + * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is + * automatically enabled for the new file descriptor. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_OBJ_PIN + * Description + * Pin an eBPF program or map referred by the specified *bpf_fd* + * to the provided *pathname* on the filesystem. + * + * The *pathname* argument must not contain a dot ("."). + * + * On success, *pathname* retains a reference to the eBPF object, + * preventing deallocation of the object when the original + * *bpf_fd* is closed. This allow the eBPF object to live beyond + * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent + * process. + * + * Applying **unlink**\ (2) or similar calls to the *pathname* + * unpins the object from the filesystem, removing the reference. + * If no other file descriptors or filesystem nodes refer to the + * same object, it will be deallocated (see NOTES). + * + * The filesystem type for the parent directory of *pathname* must + * be **BPF_FS_MAGIC**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_OBJ_GET + * Description + * Open a file descriptor for the eBPF object pinned to the + * specified *pathname*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_PROG_ATTACH + * Description + * Attach an eBPF program to a *target_fd* at the specified + * *attach_type* hook. + * + * The *attach_type* specifies the eBPF attachment point to + * attach the program to, and must be one of *bpf_attach_type* + * (see below). + * + * The *attach_bpf_fd* must be a valid file descriptor for a + * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap + * or sock_ops type corresponding to the specified *attach_type*. + * + * The *target_fd* must be a valid file descriptor for a kernel + * object which depends on the attach type of *attach_bpf_fd*: + * + * **BPF_PROG_TYPE_CGROUP_DEVICE**, + * **BPF_PROG_TYPE_CGROUP_SKB**, + * **BPF_PROG_TYPE_CGROUP_SOCK**, + * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + * **BPF_PROG_TYPE_CGROUP_SOCKOPT**, + * **BPF_PROG_TYPE_CGROUP_SYSCTL**, + * **BPF_PROG_TYPE_SOCK_OPS** + * + * Control Group v2 hierarchy with the eBPF controller + * enabled. Requires the kernel to be compiled with + * **CONFIG_CGROUP_BPF**. + * + * **BPF_PROG_TYPE_FLOW_DISSECTOR** + * + * Network namespace (eg /proc/self/ns/net). + * + * **BPF_PROG_TYPE_LIRC_MODE2** + * + * LIRC device path (eg /dev/lircN). Requires the kernel + * to be compiled with **CONFIG_BPF_LIRC_MODE2**. + * + * **BPF_PROG_TYPE_SK_SKB**, + * **BPF_PROG_TYPE_SK_MSG** + * + * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**). + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_DETACH + * Description + * Detach the eBPF program associated with the *target_fd* at the + * hook specified by *attach_type*. The program must have been + * previously attached using **BPF_PROG_ATTACH**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_TEST_RUN + * Description + * Run the eBPF program associated with the *prog_fd* a *repeat* + * number of times against a provided program context *ctx_in* and + * data *data_in*, and return the modified program context + * *ctx_out*, *data_out* (for example, packet data), result of the + * execution *retval*, and *duration* of the test run. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * **ENOSPC** + * Either *data_size_out* or *ctx_size_out* is too small. + * **ENOTSUPP** + * This command is not supported by the program type of + * the program referred to by *prog_fd*. + * + * BPF_PROG_GET_NEXT_ID + * Description + * Fetch the next eBPF program currently loaded into the kernel. + * + * Looks for the eBPF program with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF programs + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_MAP_GET_NEXT_ID + * Description + * Fetch the next eBPF map currently loaded into the kernel. + * + * Looks for the eBPF map with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF maps + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_PROG_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF program corresponding to + * *prog_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_MAP_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF map corresponding to + * *map_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_OBJ_GET_INFO_BY_FD + * Description + * Obtain information about the eBPF object corresponding to + * *bpf_fd*. + * + * Populates up to *info_len* bytes of *info*, which will be in + * one of the following formats depending on the eBPF object type + * of *bpf_fd*: + * + * * **struct bpf_prog_info** + * * **struct bpf_map_info** + * * **struct bpf_btf_info** + * * **struct bpf_link_info** + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_QUERY + * Description + * Obtain information about eBPF programs associated with the + * specified *attach_type* hook. + * + * The *target_fd* must be a valid file descriptor for a kernel + * object which depends on the attach type of *attach_bpf_fd*: + * + * **BPF_PROG_TYPE_CGROUP_DEVICE**, + * **BPF_PROG_TYPE_CGROUP_SKB**, + * **BPF_PROG_TYPE_CGROUP_SOCK**, + * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + * **BPF_PROG_TYPE_CGROUP_SOCKOPT**, + * **BPF_PROG_TYPE_CGROUP_SYSCTL**, + * **BPF_PROG_TYPE_SOCK_OPS** + * + * Control Group v2 hierarchy with the eBPF controller + * enabled. Requires the kernel to be compiled with + * **CONFIG_CGROUP_BPF**. + * + * **BPF_PROG_TYPE_FLOW_DISSECTOR** + * + * Network namespace (eg /proc/self/ns/net). + * + * **BPF_PROG_TYPE_LIRC_MODE2** + * + * LIRC device path (eg /dev/lircN). Requires the kernel + * to be compiled with **CONFIG_BPF_LIRC_MODE2**. + * + * **BPF_PROG_QUERY** always fetches the number of programs + * attached and the *attach_flags* which were used to attach those + * programs. Additionally, if *prog_ids* is nonzero and the number + * of attached programs is less than *prog_cnt*, populates + * *prog_ids* with the eBPF program ids of the programs attached + * at *target_fd*. + * + * The following flags may alter the result: + * + * **BPF_F_QUERY_EFFECTIVE** + * Only return information regarding programs which are + * currently effective at the specified *target_fd*. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_RAW_TRACEPOINT_OPEN + * Description + * Attach an eBPF program to a tracepoint *name* to access kernel + * internal arguments of the tracepoint in their raw form. + * + * The *prog_fd* must be a valid file descriptor associated with + * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**. + * + * No ABI guarantees are made about the content of tracepoint + * arguments exposed to the corresponding eBPF program. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES). + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_BTF_LOAD + * Description + * Verify and load BPF Type Format (BTF) metadata into the kernel, + * returning a new file descriptor associated with the metadata. + * BTF is described in more detail at + * https://www.kernel.org/doc/html/latest/bpf/btf.html. + * + * The *btf* parameter must point to valid memory providing + * *btf_size* bytes of BTF binary metadata. + * + * The returned file descriptor can be passed to other **bpf**\ () + * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to + * associate the BTF with those objects. + * + * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional + * parameters to specify a *btf_log_buf*, *btf_log_size* and + * *btf_log_level* which allow the kernel to return freeform log + * output regarding the BTF verification process. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_BTF_GET_FD_BY_ID + * Description + * Open a file descriptor for the BPF Type Format (BTF) + * corresponding to *btf_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_TASK_FD_QUERY + * Description + * Obtain information about eBPF programs associated with the + * target process identified by *pid* and *fd*. + * + * If the *pid* and *fd* are associated with a tracepoint, kprobe + * or uprobe perf event, then the *prog_id* and *fd_type* will + * be populated with the eBPF program id and file descriptor type + * of type **bpf_task_fd_type**. If associated with a kprobe or + * uprobe, the *probe_offset* and *probe_addr* will also be + * populated. Optionally, if *buf* is provided, then up to + * *buf_len* bytes of *buf* will be populated with the name of + * the tracepoint, kprobe or uprobe. + * + * The resulting *prog_id* may be introspected in deeper detail + * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_LOOKUP_AND_DELETE_ELEM + * Description + * Look up an element with the given *key* in the map referred to + * by the file descriptor *fd*, and if found, delete the element. + * + * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types + * implement this command as a "pop" operation, deleting the top + * element rather than one corresponding to *key*. + * The *key* and *key_len* parameters should be zeroed when + * issuing this operation for these map types. + * + * This command is only valid for the following map types: + * * **BPF_MAP_TYPE_QUEUE** + * * **BPF_MAP_TYPE_STACK** + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_FREEZE + * Description + * Freeze the permissions of the specified map. + * + * Write permissions may be frozen by passing zero *flags*. + * Upon success, no future syscall invocations may alter the + * map state of *map_fd*. Write operations from eBPF programs + * are still possible for a frozen map. + * + * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_BTF_GET_NEXT_ID + * Description + * Fetch the next BPF Type Format (BTF) object currently loaded + * into the kernel. + * + * Looks for the BTF object with an id greater than *start_id* + * and updates *next_id* on success. If no other BTF objects + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_MAP_LOOKUP_BATCH + * Description + * Iterate and fetch multiple elements in a map. + * + * Two opaque values are used to manage batch operations, + * *in_batch* and *out_batch*. Initially, *in_batch* must be set + * to NULL to begin the batched operation. After each subsequent + * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant + * *out_batch* as the *in_batch* for the next operation to + * continue iteration from the current point. + * + * The *keys* and *values* are output parameters which must point + * to memory large enough to hold *count* items based on the key + * and value size of the map *map_fd*. The *keys* buffer must be + * of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * The *elem_flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * On success, *count* elements from the map are copied into the + * user buffer, with the keys copied into *keys* and the values + * copied into the corresponding indices in *values*. