summaryrefslogtreecommitdiff
path: root/include/linux/bpf.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/bpf.h')
-rw-r--r--include/linux/bpf.h862
1 files changed, 770 insertions, 92 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f3f50e29d639..7719f6528445 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -6,7 +6,9 @@
#include <uapi/linux/bpf.h>
#include <uapi/linux/filter.h>
+#include <linux/bpf_defs.h>
+#include <crypto/sha2.h>
#include <linux/workqueue.h>
#include <linux/file.h>
#include <linux/percpu.h>
@@ -30,6 +32,10 @@
#include <linux/static_call.h>
#include <linux/memcontrol.h>
#include <linux/cfi.h>
+#include <linux/xattr.h>
+#include <linux/key.h>
+#include <linux/ftrace.h>
+#include <asm/rqspinlock.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
@@ -108,6 +114,7 @@ struct bpf_map_ops {
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);
+ int (*map_get_hash)(struct bpf_map *map);
/* funcs called by prog_array and perf_event_array map */
void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
@@ -121,7 +128,7 @@ struct bpf_map_ops {
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,
+ int (*map_check_btf)(struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
@@ -204,8 +211,24 @@ enum btf_field_type {
BPF_REFCOUNT = (1 << 9),
BPF_WORKQUEUE = (1 << 10),
BPF_UPTR = (1 << 11),
+ BPF_RES_SPIN_LOCK = (1 << 12),
+ BPF_TASK_WORK = (1 << 13),
};
+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 {
@@ -239,9 +262,11 @@ 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;
+ int task_work_off;
struct btf_field fields[];
};
@@ -257,7 +282,24 @@ 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;
+ bool sleepable;
+ u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE];
+ const struct btf_type *attach_func_proto;
+ enum bpf_attach_type expected_attach_type;
+};
+
struct bpf_map {
+ u8 sha[SHA256_DIGEST_SIZE];
+ u32 excl;
const struct bpf_map_ops *ops;
struct bpf_map *inner_map_meta;
#ifdef CONFIG_SECURITY
@@ -289,24 +331,16 @@ 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 */
+ char *excl_prog_sha;
};
static inline const char *btf_field_type_name(enum btf_field_type type)
@@ -314,6 +348,8 @@ 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:
@@ -335,17 +371,27 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
return "bpf_rb_node";
case BPF_REFCOUNT:
return "bpf_refcount";
+ case BPF_TASK_WORK:
+ return "bpf_task_work";
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:
@@ -365,6 +411,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
return sizeof(struct bpf_rb_node);
case BPF_REFCOUNT:
return sizeof(struct bpf_refcount);
+ case BPF_TASK_WORK:
+ return sizeof(struct bpf_task_work);
default:
WARN_ON_ONCE(1);
return 0;
@@ -376,6 +424,8 @@ 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:
@@ -395,6 +445,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
return __alignof__(struct bpf_rb_node);
case BPF_REFCOUNT:
return __alignof__(struct bpf_refcount);
+ case BPF_TASK_WORK:
+ return __alignof__(struct bpf_task_work);
default:
WARN_ON_ONCE(1);
return 0;
@@ -419,12 +471,14 @@ 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:
case BPF_KPTR_REF:
case BPF_KPTR_PERCPU:
case BPF_UPTR:
+ case BPF_TASK_WORK:
break;
default:
WARN_ON_ONCE(1);
@@ -439,6 +493,35 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f
return rec->field_mask & type;
}
+static inline bool btf_field_is_nmi_safe(enum btf_field_type type)
+{
+ switch (type) {
+ case BPF_SPIN_LOCK:
+ case BPF_RES_SPIN_LOCK:
+ case BPF_TIMER:
+ case BPF_WORKQUEUE:
+ case BPF_TASK_WORK:
+ case BPF_KPTR_UNREF:
+ case BPF_REFCOUNT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static inline bool btf_record_has_nmi_unsafe_fields(const struct btf_record *rec)
+{
+ int i;
+
+ if (IS_ERR_OR_NULL(rec))
+ return false;
+ for (i = 0; i < rec->cnt; i++) {
+ if (!btf_field_is_nmi_safe(rec->fields[i].type))
+ return true;
+ }
+ return false;
+}
+
static inline void bpf_obj_init(const struct btf_record *rec, void *obj)
{
int i;
@@ -561,12 +644,15 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
bool lock_src);
void bpf_timer_cancel_and_free(void *timer);
