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.h183
1 files changed, 155 insertions, 28 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bdadb0bb6cec..5b25d278409b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -30,6 +30,7 @@
#include <linux/static_call.h>
#include <linux/memcontrol.h>
#include <linux/cfi.h>
+#include <asm/rqspinlock.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
@@ -203,6 +204,8 @@ 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),
+ BPF_RES_SPIN_LOCK = (1 << 12),
};
typedef void (*btf_dtor_kfunc_t)(void *);
@@ -238,6 +241,7 @@ struct btf_record {
u32 cnt;
u32 field_mask;
int spin_lock_off;
+ int res_spin_lock_off;
int timer_off;
int wq_off;
int refcount_off;
@@ -313,6 +317,8 @@ 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:
@@ -322,6 +328,8 @@ 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:
@@ -338,11 +346,19 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
}
}
+#if IS_ENABLED(CONFIG_DEBUG_KERNEL)
+#define BPF_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
+#else
+#define BPF_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
+#endif
+
static inline u32 btf_field_type_size(enum btf_field_type type)
{
switch (type) {
case BPF_SPIN_LOCK:
return sizeof(struct bpf_spin_lock);
+ case BPF_RES_SPIN_LOCK:
+ return sizeof(struct bpf_res_spin_lock);
case BPF_TIMER:
return sizeof(struct bpf_timer);
case BPF_WORKQUEUE:
@@ -350,6 +366,7 @@ 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);
@@ -372,6 +389,8 @@ 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:
@@ -379,6 +398,7 @@ 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);
@@ -414,11 +434,13 @@ 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:
break;
default:
WARN_ON_ONCE(1);
@@ -507,6 +529,25 @@ 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 +948,6 @@ 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 +960,10 @@ 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
@@ -943,6 +984,7 @@ struct bpf_insn_access_aux {
struct {
struct btf *btf;
u32 btf_id;
+ u32 ref_obj_id;
};
};
struct bpf_verifier_log *log; /* for verbose logs */
@@ -965,6 +1007,21 @@ 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);
@@ -1298,10 +1355,28 @@ u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len);
void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len);
bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr);
+int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset,
+ void *src, u32 len, u64 flags);
+void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u32 offset,
+ void *buffer__opt, u32 buffer__szk);
+
+static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len)
+{
+ u32 size = __bpf_dynptr_size(ptr);
+
+ if (len > size || offset > size - len)
+ return -E2BIG;
+
+ return 0;
+}
#ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_tramp_link *link, 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 +1448,8 @@ 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 +1458,14 @@ 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;
}
@@ -1449,6 +1527,8 @@ struct bpf_ctx_arg_aux {
enum bpf_reg_type reg_type;
struct btf *btf;
u32 btf_id;
+ u32 ref_obj_id;
+ bool refcounted;
};
struct btf_mod_pair {
@@ -1471,11 +1551,13 @@ 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;
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;
struct bpf_trampoline *dst_trampoline;
@@ -1491,7 +1573,15 @@ 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;
+ bool changes_pkt_data;
+ bool might_sleep;
+ u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
+ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
struct bpf_arena *arena;
+ 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 */
@@ -1507,6 +1597,7 @@ 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;
@@ -1606,6 +1697,11 @@ 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;
/* rcu is used before freeing, work can be used to schedule that
* RCU-based freeing before that, so they never overlap
*/
@@ -1622,8 +1718,10 @@ struct bpf_link_ops {
*/
void (*dealloc)(struct bpf_link *link);
/* deallocate link resources callback, called after RCU grace period;
- * if underlying BPF program is sleepable we go through tasks trace
- * RCU GP and then "classic" RCU GP
+ * if either the underlying BPF program is sleepable or BPF link's
+ * 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
*/
void (*dealloc_deferred)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
@@ -1898,6 +1996,9 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op
#endif
+int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
+ const struct bpf_ctx_arg_aux *info, u32 cnt);
+
#if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM)
int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
int cgroup_atype);
@@ -1933,6 +2034,7 @@ struct bpf_array {
*/
enum {
BPF_MAX_LOOPS = 8 * 1024 * 1024,
+ BPF_MAX_TIMED_LOOPS = 0xffff,
};
#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \
@@ -1989,6 +2091,8 @@ 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,
@@ -2147,26 +2251,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
* rcu-protected dynamically sized maps.