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **ENOSPC** to indicate that *keys* or + * *values* is too small to dump an entire bucket during + * iteration of a hash-based map type. + * + * BPF_MAP_LOOKUP_AND_DELETE_BATCH + * Description + * Iterate and delete all elements in a map. + * + * This operation has the same behavior as + * **BPF_MAP_LOOKUP_BATCH** with two exceptions: + * + * * Every element that is successfully returned is also deleted + * from the map. This is at least *count* elements. Note that + * *count* is both an input and an output parameter. + * * Upon returning with *errno* set to **EFAULT**, up to + * *count* elements may be deleted without returning the keys + * and values of the deleted elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_UPDATE_BATCH + * Description + * Update multiple elements in a map by *key*. + * + * The *keys* and *values* are input parameters which must point + * to memory large enough to hold *count* items based on the key + * and value size of the map *map_fd*. The *keys* buffer must be + * of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * Each element specified in *keys* is sequentially updated to the + * value in the corresponding index in *values*. The *in_batch* + * and *out_batch* parameters are ignored and should be zeroed. + * + * The *elem_flags* argument should be specified as one of the + * following: + * + * **BPF_ANY** + * Create new elements or update a existing elements. + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * **BPF_EXIST** + * Update existing elements. + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * On success, *count* elements from the map are updated. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or + * **E2BIG**. **E2BIG** indicates that the number of elements in + * the map reached the *max_entries* limit specified at map + * creation time. + * + * May set *errno* to one of the following error codes under + * specific circumstances: + * + * **EEXIST** + * If *flags* specifies **BPF_NOEXIST** and the element + * with *key* already exists in the map. + * **ENOENT** + * If *flags* specifies **BPF_EXIST** and the element with + * *key* does not exist in the map. + * + * BPF_MAP_DELETE_BATCH + * Description + * Delete multiple elements in a map by *key*. + * + * The *keys* parameter is an input parameter which must point + * to memory large enough to hold *count* items based on the key + * size of the map *map_fd*, that is, *key_size* * *count*. + * + * Each element specified in *keys* is sequentially deleted. The + * *in_batch*, *out_batch*, and *values* parameters are ignored + * and should be zeroed. + * + * The *elem_flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * On success, *count* elements from the map are updated. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. If + * *errno* is **EFAULT**, up to *count* elements may be been + * deleted. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_LINK_CREATE + * Description + * Attach an eBPF program to a *target_fd* at the specified + * *attach_type* hook and return a file descriptor handle for + * managing the link. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_UPDATE + * Description + * Update the eBPF program in the specified *link_fd* to + * *new_prog_fd*. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_LINK_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF Link corresponding to + * *link_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_GET_NEXT_ID + * Description + * Fetch the next eBPF link currently loaded into the kernel. + * + * Looks for the eBPF link with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF links + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_ENABLE_STATS + * Description + * Enable eBPF runtime statistics gathering. + * + * Runtime statistics gathering for the eBPF runtime is disabled + * by default to minimize the corresponding performance overhead. + * This command enables statistics globally. + * + * Multiple programs may independently enable statistics. + * After gathering the desired statistics, eBPF runtime statistics + * may be disabled again by calling **close**\ (2) for the file + * descriptor returned by this function. Statistics will only be + * disabled system-wide when all outstanding file descriptors + * returned by prior calls for this subcommand are closed. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_ITER_CREATE + * Description + * Create an iterator on top of the specified *link_fd* (as + * previously created using **BPF_LINK_CREATE**) and return a + * file descriptor that can be used to trigger the iteration. + * + * If the resulting file descriptor is pinned to the filesystem + * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls + * for that path will trigger the iterator to read kernel state + * using the eBPF program attached to *link_fd*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_DETACH + * Description + * Forcefully detach the specified *link_fd* from its + * corresponding attachment point. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_BIND_MAP + * Description + * Bind a map to the lifetime of an eBPF program. + * + * The map identified by *map_fd* is bound to the program + * identified by *prog_fd* and only released when *prog_fd* is + * released. This may be used in cases where metadata should be + * associated with a program which otherwise does not contain any + * references to the map (for example, embedded in the eBPF + * program instructions). + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * NOTES + * eBPF objects (maps and programs) can be shared between processes. + * + * * After **fork**\ (2), the child inherits file descriptors + * referring to the same eBPF objects. + * * File descriptors referring to eBPF objects can be transferred over + * **unix**\ (7) domain sockets. + * * File descriptors referring to eBPF objects can be duplicated in the + * usual way, using **dup**\ (2) and similar calls. + * * File descriptors referring to eBPF objects can be pinned to the + * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2). + * + * An eBPF object is deallocated only after all file descriptors referring + * to the object have been closed and no references remain pinned to the + * filesystem or attached (for example, bound to a program or device). + */ enum bpf_cmd { BPF_MAP_CREATE, BPF_MAP_LOOKUP_ELEM, @@ -393,6 +1103,15 @@ enum bpf_link_type { * is struct/union. */ #define BPF_PSEUDO_BTF_ID 3 +/* insn[0].src_reg: BPF_PSEUDO_FUNC + * insn[0].imm: insn offset to the func + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of the function + * verifier type: PTR_TO_FUNC. + */ +#define BPF_PSEUDO_FUNC 4 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function @@ -720,7 +1439,7 @@ union bpf_attr { * parsed and used to produce a manual page. The workflow is the following, * and requires the rst2man utility: * - * $ ./scripts/bpf_helpers_doc.py \ + * $ ./scripts/bpf_doc.py \ * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 * $ man /tmp/bpf-helpers.7 @@ -1765,6 +2484,10 @@ union bpf_attr { * Use with ENCAP_L3/L4 flags to further specify the tunnel * type; *len* is the length of the inner MAC header. * + * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**: + * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the + * L2 type as Ethernet. + * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -3909,6 +4632,34 @@ union bpf_attr { * * **BPF_MTU_CHK_RET_FRAG_NEEDED** * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** * + * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For each element in **map**, call **callback_fn** function with + * **map**, **callback_ctx** and other map-specific parameters. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. + * + * The following are a list of supported map types and their + * respective expected callback signatures: + * + * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH, + * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, + * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY + * + * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx); + * + * For per_cpu maps, the map_value is the value on the cpu where the + * bpf_prog is running. + * + * If **callback_fn** return 0, the helper will continue to the next + * element. If return value is 1, the helper will skip the rest of + * elements and return. Other return values are not used now. + * + * Return + * The number of traversed map elements for success, **-EINVAL** for + * invalid **flags**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4075,6 +4826,7 @@ union bpf_attr { FN(ima_inode_hash), \ FN(sock_from_file), \ FN(check_mtu), \ + FN(for_each_map_elem), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4168,6 +4920,7 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), + BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), }; enum { @@ -5205,7 +5958,10 @@ struct bpf_pidns_info { /* User accessible data for SK_LOOKUP programs. Add new fields at the end. */ struct bpf_sk_lookup { - __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + union { + __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */ + }; __u32 family; /* Protocol family (AF_INET, AF_INET6) */ __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 5a667107ad2c..d27b1708efe9 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -52,7 +52,7 @@ struct btf_type { }; }; -#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f) #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) @@ -72,7 +72,8 @@ struct btf_type { #define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ #define BTF_KIND_VAR 14 /* Variable */ #define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_MAX BTF_KIND_DATASEC +#define BTF_KIND_FLOAT 16 /* Floating point */ +#define BTF_KIND_MAX BTF_KIND_FLOAT #define NR_BTF_KINDS (BTF_KIND_MAX + 1) /* For some specific BTF_KIND, "struct btf_type" is immediately |