diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf.h | 63 | ||||
| -rw-r--r-- | include/linux/bpf_local_storage.h | 12 | ||||
| -rw-r--r-- | include/linux/bpf_verifier.h | 67 | ||||
| -rw-r--r-- | include/linux/btf.h | 22 | ||||
| -rw-r--r-- | include/linux/btf_ids.h | 1 | ||||
| -rw-r--r-- | include/linux/filter.h | 1 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 9 |
7 files changed, 111 insertions, 64 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdadb0bb6cec..3ace0d6227e3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -203,6 +203,7 @@ enum btf_field_type { BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), + BPF_UPTR = (1 << 11), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -322,6 +323,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) 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: @@ -350,6 +353,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type) 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); @@ -379,6 +383,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type) 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); @@ -419,6 +424,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: break; default: WARN_ON_ONCE(1); @@ -507,6 +513,25 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } +static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src) +{ + unsigned long *src_uptr, *dst_uptr; + const struct btf_field *field; + int i; + + if (!btf_record_has_field(rec, BPF_UPTR)) + return; + + for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + src_uptr = src + field->offset; + dst_uptr = dst + field->offset; + swap(*src_uptr, *dst_uptr); + } +} + static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; @@ -907,10 +932,6 @@ enum bpf_reg_type { * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, - /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not - * been checked for null. Used primarily to inform the verifier - * an explicit null check is required for this struct. - */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_ARENA, PTR_TO_BUF, /* reg points to a read/write buffer */ @@ -923,6 +944,10 @@ enum bpf_reg_type { PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, + /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not + * been checked for null. Used primarily to inform the verifier + * an explicit null check is required for this struct. + */ PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is @@ -1300,8 +1325,12 @@ void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); -int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog); +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); @@ -1373,7 +1402,8 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); +void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym); +void bpf_image_ksym_add(struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); @@ -1382,12 +1412,14 @@ void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, - struct bpf_trampoline *tr) + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, - struct bpf_trampoline *tr) + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { return -ENOTSUPP; } @@ -1476,6 +1508,7 @@ struct bpf_prog_aux { u32 max_rdwr_access; struct btf *attach_btf; const 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; struct bpf_trampoline *dst_trampoline; @@ -1491,7 +1524,13 @@ struct bpf_prog_aux { bool xdp_has_frags; bool exception_cb; bool exception_boundary; + bool is_extended; /* true if extended by freplace program */ + bool jits_use_priv_stack; + bool priv_stack_requested; + 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; + void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */ /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -3461,4 +3500,10 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog) return prog->aux->func_idx != 0; } +static inline bool bpf_prog_is_raw_tp(const struct bpf_prog *prog) +{ + return prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP; +} + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index dcddb0aef7d8..ab7244d8108f 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -77,7 +77,13 @@ struct bpf_local_storage_elem { struct hlist_node map_node; /* Linked to bpf_local_storage_map */ struct hlist_node snode; /* Linked to bpf_local_storage */ struct bpf_local_storage __rcu *local_storage; - struct rcu_head rcu; + union { + struct rcu_head rcu; + struct hlist_node free_node; /* used to postpone + * bpf_selem_free + * after raw_spin_unlock + */ + }; /* 8 bytes hole */ /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. @@ -181,7 +187,7 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem, gfp_t gfp_flags); + bool charge_mem, bool swap_uptrs, gfp_t gfp_flags); void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, @@ -195,7 +201,7 @@ bpf_local_storage_alloc(void *owner, struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags, gfp_t gfp_flags); + void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags); u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 4513372c5bc8..f4290c179bee 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -48,22 +48,6 @@ enum bpf_reg_liveness { REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */ }; -/* For every reg representing a map value or allocated object pointer, - * we consider the tuple of (ptr, id) for them to be unique in verifier - * context and conside them to not alias each other for the purposes of - * tracking lock state. - */ -struct bpf_active_lock { - /* This can either be reg->map_ptr or reg->btf. If ptr is NULL, - * there's no active lock held, and other fields have no - * meaning. If non-NULL, it indicates that a lock is held and - * id member has the reg->id of the register which can be >= 0. - */ - void *ptr; - /* This will be reg->id */ - u32 id; -}; - #define ITER_PREFIX "bpf_iter_" enum bpf_iter_state { @@ -266,6 +250,13 @@ struct bpf_stack_state { }; struct bpf_reference_state { + /* Each reference object has a type. Ensure REF_TYPE_PTR is zero to + * default to pointer reference on zero initialization of a state. + */ + enum ref_state_type { + REF_TYPE_PTR = 0, + REF_TYPE_LOCK, + } type; /* Track each reference created with a unique id, even if the same * instruction creates the reference multiple times (eg, via CALL). */ @@ -274,17 +265,10 @@ struct