void bpf_wq_cancel_and_free(void *timer);
+void bpf_task_work_cancel_and_free(void *timer);
void bpf_list_head_free(const struct btf_field *field, void *list_head,
struct bpf_spin_lock *spin_lock);
void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
struct bpf_spin_lock *spin_lock);
u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena);
u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena);
+u64 bpf_arena_map_kern_vm_start(struct bpf_map *map);
+struct bpf_map *bpf_prog_arena(struct bpf_prog *prog);
int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
struct bpf_offload_dev;
@@ -606,7 +692,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
map->ops->map_seq_show_elem;
}
-int map_check_no_btf(const struct bpf_map *map,
+int map_check_no_btf(struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
@@ -614,6 +700,40 @@ int map_check_no_btf(const struct bpf_map *map,
bool bpf_map_meta_equal(const struct bpf_map *meta0,
const struct bpf_map *meta1);
+static inline bool bpf_map_has_internal_structs(struct bpf_map *map)
+{
+ return btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK);
+}
+
+void bpf_map_free_internal_structs(struct bpf_map *map, void *obj);
+
+int bpf_dynptr_from_file_sleepable(struct file *file, u32 flags,
+ struct bpf_dynptr *ptr__uninit);
+
+#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
+void *bpf_arena_alloc_pages_non_sleepable(void *p__map, void *addr__ign, u32 page_cnt, int node_id,
+ u64 flags);
+void bpf_arena_free_pages_non_sleepable(void *p__map, void *ptr__ign, u32 page_cnt);
+void *bpf_arena_alloc_pages_sleepable(void *p__map, void *addr__ign, u32 page_cnt, int node_id,
+ u64 flags);
+#else
+static inline void *bpf_arena_alloc_pages_non_sleepable(void *p__map, void *addr__ign, u32 page_cnt,
+ int node_id, u64 flags)
+{
+ return NULL;
+}
+
+static inline void bpf_arena_free_pages_non_sleepable(void *p__map, void *ptr__ign, u32 page_cnt)
+{
+}
+
+static inline void *bpf_arena_alloc_pages_sleepable(void *p__map, void *addr__ign, u32 page_cnt,
+ int node_id, u64 flags)
+{
+ return NULL;
+}
+#endif
+
extern const struct bpf_map_ops bpf_map_offload_ops;
/* bpf_type_flag contains a set of flags that are applicable to the values of
@@ -678,7 +798,7 @@ enum bpf_type_flag {
MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS),
/* PTR was passed from the kernel in a trusted context, and may be
- * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions.
+ * passed to kfuncs or BPF helper functions.
* Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above.
* PTR_UNTRUSTED refers to a kptr that was read directly from a map
* without invoking bpf_kptr_xchg(). What we really need to know is
@@ -733,12 +853,18 @@ enum bpf_type_flag {
*/
MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS),
+ /* DYNPTR points to skb_metadata_end()-skb_metadata_len() */
+ DYNPTR_TYPE_SKB_META = BIT(19 + BPF_BASE_TYPE_BITS),
+
+ /* DYNPTR points to file */
+ DYNPTR_TYPE_FILE = BIT(20 + BPF_BASE_TYPE_BITS),
+
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \
- | DYNPTR_TYPE_XDP)
+ | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META | DYNPTR_TYPE_FILE)
/* Max number of base types. */
#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS)
@@ -936,6 +1062,7 @@ enum bpf_reg_type {
PTR_TO_ARENA,
PTR_TO_BUF, /* reg points to a read/write buffer */
PTR_TO_FUNC, /* reg points to a bpf program function */
+ PTR_TO_INSN, /* reg points to a bpf program instruction */
CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */
__BPF_REG_TYPE_MAX,
@@ -968,6 +1095,7 @@ struct bpf_insn_access_aux {
struct {
struct btf *btf;
u32 btf_id;
+ u32 ref_id;
};
};
struct bpf_verifier_log *log; /* for verbose logs */
@@ -990,6 +1118,21 @@ 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);
@@ -1050,16 +1193,13 @@ 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
+ *
+ * Also reuse this macro for maximum number of arguments a BPF function
+ * or a kfunc can have. Args 1-5 are passed in registers, args 6-12 via
+ * stack arg slots. The JIT may map some stack arg slots to registers based
+ * on the native calling convention (e.g., arg 6 to R9 on x86-64).
