diff options
Diffstat (limited to 'include/linux/bpf.h')
| -rw-r--r-- | include/linux/bpf.h | 277 |
1 files changed, 233 insertions, 44 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e63dd3443b9..cc700925b802 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -30,6 +30,7 @@ #include <linux/static_call.h> #include <linux/memcontrol.h> #include <linux/cfi.h> +#include <asm/rqspinlock.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -204,8 +205,23 @@ enum btf_field_type { BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), BPF_UPTR = (1 << 11), + BPF_RES_SPIN_LOCK = (1 << 12), }; +enum bpf_cgroup_storage_type { + BPF_CGROUP_STORAGE_SHARED, + BPF_CGROUP_STORAGE_PERCPU, + __BPF_CGROUP_STORAGE_MAX +#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX +}; + +#ifdef CONFIG_CGROUP_BPF +# define for_each_cgroup_storage_type(stype) \ + for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) +#else +# define for_each_cgroup_storage_type(stype) for (; false; ) +#endif /* CONFIG_CGROUP_BPF */ + typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { @@ -239,6 +255,7 @@ struct btf_record { u32 cnt; u32 field_mask; int spin_lock_off; + int res_spin_lock_off; int timer_off; int wq_off; int refcount_off; @@ -257,6 +274,19 @@ struct bpf_list_node_kern { void *owner; } __attribute__((aligned(8))); +/* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ +struct bpf_map_owner { + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE]; + const struct btf_type *attach_func_proto; +}; + struct bpf_map { const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; @@ -289,24 +319,15 @@ struct bpf_map { struct rcu_head rcu; }; atomic64_t writecnt; - /* 'Ownership' of program-containing map is claimed by the first program - * that is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have the - * same prog type, JITed flag and xdp_has_frags flag. - */ - struct { - const struct btf_type *attach_func_proto; - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - bool xdp_has_frags; - } owner; + spinlock_t owner_lock; + struct bpf_map_owner *owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; bool free_after_rcu_gp; atomic64_t sleepable_refcnt; s64 __percpu *elem_count; + u64 cookie; /* write-once */ }; static inline const char *btf_field_type_name(enum btf_field_type type) @@ -314,6 +335,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) switch (type) { case BPF_SPIN_LOCK: return "bpf_spin_lock"; + case BPF_RES_SPIN_LOCK: + return "bpf_res_spin_lock"; case BPF_TIMER: return "bpf_timer"; case BPF_WORKQUEUE: @@ -341,11 +364,19 @@ static inline const char *btf_field_type_name(enum btf_field_type type) } } +#if IS_ENABLED(CONFIG_DEBUG_KERNEL) +#define BPF_WARN_ONCE(cond, format...) WARN_ONCE(cond, format) +#else +#define BPF_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) +#endif + static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return sizeof(struct bpf_spin_lock); + case BPF_RES_SPIN_LOCK: + return sizeof(struct bpf_res_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); case BPF_WORKQUEUE: @@ -376,6 +407,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) switch (type) { case BPF_SPIN_LOCK: return __alignof__(struct bpf_spin_lock); + case BPF_RES_SPIN_LOCK: + return __alignof__(struct bpf_res_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); case BPF_WORKQUEUE: @@ -419,6 +452,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_RB_ROOT: /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: + case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_WORKQUEUE: case BPF_KPTR_UNREF: @@ -968,6 +1002,7 @@ struct bpf_insn_access_aux { struct { struct btf *btf; u32 btf_id; + u32 ref_obj_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ @@ -990,6 +1025,21 @@ static inline bool bpf_pseudo_func(const struct bpf_insn *insn) return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } +/* Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an + * atomic load or store, and false if it is a read-modify-write instruction. + */ +static inline bool +bpf_atomic_is_load_store(const struct bpf_insn *atomic_insn) +{ + switch (atomic_insn->imm) { + case BPF_LOAD_ACQ: + case BPF_STORE_REL: + return true; + default: + return false; + } +} + struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); @@ -1050,14 +1100,6 @@ struct bpf_prog_offload { u32 jited_len; }; -enum bpf_cgroup_storage_type { - BPF_CGROUP_STORAGE_SHARED, - BPF_CGROUP_STORAGE_PERCPU, - __BPF_CGROUP_STORAGE_MAX -}; - -#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX - /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ @@ -1323,6 +1365,20 @@ u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); +int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, + void *src, u32 len, u64 flags); +void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u32 offset, + void *buffer__opt, u32 buffer__szk); + +static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) +{ + u32 size = __bpf_dynptr_size(ptr); + + if (len > size || offset > size - len) + return -E2BIG; + + return 0; +} #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, @@ -1481,6 +1537,8 @@ struct bpf_ctx_arg_aux { enum bpf_reg_type reg_type; struct btf *btf; u32 btf_id; + u32 ref_obj_id; + bool refcounted; }; struct btf_mod_pair { @@ -1490,6 +1548,37 @@ struct btf_mod_pair { struct bpf_kfunc_desc_tab; +enum bpf_stream_id { + BPF_STDOUT = 1, + BPF_STDERR = 2, +}; + +struct bpf_stream_elem { + struct llist_node node; + int total_len; + int consumed_len; + char str[]; +}; + +enum { + /* 100k bytes */ + BPF_STREAM_MAX_CAPACITY = 100000ULL, +}; + +struct bpf_stream { + atomic_t capacity; + struct llist_head log; /* list of in-flight stream elements in LIFO order */ + + struct mutex lock; /* lock protecting backlog_{head,tail} */ + struct llist_node *backlog_head; /* list of in-flight stream elements in FIFO order */ + struct llist_node *backlog_tail; /* tail of the list above */ +}; + +struct bpf_stream_stage { + struct llist_head log; + int len; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; @@ -1503,11 +1592,12 @@ struct bpf_prog_aux { u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + u32 attach_st_ops_member_off; u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; struct btf *attach_btf; - const struct bpf_ctx_arg_aux *ctx_arg_info; + struct bpf_ctx_arg_aux *ctx_arg_info; void __percpu *priv_stack_ptr; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; @@ -1528,6 +1618,7 @@ struct bpf_prog_aux { bool jits_use_priv_stack; bool priv_stack_requested; bool changes_pkt_data; + bool might_sleep; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; @@ -1547,6 +1638,7 @@ struct bpf_prog_aux { #endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; + const struct bpf_struct_ops *st_ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; @@ -1595,6 +1687,7 @@ struct bpf_prog_aux { struct work_struct work; struct rcu_head rcu; }; + struct bpf_stream stream[2]; }; struct bpf_prog { @@ -1646,11 +1739,10 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; - /* whether BPF link itself has "sleepable" semantics, which can differ - * from underlying BPF program having a "sleepable" semantics, as BPF - * link's semantics is determined by target attach hook - */ - bool sleepable; + + u32 flags; + enum bpf_attach_type attach_type; + /* rcu is used before freeing, work can be used to schedule that * RCU-based freeing before that, so they never overlap */ @@ -1658,6 +1750,11 @@ struct bpf_link { struct rcu_head rcu; struct work_struct work; }; + /* whether BPF link itself has "sleepable" semantics, which can differ + * from underlying BPF program having a "sleepable" semantics, as BPF + * link's semantics is determined by target attach hook + */ + bool sleepable; }; struct bpf_link_ops { @@ -1697,7 +1794,6 @@ struct bpf_shim_tramp_link { struct bpf_tracing_link { struct bpf_tramp_link link; - enum bpf_attach_type attach_type; struct bpf_trampoline *trampoline; struct bpf_prog *tgt_prog; }; @@ -1945,13 +2041,18 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op #endif +int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, + const struct bpf_ctx_arg_aux *info, u32 cnt); + #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, - int cgroup_atype); + int cgroup_atype, + enum bpf_attach_type attach_type); void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, - int cgroup_atype) + int cgroup_atype, + enum bpf_attach_type attach_type) { return -EOPNOTSUPP; } @@ -1980,6 +2081,7 @@ struct bpf_array { */ enum { BPF_MAX_LOOPS = 8 * 1024 * 1024, + BPF_MAX_TIMED_LOOPS = 0xffff, }; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ @@ -2016,6 +2118,16 @@ static inline bool bpf_map_flags_access_ok(u32 access_flags) (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } +static inline struct bpf_map_owner *bpf_map_owner_alloc(struct bpf_map *map) +{ + return kzalloc(sizeof(*map->owner), GFP_ATOMIC); +} + +static inline void bpf_map_owner_free(struct bpf_map *map) +{ + kfree(map->owner); +} + struct bpf_event_entry { struct perf_event *event; struct file *perf_file; @@ -2036,6 +2148,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); +const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void); + typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, @@ -2231,6 +2345,9 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, return ret; } +bool bpf_jit_bypass_spec_v1(void); +bool bpf_jit_bypass_spec_v4(void); + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; @@ -2257,6 +2374,7 @@ extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; +extern const struct file_operations bpf_token_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ @@ -2299,6 +2417,14 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); +/* + * The __bpf_map_get() and __btf_get_by_fd() functions parse a file + * descriptor and return a corresponding map or btf object. + * Their names are double underscored to emphasize the fact that they + * do not increase refcnt. To also increase refcnt use corresponding + * bpf_map_get() and btf_get_by_fd() functions. + */ + static inline struct bpf_map *__bpf_map_get(struct fd f) { if (fd_empty(f)) @@ -2308,6 +2434,15 @@ static inline struct bpf_map *__bpf_map_get(struct fd f) return fd_file(f)->private_data; } +static inline struct btf *__btf_get_by_fd(struct fd f) +{ + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (unlikely(fd_file(f)->f_op != &btf_fops)) + return ERR_PTR(-EINVAL); + return fd_file(f)->private_data; +} + void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); @@ -2331,7 +2466,8 @@ int generic_map_delete_batch(struct bpf_map *map, struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); -int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, + +int bpf_map_alloc_pages(const struct bpf_map *map, int nid, unsigned long nr_pages, struct page **page_array); #ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, @@ -2401,22 +2537,27 @@ static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { - return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); + return bpf_jit_bypass_spec_v1() || + cpu_mitigations_off() || + bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { - return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); + return bpf_jit_bypass_spec_v4() || + cpu_mitigations_off() || + bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, - const struct bpf_link_ops *ops, struct bpf_prog *prog); + const struct bpf_link_ops *ops, struct bpf_prog *prog, + enum bpf_attach_type attach_type); void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, - bool sleepable); + enum bpf_attach_type attach_type, bool sleepable); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); @@ -2431,6 +2572,9 @@ void bpf_token_inc(struct bpf_token *token); void bpf_token_put(struct bpf_token *token); int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); +int bpf_token_get_info_by_fd(struct bpf_token *token, + const union bpf_attr *attr, + union bpf_attr __user *uattr); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); @@ -2529,7 +2673,7 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); -bool bpf_iter_prog_supported(struct bpf_prog *prog); +int bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); @@ -2589,10 +2733,10 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog); + const struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress); + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, @@ -2768,13 +2912,13 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog) static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, - struct bpf_prog *prog) + struct bpf_prog *prog, enum bpf_attach_type attach_type) { } static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, - bool sleepable) + enum bpf_attach_type attach_type, bool sleepable) { } @@ -2829,6 +2973,13 @@ static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) return ERR_PTR(-EOPNOTSUPP); } +static inline int bpf_token_get_info_by_fd(struct bpf_token *token, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + static inline void __dev_flush(struct list_head *flush_list) { } @@ -2862,15 +3013,15 @@ struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress) + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress) { return 0; } @@ -3469,6 +3620,16 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 #define MAX_BPRINTF_BUF 1024 +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. + */ +#define MAX_BPRINTF_BIN_ARGS 512 + +struct bpf_bprintf_buffers { + char bin_args[MAX_BPRINTF_BIN_ARGS]; + char buf[MAX_BPRINTF_BUF]; +}; + struct bpf_bprintf_data { u32 *bin_args; char *buf; @@ -3476,9 +3637,33 @@ struct bpf_bprintf_data { bool get_buf; }; -int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, +int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); +int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs); +void bpf_put_buffers(void); + +void bpf_prog_stream_init(struct bpf_prog *prog); +void bpf_prog_stream_free(struct bpf_prog *prog); +int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len); +void bpf_stream_stage_init(struct bpf_stream_stage *ss); +void bpf_stream_stage_free(struct bpf_stream_stage *ss); +__printf(2, 3) +int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...); +int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog, + enum bpf_stream_id stream_id); +int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss); + +#define bpf_stream_printk(ss, ...) bpf_stream_stage_printk(&ss, __VA_ARGS__) +#define bpf_stream_dump_stack(ss) bpf_stream_stage_dump_stack(&ss) + +#define bpf_stream_stage(ss, prog, stream_id, expr) \ + ({ \ + bpf_stream_stage_init(&ss); \ + (expr); \ + bpf_stream_stage_commit(&ss, prog, stream_id); \ + bpf_stream_stage_free(&ss); \ + }) #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); @@ -3514,4 +3699,8 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog) return prog->aux->func_idx != 0; } +int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep, + const char **linep, int *nump); +struct bpf_prog *bpf_prog_find_from_stack(void); + #endif /* _LINUX_BPF_H */ |