bpf_reference_state { * is used purely to inform the user of a reference leak. */ int insn_idx; - /* There can be a case like: - * main (frame 0) - * cb (frame 1) - * func (frame 3) - * cb (frame 4) - * Hence for frame 4, if callback_ref just stored boolean, it would be - * impossible to distinguish nested callback refs. Hence store the - * frameno and compare that to callback_ref in check_reference_leak when - * exiting a callback function. - */ - int callback_ref; + /* Use to keep track of the source object of a lock, to ensure + * it matches on unlock. + */ + void *ptr; }; struct bpf_retval_range { @@ -332,6 +316,7 @@ struct bpf_func_state { /* The following fields should be last. See copy_func_state() */ int acquired_refs; + int active_locks; struct bpf_reference_state *refs; /* The state of the stack. Each element of the array describes BPF_REG_SIZE * (i.e. 8) bytes worth of stack memory. @@ -349,7 +334,7 @@ struct bpf_func_state { #define MAX_CALL_FRAMES 8 -/* instruction history flags, used in bpf_jmp_history_entry.flags field */ +/* instruction history flags, used in bpf_insn_hist_entry.flags field */ enum { /* instruction references stack slot through PTR_TO_STACK register; * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) @@ -367,7 +352,7 @@ enum { static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); -struct bpf_jmp_history_entry { +struct bpf_insn_hist_entry { u32 idx; /* insn idx can't be bigger than 1 million */ u32 prev_idx : 22; @@ -434,7 +419,6 @@ struct bpf_verifier_state { u32 insn_idx; u32 curframe; - struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; u32 active_preempt_lock; @@ -458,13 +442,14 @@ struct bpf_verifier_state { * See get_loop_entry() for more information. */ struct bpf_verifier_state *loop_entry; - /* jmp history recorded from first to last. - * backtracking is using it to go from last to first. - * For most states jmp_history_cnt is [0-3]. + /* Sub-range of env->insn_hist[] corresponding to this state's + * instruction history. + * Backtracking is using it to go from last to first. + * For most states instruction history is short, 0-3 instructions. * For loops can go up to ~40. */ - struct bpf_jmp_history_entry *jmp_history; - u32 jmp_history_cnt; + u32 insn_hist_start; + u32 insn_hist_end; u32 dfs_depth; u32 callback_unroll_depth; u32 may_goto_depth; @@ -649,6 +634,12 @@ struct bpf_subprog_arg_info { }; }; +enum priv_stack_mode { + PRIV_STACK_UNKNOWN, + NO_PRIV_STACK, + PRIV_STACK_ADAPTIVE, +}; + struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ @@ -669,6 +660,7 @@ struct bpf_subprog_info { /* true if bpf_fastcall stack region is used by functions that can't be inlined */ bool keep_fastcall_stack: 1; + enum priv_stack_mode priv_stack_mode; u8 arg_cnt; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; @@ -747,7 +739,9 @@ struct bpf_verifier_env { int cur_stack; } cfg; struct backtrack_state bt; - struct bpf_jmp_history_entry *cur_hist_ent; + struct bpf_insn_hist_entry *insn_hist; + struct bpf_insn_hist_entry *cur_hist_ent; + u32 insn_hist_cap; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ @@ -888,6 +882,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) case BPF_PROG_TYPE_TRACING: return prog->expected_attach_type != BPF_TRACE_ITER; case BPF_PROG_TYPE_STRUCT_OPS: + return prog->aux->jits_use_priv_stack; case BPF_PROG_TYPE_LSM: return false; default: diff --git a/include/linux/btf.h b/include/linux/btf.h index b8a583194c4a..4214e76c9168 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -75,6 +75,7 @@ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ #define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ +#define KF_FASTCALL (1 << 12) /* kfunc supports bpf_fastcall protocol */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the @@ -581,6 +582,16 @@ int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_ty bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx); + +static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) +{ + if (!btf_type_is_ptr(t)) + return false; + + t = btf_type_skip_modifiers(btf, t->type, NULL); + + return btf_type_is_struct(t); +} #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -660,15 +671,4 @@ static inline int btf_check_iter_arg(struct btf *btf, const struct btf_type *fun return -EOPNOTSUPP; } #endif - -static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) -{ - if (!btf_type_is_ptr(t)) - return false; - - t = btf_type_skip_modifiers(btf, t->type, NULL); - - return btf_type_is_struct(t); -} - #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index c0e3e1426a82..139bdececdcf 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -283,5 +283,6 @@ extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; extern u32 btf_bpf_map_id[]; +extern u32 bpf_kmem_cache_btf_id[]; #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 7d7578a8eac1..3a21947f2fd4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1119,6 +1119,7 @@ bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); +bool bpf_jit_supports_private_stack(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4a939c90dc2e..4162afc6b5d0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1116,6 +1116,7 @@ enum bpf_attach_type { BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, BPF_TRACE_KPROBE_SESSION, + BPF_TRACE_UPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; @@ -1973,6 +1974,8 @@ union bpf_attr { * program. * Return * The SMP id of the processor running the program. + * Attributes + * __bpf_fastcall * * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description @@ -3104,10 +3107,6 @@ union bpf_attr { * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration * option, and in this case it only works on functions tagged with * **ALLOW_ERROR_INJECTION** in the kernel code. - * - * Also, the helper is only available for the architectures having - * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, - * x86 architecture is the only one to support this feature. * Return * 0 * @@ -5372,7 +5371,7 @@ union bpf_attr { * Currently, the **flags** must be 0. Currently, nr_loops is * limited to 1 << 23 (~8 million) loops. * - * long (\*callback_fn)(u32 index, void \*ctx); + * long (\*callback_fn)(u64 index, void \*ctx); * * where **index** is the current index in the loop. The index * is zero-indexed. |