*/
#define MAX_BPF_FUNC_ARGS 12
@@ -1068,7 +1208,7 @@ enum bpf_cgroup_storage_type {
*/
#define MAX_BPF_FUNC_REG_ARGS 5
-/* The argument is a structure. */
+/* The argument is a structure or a union. */
#define BTF_FMODEL_STRUCT_ARG BIT(0)
/* The argument is signed. */
@@ -1139,9 +1279,12 @@ enum {
#endif
};
-struct bpf_tramp_links {
- struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];
- int nr_links;
+#define BPF_TRAMP_COOKIE_INDEX_SHIFT 8
+#define BPF_TRAMP_IS_RETURN_SHIFT 63
+
+struct bpf_tramp_nodes {
+ struct bpf_tramp_node *nodes[BPF_MAX_TRAMP_LINKS];
+ int nr_nodes;
};
struct bpf_tramp_run_ctx;
@@ -1169,13 +1312,13 @@ struct bpf_tramp_run_ctx;
struct bpf_tramp_image;
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr);
void *arch_alloc_bpf_trampoline(unsigned int size);
void arch_free_bpf_trampoline(void *image, unsigned int size);
int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size);
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr);
+ struct bpf_tramp_nodes *tnodes, void *func_addr);
u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
struct bpf_tramp_run_ctx *run_ctx);
@@ -1190,6 +1333,18 @@ typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start,
bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog);
bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog);
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+ return flags & BPF_TRAMP_F_CALL_ORIG && !(flags & BPF_TRAMP_F_SKIP_FRAME);
+}
+#else
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+ return false;
+}
+#endif
+
struct bpf_ksym {
unsigned long start;
unsigned long end;
@@ -1197,6 +1352,8 @@ struct bpf_ksym {
struct list_head lnode;
struct latch_tree_node tnode;
bool prog;
+ u32 fp_start;
+ u32 fp_end;
};
enum bpf_tramp_prog_type {
@@ -1205,6 +1362,7 @@ enum bpf_tramp_prog_type {
BPF_TRAMP_MODIFY_RETURN,
BPF_TRAMP_MAX,
BPF_TRAMP_REPLACE, /* more than MAX */
+ BPF_TRAMP_FSESSION,
};
struct bpf_tramp_image {
@@ -1221,14 +1379,15 @@ struct bpf_tramp_image {
};
struct bpf_trampoline {
- /* hlist for trampoline_table */
- struct hlist_node hlist;
+ /* hlist for trampoline_key_table */
+ struct hlist_node hlist_key;
+ /* hlist for trampoline_ip_table */
+ struct hlist_node hlist_ip;
struct ftrace_ops *fops;
- /* serializes access to fields of this trampoline */
- struct mutex mutex;
refcount_t refcnt;
u32 flags;
u64 key;
+ unsigned long ip;
struct {
struct btf_func_model model;
void *addr;
@@ -1245,6 +1404,11 @@ struct bpf_trampoline {
int progs_cnt[BPF_TRAMP_MAX];
/* Executable image of trampoline */
struct bpf_tramp_image *cur_image;
+ /* Used as temporary old image storage for multi_attach */
+ struct {
+ struct bpf_tramp_image *old_image;
+ u32 old_flags;
+ } multi_attach;
};
struct bpf_attach_target_info {
@@ -1316,19 +1480,39 @@ enum bpf_dynptr_type {
BPF_DYNPTR_TYPE_SKB,
/* Underlying data is a xdp_buff */
BPF_DYNPTR_TYPE_XDP,
+ /* Points to skb_metadata_end()-skb_metadata_len() */
+ BPF_DYNPTR_TYPE_SKB_META,
+ /* Underlying data is a file */
+ BPF_DYNPTR_TYPE_FILE,
};
-int bpf_dynptr_check_size(u32 size);
-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);
+int bpf_dynptr_check_size(u64 size);
+u64 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u64 len);
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u64 len);
bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr);
+int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u64 offset,
+ void *src, u64 len, u64 flags);
+void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u64 offset,
+ void *buffer__nullable, u64 buffer__szk);
+
+static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u64 offset, u64 len)
+{
+ u64 size = __bpf_dynptr_size(ptr);
+
+ if (len > size || offset > size - len)
+ return -E2BIG;
+
+ return 0;
+}
+
+struct bpf_tracing_multi_link;
#ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog);
-int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog);
struct bpf_trampoline *bpf_trampoline_get(u64 key,
@@ -1336,6 +1520,11 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
void bpf_trampoline_put(struct bpf_trampoline *tr);
int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
+int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
+ struct bpf_tracing_multi_link *link);
+int bpf_trampoline_multi_detach(struct bpf_prog *prog,
+ struct bpf_tracing_multi_link *link);
+
/*
* When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
* indirection with a direct call to the bpf program. If the architecture does
