/* SPDX-License-Identifier: GPL-2.0-only *//* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */#ifndef _LINUX_BPF_H#define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h>#include <uapi/linux/filter.h> #include <linux/workqueue.h>#include <linux/file.h>#include <linux/percpu.h>#include <linux/err.h>#include <linux/rbtree_latch.h>#include <linux/numa.h>#include <linux/mm_types.h>#include <linux/wait.h>#include <linux/refcount.h>#include <linux/mutex.h>#include <linux/module.h>#include <linux/kallsyms.h>#include <linux/capability.h>#include <linux/sched/mm.h>#include <linux/slab.h>#include <linux/percpu-refcount.h>#include <linux/stddef.h>#include <linux/bpfptr.h>#include <linux/btf.h>#include <linux/rcupdate_trace.h>#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;struct perf_event;struct bpf_prog;struct bpf_prog_aux;struct bpf_map;struct bpf_arena;struct sock;struct seq_file;struct btf;struct btf_type;struct exception_table_entry;struct seq_operations;struct bpf_iter_aux_info;struct bpf_local_storage;struct bpf_local_storage_map;struct kobject;struct mem_cgroup;struct module;struct bpf_func_state;struct ftrace_ops;struct cgroup;struct bpf_token;struct user_namespace;struct super_block;struct inode; extern struct idr btf_idr;extern spinlock_t btf_idr_lock;extern struct kobject *btf_kobj;extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux);typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);typedef unsigned int (*bpf_func_t)(const void *, const struct bpf_insn *);struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size;}; /* map is generic key/value storage optionally accessible by eBPF programs */struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); 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_elem)(struct bpf_map *map, void *key, void *value, u64 flags); 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, struct file *map_file, 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); long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); long (*map_delete_elem)(struct bpf_map *map, void *key); long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ long (*map_redirect)(struct bpf_map *map, u64 key, 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. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ 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); long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); u64 (*map_mem_usage)(const struct bpf_map *map); /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info;}; enum { /* Support at most 11 fields in a BTF type */ BTF_FIELDS_MAX = 11,}; enum btf_field_type { BPF_SPIN_LOCK = (1 << 0), BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR_PERCPU = (1 << 4), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, BPF_LIST_HEAD = (1 << 5), BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), BPF_UPTR = (1 << 11), BPF_RES_SPIN_LOCK = (1 << 12),}; typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { struct btf *btf; struct module *module; /* dtor used if btf_is_kernel(btf), otherwise the type is * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used */ btf_dtor_kfunc_t dtor; u32 btf_id;}; struct btf_field_graph_root { struct btf *btf; u32 value_btf_id; u32 node_offset; struct btf_record *value_rec;}; struct btf_field { u32 offset; u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; struct btf_field_graph_root graph_root; };}; 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; struct btf_field fields[];}; /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */struct bpf_rb_node_kern { struct rb_node rb_node; void *owner;} __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */struct bpf_list_node_kern { struct list_head list_head; void *owner;} __attribute__((aligned(8))); struct bpf_map { const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta;#ifdef CONFIG_SECURITY void *security;#endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; u32 id; struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf;#ifdef CONFIG_MEMCG struct obj_cgroup *objcg;#endif char name[BPF_OBJ_NAME_LEN]; struct mutex freeze_mutex; atomic64_t refcnt; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; 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; 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;}; 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: return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; case BPF_UPTR: return "uptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; case BPF_RB_ROOT: return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; }} #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: return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); case BPF_RB_ROOT: return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; }} 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: return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); case BPF_RB_ROOT: return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; }} static inline void bpf_obj_init_field(const struct btf_field *field, void *addr){ memset(addr, 0, field->size); switch (field->type) { case BPF_REFCOUNT: refcount_set((refcount_t *)addr, 1); break; case BPF_RB_NODE: RB_CLEAR_NODE((struct rb_node *)addr); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: INIT_LIST_HEAD((struct list_head *)addr); break; 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: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: break; default: WARN_ON_ONCE(1); return; }} static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type){ if (IS_ERR_OR_NULL(rec)) return false; return rec->field_mask & type;} static inline void bpf_obj_init(const struct btf_record *rec, void *obj){ int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset);} /* 'dst' must be a temporary buffer and should not point to memory that is being * used in parallel by a bpf program or bpf syscall, otherwise the access from * the bpf program or bpf syscall may be corrupted by the reinitialization, * leading to weird problems. Even 'dst' is newly-allocated from bpf memory * allocator, it is still possible for 'dst' to be used in parallel by a bpf * program or bpf syscall. */static inline void check_and_init_map_value(struct bpf_map *map, void *dst){ bpf_obj_init(map->record, dst);} /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */static inline void bpf_long_memcpy(void *dst, const void *src, u32 size){ const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) data_race(*ldst++ = *lsrc++);} /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy){Lines 1–500 of 3591. Load more
/* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_H #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> #include <uapi/linux/filter.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> #include <linux/mm_types.h> #include <linux/wait.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/stddef.h> #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> #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; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; struct bpf_arena; struct sock; struct seq_file; struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; struct bpf_token; struct user_namespace; struct super_block; struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); typedef unsigned int (*bpf_func_t)(const void *, const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; }; /* map is generic key/value storage optionally accessible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); 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_elem)(struct bpf_map *map, void *key, void *value, u64 flags); 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, struct file *map_file, 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); long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); long (*map_delete_elem)(struct bpf_map *map, void *key); long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ long (*map_redirect)(struct bpf_map *map, u64 key, 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. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ 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); long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); u64 (*map_mem_usage)(const struct bpf_map *map); /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; enum { /* Support at most 11 fields in a BTF type */ BTF_FIELDS_MAX = 11, }; enum btf_field_type { BPF_SPIN_LOCK = (1 << 0), BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR_PERCPU = (1 << 4), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, BPF_LIST_HEAD = (1 << 5), BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), BPF_UPTR = (1 << 11), BPF_RES_SPIN_LOCK = (1 << 12), }; typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { struct btf *btf; struct module *module; /* dtor used if btf_is_kernel(btf), otherwise the type is * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used */ btf_dtor_kfunc_t dtor; u32 btf_id; }; struct btf_field_graph_root { struct btf *btf; u32 value_btf_id; u32 node_offset; struct btf_record *value_rec; }; struct btf_field { u32 offset; u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; struct btf_field_graph_root graph_root; }; }; 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; struct btf_field fields[]; }; /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ struct bpf_rb_node_kern { struct rb_node rb_node; void *owner; } __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ struct bpf_list_node_kern { struct list_head list_head; void *owner; } __attribute__((aligned(8))); struct bpf_map { const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; #endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; u32 id; struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; struct mutex freeze_mutex; atomic64_t refcnt; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; 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; 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; }; 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: return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; case BPF_UPTR: return "uptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; case BPF_RB_ROOT: return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; } } #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: return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); case BPF_RB_ROOT: return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } 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: return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); case BPF_RB_ROOT: return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) { memset(addr, 0, field->size); switch (field->type) { case BPF_REFCOUNT: refcount_set((refcount_t *)addr, 1); break; case BPF_RB_NODE: RB_CLEAR_NODE((struct rb_node *)addr); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: INIT_LIST_HEAD((struct list_head *)addr); break; 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: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: break; default: WARN_ON_ONCE(1); return; } } static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) return false; return rec->field_mask & type; } static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being * used in parallel by a bpf program or bpf syscall, otherwise the access from * the bpf program or bpf syscall may be corrupted by the reinitialization, * leading to weird problems. Even 'dst' is newly-allocated from bpf memory * allocator, it is still possible for 'dst' to be used in parallel by a bpf * program or bpf syscall. */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) { const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) data_race(*ldst++ = *lsrc++); } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) {