*/
static __always_inline u32
-bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
const void *ctx, bpf_prog_run_fn run_prog)
{
const struct bpf_prog_array_item *item;
const struct bpf_prog *prog;
- const struct bpf_prog_array *array;
struct bpf_run_ctx *old_run_ctx;
struct bpf_trace_run_ctx run_ctx;
u32 ret = 1;
might_fault();
+ RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held");
+
+ if (unlikely(!array))
+ return ret;
- rcu_read_lock_trace();
migrate_disable();
run_ctx.is_uprobe = true;
- array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
- if (unlikely(!array))
- goto out;
old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
item = &array->items[0];
while ((prog = READ_ONCE(item->prog))) {
@@ -2181,9 +2284,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
rcu_read_unlock();
}
bpf_reset_run_ctx(old_run_ctx);
-out:
migrate_enable();
- rcu_read_unlock_trace();
return ret;
}
@@ -2255,6 +2356,14 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
struct bpf_map *bpf_map_get(u32 ufd);
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
+/*
+ * The __bpf_map_get() and __btf_get_by_fd() functions parse a file
+ * descriptor and return a corresponding map or btf object.
+ * Their names are double underscored to emphasize the fact that they
+ * do not increase refcnt. To also increase refcnt use corresponding
+ * bpf_map_get() and btf_get_by_fd() functions.
+ */
+
static inline struct bpf_map *__bpf_map_get(struct fd f)
{
if (fd_empty(f))
@@ -2264,6 +2373,15 @@ static inline struct bpf_map *__bpf_map_get(struct fd f)
return fd_file(f)->private_data;
}
+static inline struct btf *__btf_get_by_fd(struct fd f)
+{
+ if (fd_empty(f))
+ return ERR_PTR(-EBADF);
+ if (unlikely(fd_file(f)->f_op != &btf_fops))
+ return ERR_PTR(-EINVAL);
+ return fd_file(f)->private_data;
+}
+
void bpf_map_inc(struct bpf_map *map);
void bpf_map_inc_with_uref(struct bpf_map *map);
struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref);
@@ -2287,7 +2405,7 @@ int generic_map_delete_batch(struct bpf_map *map,
struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
-int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
+int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
unsigned long nr_pages, struct page **page_array);
#ifdef CONFIG_MEMCG
void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
@@ -2370,6 +2488,9 @@ 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);
+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);
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);
@@ -2482,7 +2603,7 @@ 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);
@@ -2542,10 +2663,10 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
struct bpf_map *map, bool exclude_ingress);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
- struct bpf_prog *xdp_prog);
+ const struct bpf_prog *xdp_prog);
int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog, struct bpf_map *map,
- bool exclude_ingress);
+ const struct bpf_prog *xdp_prog,
+ struct bpf_map *map, bool exclude_ingress);
void __cpu_map_flush(struct list_head *flush_list);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
@@ -2725,6 +2846,12 @@ static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type 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)
+{
+}
+
static inline int bpf_link_prime(struct bpf_link *link,
struct bpf_link_primer *primer)
{
@@ -2809,15 +2936,15 @@ struct sk_buff;
static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+ const struct bpf_prog *xdp_prog)
{
return 0;
}
static inline
int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog, struct bpf_map *map,
- bool exclude_ingress)
+ const struct bpf_prog *xdp_prog,
+ struct bpf_map *map, bool exclude_ingress)
{
return 0;
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-28 11:52:49 +0300