@@ -1407,17 +1596,21 @@ 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);
+bool bpf_has_frame_pointer(unsigned long ip);
int bpf_jit_charge_modmem(u32 size);
void bpf_jit_uncharge_modmem(u32 size);
bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
+bool bpf_insn_is_indirect_target(const struct bpf_verifier_env *env, const struct bpf_prog *prog,
+ int insn_idx);
+u16 bpf_out_stack_arg_cnt(const struct bpf_verifier_env *env, const struct bpf_prog *prog);
#else
-static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+static inline int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog)
{
return -ENOTSUPP;
}
-static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog)
{
@@ -1444,6 +1637,16 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
{
return false;
}
+static inline int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
+ struct bpf_tracing_multi_link *link)
+{
+ return -ENOTSUPP;
+}
+static inline int bpf_trampoline_multi_detach(struct bpf_prog *prog,
+ struct bpf_tracing_multi_link *link)
+{
+ return -ENOTSUPP;
+}
#endif
struct bpf_func_info_aux {
@@ -1481,6 +1684,8 @@ struct bpf_ctx_arg_aux {
enum bpf_reg_type reg_type;
struct btf *btf;
u32 btf_id;
+ u32 ref_id;
+ bool refcounted;
};
struct btf_mod_pair {
@@ -1490,6 +1695,50 @@ 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;
+};
+
+enum bpf_sig_verdict {
+ BPF_SIG_UNSIGNED = 0,
+ BPF_SIG_VERIFIED,
+};
+
+enum bpf_sig_keyring {
+ BPF_SIG_KEYRING_NONE = 0,
+ BPF_SIG_KEYRING_BUILTIN,
+ BPF_SIG_KEYRING_SECONDARY,
+ BPF_SIG_KEYRING_PLATFORM,
+ BPF_SIG_KEYRING_USER,
+};
+
struct bpf_prog_aux {
atomic64_t refcnt;
u32 used_map_cnt;
@@ -1503,11 +1752,13 @@ 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;
+ u32 subprog_start;
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 +1779,13 @@ struct bpf_prog_aux {
bool jits_use_priv_stack;
bool priv_stack_requested;
bool changes_pkt_data;
+ bool might_sleep;
+ bool kprobe_write_ctx;
+ struct {
+ s32 keyring_serial;
+ u8 keyring_type;
+ u8 verdict;
+ } sig;
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;
@@ -1537,6 +1795,7 @@ struct bpf_prog_aux {
/* function name for valid attach_btf_id */
const char *attach_func_name;
struct bpf_prog **func;
+ struct bpf_prog_aux *main_prog_aux;
void *jit_data; /* JIT specific data. arch dependent */
struct bpf_jit_poke_descriptor *poke_tab;
struct bpf_kfunc_desc_tab *kfunc_tab;
@@ -1547,6 +1806,7 @@ 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;
@@ -1558,6 +1818,7 @@ struct bpf_prog_aux {
struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
char name[BPF_OBJ_NAME_LEN];
u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64);
+ u16 stack_arg_sp_adjust;
#ifdef CONFIG_SECURITY
void *security;
#endif
@@ -1595,8 +1856,13 @@ struct bpf_prog_aux {
struct work_struct work;
struct rcu_head rcu;
};
+ struct bpf_stream stream[2];
+ struct mutex st_ops_assoc_mutex;
+ struct bpf_map __rcu *st_ops_assoc;
};
+#define BPF_NR_CONTEXTS 4 /* normal, softirq, hardirq, NMI */
+
struct bpf_prog {
u16 pages; /* Number of allocated pages */
u16 jited:1, /* Is our filter JIT'ed? */
@@ -1612,15 +1878,19 @@ struct bpf_prog {
enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
call_get_func_ip:1, /* Do we call get_func_ip() */
+ call_session_cookie:1, /* Do we call bpf_session_cookie() */
tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */
sleepable:1; /* BPF program is sleepable */
enum bpf_prog_type type; /* Type of BPF program */
enum bpf_attach_type expected_attach_type; /* For some prog types */
u32 len; /* Number of filter blocks */
u32 jited_len; /* Size of jited insns in bytes */
- u8 tag[BPF_TAG_SIZE];
+ union {
+ u8 digest[SHA256_DIGEST_SIZE];
+ u8 tag[BPF_TAG_SIZE];
+ };
struct bpf_prog_stats __percpu *stats;
- int __percpu *active;
+ u8 __percpu *active; /* u8[BPF_NR_CONTEXTS] for recursion protection */
unsigned int (*bpf_func)(const void *ctx,
const struct bpf_insn *insn);
struct bpf_prog_aux *aux; /* Auxiliary fields */
@@ -1646,11 +1916,10 @@ 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 +1927,11 @@ 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 {
@@ -1671,6 +1945,10 @@ struct bpf_link_ops {
* target hook is sleepable, we'll go through tasks trace RCU GP and
* then "classic" RCU GP; this need for chaining tasks trace and
* classic RCU GPs is designated by setting bpf_link->sleepable flag
+ *
+ * For non-sleepable tracepoint links we go through SRCU gp instead,
+ * since RCU is not used in that case. Sleepable tracepoints still
+ * follow the scheme above.
*/
void (*dealloc_deferred)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
@@ -1684,12 +1962,17 @@ struct bpf_link_ops {
__poll_t (*poll)(struct file *file, struct poll_table_struct *pts);
};
-struct bpf_tramp_link {
- struct bpf_link link;
+struct bpf_tramp_node {
+ struct bpf_link *link;
struct hlist_node tramp_hlist;
u64 cookie;
};
+struct bpf_tramp_link {
+ struct bpf_link link;
+ struct bpf_tramp_node node;
+};
+
struct bpf_shim_tramp_link {
struct bpf_tramp_link link;
struct bpf_trampoline *trampoline;
@@ -1697,11 +1980,33 @@ struct bpf_shim_tramp_link {
struct bpf_tracing_link {
struct bpf_tramp_link link;
- enum bpf_attach_type attach_type;
+ struct bpf_tramp_node fexit;
struct bpf_trampoline *trampoline;
struct bpf_prog *tgt_prog;
};
+struct bpf_tracing_multi_node {
+ struct bpf_tramp_node node;
+ struct bpf_trampoline *trampoline;
+ struct ftrace_func_entry entry;
+};
+
+struct bpf_tracing_multi_data {
+ struct ftrace_hash *unreg;
+ struct ftrace_hash *modify;
+ struct ftrace_hash *reg;
+ struct ftrace_func_entry *entry;
+};
+
+struct bpf_tracing_multi_link {
+ struct bpf_link link;
+ struct bpf_tracing_multi_data data;
+ u64 *cookies;
+ struct bpf_tramp_node *fexits;
+ int nodes_cnt;
+ struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt);
+};
+
struct bpf_raw_tp_link {
struct bpf_link link;
struct bpf_raw_event_map *btp;
@@ -1725,6 +2030,8 @@ struct bpf_mount_opts {
u64 delegate_maps;
u64 delegate_progs;
u64 delegate_attachs;
+
+ struct simple_xattr_cache xa_cache;
};
struct bpf_token {
@@ -1784,12 +2091,14 @@ struct btf_member;
* reason, if this callback is not defined, the check is skipped as
* the struct_ops map will have final verification performed in
* @reg.
- * @type: BTF type.
- * @value_type: Value type.
+ * @cfi_stubs: Pointer to a structure of stub functions for CFI. These stubs
+ * provide the correct Control Flow Integrity hashes for the
+ * trampolines generated by BPF struct_ops.
+ * @owner: The module that owns this struct_ops. Used for module reference
+ * counting to ensure the module providing the struct_ops cannot be
+ * unloaded while in use.
* @name: The name of the struct bpf_struct_ops object.
* @func_models: Func models
- * @type_id: BTF type id.
- * @value_id: BTF value id.
*/
struct bpf_struct_ops {
const struct bpf_verifier_ops *verifier_ops;
@@ -1847,6 +2156,46 @@ struct bpf_struct_ops_common_value {
enum bpf_struct_ops_state state;
};
+static inline bool bpf_prog_get_recursion_context(struct bpf_prog *prog)
+{
+#ifdef CONFIG_ARM64
+ u8 rctx = interrupt_context_level();
+ u8 *active = this_cpu_ptr(prog->active);
+ u32 val;
+
+ preempt_disable();
+ active[rctx]++;
+ val = le32_to_cpu(*(__le32 *)active);
+ preempt_enable();
+ if (val != BIT(rctx * 8))
+ return false;
+
+ return true;
+#else
+ return this_cpu_inc_return(*(int __percpu *)(prog->active)) == 1;
+#endif
+}
+
+static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog)
+{
+#ifdef CONFIG_ARM64
+ u8 rctx = interrupt_context_level();
+ u8 *active = this_cpu_ptr(prog->active);
+
+ preempt_disable();
+ active[rctx]--;
+ preempt_enable();
+#else
+ this_cpu_dec(*(int __percpu *)(prog->active));
+#endif
+}
+
+static inline bool is_tracing_multi(enum bpf_attach_type type)
+{
+ return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI ||
+ type == BPF_TRACE_FSESSION_MULTI;
+}
+
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
/* This macro helps developer to register a struct_ops type and generate
* type information correctly. Developers should use this macro to register
@@ -1867,8 +2216,8 @@ void bpf_struct_ops_put(const void *kdata);
int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff);
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value);
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
- struct bpf_tramp_link *link,
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_nodes *tnodes,
+ struct bpf_tramp_node *node,
const struct btf_func_model *model,
void *stub_func,
void **image, u32 *image_off,
@@ -1889,6 +2238,13 @@ static inline void bpf_module_put(const void *data, struct module *owner)
module_put(owner);
}
int bpf_struct_ops_link_create(union bpf_attr *attr);
+int bpf_prog_assoc_struct_ops(struct bpf_prog *prog, struct bpf_map *map);
+void bpf_prog_disassoc_struct_ops(struct bpf_prog *prog);
+void *bpf_prog_get_assoc_struct_ops(const struct bpf_prog_aux *aux);
+u32 bpf_struct_ops_id(const void *kdata);
+int bpf_struct_ops_for_each_prog(const void *kdata,
+ int (*cb)(struct bpf_prog *prog, void *data),
+ void *data);
#ifdef CONFIG_NET
/* Define it here to avoid the use of forward declaration */
@@ -1935,6 +2291,17 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr)
{
return -EOPNOTSUPP;
}
+static inline int bpf_prog_assoc_struct_ops(struct bpf_prog *prog, struct bpf_map *map)
+{
+ return -EOPNOTSUPP;
+}
+static inline void bpf_prog_disassoc_struct_ops(struct bpf_prog *prog)
+{
+}
+static inline void *bpf_prog_get_assoc_struct_ops(const struct bpf_prog_aux *aux)
+{
+ return NULL;
+}
static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map)
{
}
@@ -1945,13 +2312,51 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op
#endif
+static inline int bpf_fsession_cnt(struct bpf_tramp_nodes *nodes)
+{
+ struct bpf_tramp_nodes fentries = nodes[BPF_TRAMP_FENTRY];
+ int cnt = 0;
+
+ for (int i = 0; i < nodes[BPF_TRAMP_FENTRY].nr_nodes; i++) {
+ if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION)
+ cnt++;
+ if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)
+ cnt++;
+ }
+
+ return cnt;
+}
+
+static inline bool bpf_prog_calls_session_cookie(struct bpf_tramp_node *node)
+{
+ return node->link->prog->call_session_cookie;
+}
+
+static inline int bpf_fsession_cookie_cnt(struct bpf_tramp_nodes *nodes)
+{
+ struct bpf_tramp_nodes fentries = nodes[BPF_TRAMP_FENTRY];
+ int cnt = 0;
+
+ for (int i = 0; i < nodes[BPF_TRAMP_FENTRY].nr_nodes; i++) {
+ if (bpf_prog_calls_session_cookie(fentries.nodes[i]))
+ cnt++;
+ }
+
+ return cnt;
+}
+
+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;
}
@@ -1972,6 +2377,12 @@ struct bpf_array {
};
};
+/*
+ * The bpf_array_get_next_key() function may be used for all array-like
+ * maps, i.e., maps with u32 keys with range [0 ,..., max_entries)
+ */
+int bpf_array_get_next_key(struct bpf_map *map, void *key, void *next_key);
+
#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */
#define MAX_TAIL_CALL_CNT 33
@@ -1980,6 +2391,7 @@ 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 +2428,16 @@ 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_obj(*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 +2458,8 @@ 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,
@@ -2072,18 +2496,13 @@ struct bpf_prog_array {
struct bpf_prog_array_item items[];
};
-struct bpf_empty_prog_array {
- struct bpf_prog_array hdr;
- struct bpf_prog *null_prog;
-};
-
/* to avoid allocating empty bpf_prog_array for cgroups that
* don't have bpf program attached use one global 'bpf_empty_prog_array'
* It will not be modified the caller of bpf_prog_array_alloc()
* (since caller requested prog_cnt == 0)
* that pointer should be 'freed' by bpf_prog_array_free()
*/
-extern struct bpf_empty_prog_array bpf_empty_prog_array;
+extern struct bpf_prog_array bpf_empty_prog_array;
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
void bpf_prog_array_free(struct bpf_prog_array *progs);
@@ -2231,6 +2650,12 @@ 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);
+
+#define bpf_rcu_lock_held() \
+ (rcu_read_lock_held() || rcu_read_lock_trace_held() || rcu_read_lock_bh_held())
+
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
extern struct mutex bpf_stats_enabled_mutex;
@@ -2257,6 +2682,7 @@ 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; \
@@ -2293,6 +2719,8 @@ struct btf_record *btf_record_dup(const struct btf_record *rec);
bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj);
+void bpf_obj_free_task_work(const struct btf_record *rec, void *obj);
+void bpf_obj_cancel_fields(struct bpf_map *map, void *obj);
void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
@@ -2348,11 +2776,18 @@ 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_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg,
+ struct mem_cgroup **new_memcg);
+void bpf_map_memcg_exit(struct mem_cgroup *old_memcg,
+ struct mem_cgroup *memcg);
void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
int node);
+void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags,
+ int node);
void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags);
void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size,
gfp_t flags);
@@ -2365,12 +2800,25 @@ void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
*/
#define bpf_map_kmalloc_node(_map, _size, _flags, _node) \
kmalloc_node(_size, _flags, _node)
+#define bpf_map_kmalloc_nolock(_map, _size, _flags, _node) \
+ kmalloc_nolock(_size, _flags, _node)
#define bpf_map_kzalloc(_map, _size, _flags) \
kzalloc(_size, _flags)
#define bpf_map_kvcalloc(_map, _n, _size, _flags) \
kvcalloc(_n, _size, _flags)
#define bpf_map_alloc_percpu(_map, _size, _align, _flags) \
__alloc_percpu_gfp(_size, _align, _flags)
+static inline void bpf_map_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg,
+ struct mem_cgroup **new_memcg)
+{
+ *new_memcg = NULL;
+ *old_memcg = NULL;
+}
+
+static inline void bpf_map_memcg_exit(struct mem_cgroup *old_memcg,
+ struct mem_cgroup *memcg)
+{
+}
#endif
static inline int
@@ -2418,22 +2866,30 @@ 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);
+void bpf_tramp_link_init(struct bpf_tramp_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type, u64 cookie);
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);
@@ -2448,6 +2904,9 @@ 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);
@@ -2546,7 +3005,7 @@ 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);
@@ -2563,14 +3022,14 @@ 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_copy(struct bpf_map *map, void *key, void *value, u64 flags);
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
u64 flags);
-int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
+int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, bool delete);
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
@@ -2584,10 +3043,18 @@ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size,
size_t actual_size);
/* verify correctness of eBPF program */
-int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size);
+struct bpf_log_attr;
+int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr,
+ struct bpf_log_attr *attr_log);
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+s32 bpf_call_args_imm(s16 idx);
+#else
+static inline s32 bpf_call_args_imm(s16 idx)
+{
+ return 0;
+}
#endif
struct btf *bpf_get_btf_vmlinux(void);
@@ -2747,6 +3214,57 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
enum bpf_dynptr_type type, u32 offset, u32 size);
void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr);
+void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip);
+
+static __always_inline u32
+bpf_prog_run_array_sleepable(const struct bpf_prog_array *array,
+ const void *ctx, bpf_prog_run_fn run_prog)
+{
+ const struct bpf_prog_array_item *item;
+ struct bpf_prog *prog;
+ struct bpf_run_ctx *old_run_ctx;
+ struct bpf_trace_run_ctx run_ctx;
+ u32 ret = 1;
+
+ if (unlikely(!array))
+ return ret;
+
+ migrate_disable();
+
+ run_ctx.is_uprobe = false;
+
+ old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+ item = &array->items[0];
+ while ((prog = READ_ONCE(item->prog))) {
+ /* Skip dummy_bpf_prog placeholder (len == 0) */
+ if (unlikely(!prog->len)) {
+ item++;
+ continue;
+ }
+
+ if (unlikely(!bpf_prog_get_recursion_context(prog))) {
+ bpf_prog_inc_misses_counter(prog);
+ bpf_prog_put_recursion_context(prog);
+ item++;
+ continue;
+ }
+
+ run_ctx.bpf_cookie = item->bpf_cookie;
+
+ if (!prog->sleepable) {
+ guard(rcu)();
+ ret &= run_prog(prog, ctx);
+ } else {
+ ret &= run_prog(prog, ctx);
+ }
+
+ bpf_prog_put_recursion_context(prog);
+ item++;
+ }
+ bpf_reset_run_ctx(old_run_ctx);
+ migrate_enable();
+ return ret;
+}
#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
@@ -2785,13 +3303,19 @@ 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)
+{
+}
+
+static inline void bpf_tramp_link_init(struct bpf_tramp_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type, u64 cookie)
{
}
@@ -2846,6 +3370,13 @@ 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)
{
}
@@ -3027,8 +3558,18 @@ static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
{
}
+
+static inline void bpf_prog_report_arena_violation(bool write, unsigned long addr,
+ unsigned long fault_ip)
+{
+}
#endif /* CONFIG_BPF_SYSCALL */
+static inline bool bpf_net_capable(void)
+{
+ return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
+}
+
static __always_inline int
bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
{
@@ -3269,6 +3810,53 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
#endif /* CONFIG_BPF_SYSCALL */
#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
+#ifdef CONFIG_KEYS
+struct bpf_key {
+ struct key *key;
+ bool has_ref;
+};
+#endif /* CONFIG_KEYS */
+
+#if defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags);
+struct bpf_key *bpf_lookup_system_key(u64 id);
+void bpf_key_put(struct bpf_key *bkey);
+int bpf_verify_pkcs7_signature(const struct bpf_dynptr *data_p,
+ const struct bpf_dynptr *sig_p,
+ struct bpf_key *trusted_keyring);
+
+static inline s32 bpf_key_serial(const struct bpf_key *key)
+{
+ return key->has_ref ? key->key->serial : 0;
+}
+#else
+static inline struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+{
+ return NULL;
+}
+
+static inline struct bpf_key *bpf_lookup_system_key(u64 id)
+{
+ return NULL;
+}
+
+static inline void bpf_key_put(struct bpf_key *bkey)
+{
+}
+
+static inline int bpf_verify_pkcs7_signature(const struct bpf_dynptr *data_p,
+ const struct bpf_dynptr *sig_p,
+ struct bpf_key *trusted_keyring)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline s32 bpf_key_serial(const struct bpf_key *key)
+{
+ return 0;
+}
+#endif /* defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL) */
+
/* verifier prototypes for helper functions called from eBPF programs */
extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
extern const struct bpf_func_proto bpf_map_update_elem_proto;
@@ -3345,6 +3933,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
+extern const struct bpf_func_proto bpf_sk_setsockopt_nodelay_proto;
extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto;
extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto;
extern const struct bpf_func_proto bpf_find_vma_proto;
@@ -3467,12 +4056,14 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
#endif /* CONFIG_INET */
enum bpf_text_poke_type {
+ BPF_MOD_NOP,
BPF_MOD_CALL,
BPF_MOD_JUMP,
};
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
- void *addr1, void *addr2);
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+ enum bpf_text_poke_type new_t, void *old_addr,
+ void *new_addr);
void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
struct bpf_prog *new, struct bpf_prog *old);
@@ -3486,6 +4077,16 @@ 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;
@@ -3493,9 +4094,33 @@ 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);
@@ -3505,15 +4130,6 @@ static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {}
static inline void bpf_cgroup_atype_put(int cgroup_atype) {}
#endif /* CONFIG_BPF_LSM */
-struct key;
-
-#ifdef CONFIG_KEYS
-struct bpf_key {
- struct key *key;
- bool has_ref;
-};
-#endif /* CONFIG_KEYS */
-
static inline bool type_is_alloc(u32 type)
{
return type & MEM_ALLOC;
@@ -3531,4 +4147,66 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog)
return prog->aux->func_idx != 0;
}
+const struct bpf_line_info *bpf_find_linfo(const struct bpf_prog *prog, u32 insn_off);
+void bpf_get_linfo_file_line(struct btf *btf, const struct bpf_line_info *linfo,
+ const char **filep, const char **linep, int *nump);
+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);
+
+int bpf_insn_array_init(struct bpf_map *map, const struct bpf_prog *prog);
+int bpf_insn_array_ready(struct bpf_map *map);
+void bpf_insn_array_release(struct bpf_map *map);
+void bpf_insn_array_adjust(struct bpf_map *map, u32 off, u32 len);
+void bpf_insn_array_adjust_after_remove(struct bpf_map *map, u32 off, u32 len);
+
+#ifdef CONFIG_BPF_SYSCALL
+void bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image);
+#else
+static inline void
+bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image)
+{
+}
+#endif
+
+static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
+{
+ switch (map_type) {
+ case BPF_MAP_TYPE_PERCPU_ARRAY:
+ case BPF_MAP_TYPE_PERCPU_HASH:
+ case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
+{
+ u32 cpu;
+
+ if ((u32)flags & ~allowed_flags)
+ return -EINVAL;
+
+ if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+ return -EINVAL;
+
+ if (!(flags & BPF_F_CPU) && flags >> 32)
+ return -EINVAL;
+
+ if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
+ if (!bpf_map_supports_cpu_flags(map->map_type))
+ return -EINVAL;
+ if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS))
+ return -EINVAL;
+
+ cpu = flags >> 32;
+ if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus())
+ return -ERANGE;
+ }
+
+ return 0;
+}
+
#endif /* _LINUX_BPF_H */