diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf.h | 54 | ||||
| -rw-r--r-- | include/linux/bpf_local_storage.h | 19 | ||||
| -rw-r--r-- | include/linux/bpf_mem_alloc.h | 2 | ||||
| -rw-r--r-- | include/linux/bpf_verifier.h | 72 | ||||
| -rw-r--r-- | include/linux/btf.h | 8 | ||||
| -rw-r--r-- | include/linux/filter.h | 9 | ||||
| -rw-r--r-- | include/linux/module.h | 127 | ||||
| -rw-r--r-- | include/linux/sched.h | 7 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 40 | ||||
| -rw-r--r-- | include/net/fou.h | 2 | ||||
| -rw-r--r-- | include/net/ip_tunnels.h | 27 | ||||
| -rw-r--r-- | include/net/tcp.h | 3 | ||||
| -rw-r--r-- | include/net/xdp.h | 29 | ||||
| -rw-r--r-- | include/net/xsk_buff_pool.h | 9 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 61 |
15 files changed, 281 insertions, 188 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6792a7940e1e..2c6095bd7d69 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -96,11 +96,11 @@ struct bpf_map_ops { /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); - int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); - int (*map_delete_elem)(struct bpf_map *map, void *key); - int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); - int (*map_pop_elem)(struct bpf_map *map, void *value); - int (*map_peek_elem)(struct bpf_map *map, void *value); + 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 */ @@ -139,7 +139,7 @@ struct bpf_map_ops { struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ - int (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); + 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 @@ -157,7 +157,7 @@ struct bpf_map_ops { int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); - int (*map_for_each_callback)(struct bpf_map *map, + long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); @@ -189,9 +189,14 @@ enum btf_field_type { BPF_RB_NODE | BPF_RB_ROOT, }; +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; }; @@ -888,8 +893,7 @@ struct bpf_verifier_ops { struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); }; struct bpf_prog_offload_ops { @@ -1098,6 +1102,7 @@ struct bpf_trampoline { struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; + struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; @@ -1401,6 +1406,7 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { @@ -1469,6 +1475,8 @@ struct bpf_link_ops { void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); + int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, + struct bpf_map *old_map); }; struct bpf_tramp_link { @@ -1511,6 +1519,8 @@ struct bpf_struct_ops { void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); + int (*update)(void *kdata, void *old_kdata); + int (*validate)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; const char *name; @@ -1545,6 +1555,7 @@ static inline void bpf_module_put(const void *data, struct module *owner) else module_put(owner); } +int bpf_struct_ops_link_create(union bpf_attr *attr); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ @@ -1585,6 +1596,11 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, { return -EINVAL; } +static inline int bpf_struct_ops_link_create(union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + #endif #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) @@ -1617,8 +1633,12 @@ struct bpf_array { #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 -/* Maximum number of loops for bpf_loop */ -#define BPF_MAX_LOOPS BIT(23) +/* Maximum number of loops for bpf_loop and bpf_iter_num. + * It's enum to expose it (and thus make it discoverable) through BTF. + */ +enum { + BPF_MAX_LOOPS = 8 * 1024 * 1024, +}; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ @@ -1921,7 +1941,7 @@ void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, - u32 offset, enum btf_field_type type); + u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); @@ -1934,6 +1954,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); 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); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); @@ -2154,7 +2175,7 @@ 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); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); @@ -2242,7 +2263,7 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, @@ -2281,7 +2302,7 @@ struct bpf_core_ctx { bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, const char *suffix); + const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, @@ -2496,7 +2517,8 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { return -EACCES; } diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index d934248b8e81..173ec7f43ed1 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -13,6 +13,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> +#include <linux/bpf_mem_alloc.h> #include <uapi/linux/btf.h> #define BPF_LOCAL_STORAGE_CACHE_SIZE 16 @@ -55,6 +56,9 @@ struct bpf_local_storage_map { u32 bucket_log; u16 elem_size; u16 cache_idx; + struct bpf_mem_alloc selem_ma; + struct bpf_mem_alloc storage_ma; + bool bpf_ma; }; struct bpf_local_storage_data { @@ -83,6 +87,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage { struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct bpf_local_storage_map __rcu *smap; struct hlist_head list; /* List of bpf_local_storage_elem */ void *owner; /* The object that owns the above "list" of * bpf_local_storage_elem. @@ -121,14 +126,15 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr); struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, - struct bpf_local_storage_cache *cache); + struct bpf_local_storage_cache *cache, + bool bpf_ma); struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit); -bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage); +void bpf_local_storage_destroy(struct bpf_local_storage *local_storage); void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache, @@ -142,17 +148,19 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); - 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); +void bpf_selem_free(struct bpf_local_storage_elem *selem, + struct bpf_local_storage_map *smap, + bool reuse_now); + int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, @@ -163,7 +171,6 @@ 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 bpf_local_storage_free_rcu(struct rcu_head *rcu); u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); #endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index a7104af61ab4..3929be5743f4 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -31,5 +31,7 @@ void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); /* kmem_cache_alloc/free equivalent: */ void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_cache_raw_free(void *ptr); +void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags); #endif /* _BPF_MEM_ALLOC_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 18538bad2b8c..f03852b89d28 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -59,6 +59,14 @@ struct bpf_active_lock { u32 id; }; +#define ITER_PREFIX "bpf_iter_" + +enum bpf_iter_state { + BPF_ITER_STATE_INVALID, /* for non-first slot */ + BPF_ITER_STATE_ACTIVE, + BPF_ITER_STATE_DRAINED, +}; + struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; @@ -103,6 +111,18 @@ struct bpf_reg_state { bool first_slot; } dynptr; + /* For bpf_iter stack slots */ + struct { + /* BTF container and BTF type ID describing + * struct bpf_iter_<type> of an iterator state + */ + struct btf *btf; + u32 btf_id; + /* packing following two fields to fit iter state into 16 bytes */ + enum bpf_iter_state state:2; + int depth:30; + } iter; + /* Max size from any of the above. */ struct { unsigned long raw1; @@ -141,6 +161,8 @@ struct bpf_reg_state { * same reference to the socket, to determine proper reference freeing. * For stack slots that are dynptrs, this is used to track references to * the dynptr to determine proper reference freeing. + * Similarly to dynptrs, we use ID to track "belonging" of a reference + * to a specific instance of bpf_iter. */ u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned @@ -211,9 +233,11 @@ enum bpf_stack_slot_type { * is stored in bpf_stack_state->spilled_ptr.dynptr.type */ STACK_DYNPTR, + STACK_ITER, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ + #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) @@ -448,12 +472,17 @@ struct bpf_insn_aux_data { bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ + bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ u8 alu_state; /* used in combination with alu_limit */ /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ - bool prune_point; bool jmp_point; + bool prune_point; + /* ensure we check state equivalence and save state checkpoint and + * this instruction, regardless of any heuristics + */ + bool force_checkpoint; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -462,39 +491,36 @@ struct bpf_insn_aux_data { #define BPF_VERIFIER_TMP_LOG_SIZE 1024 struct bpf_verifier_log { - u32 level; - char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; + /* Logical start and end positions of a "log window" of the verifier log. + * start_pos == 0 means we haven't truncated anything. + * Once truncation starts to happen, start_pos + len_total == end_pos, + * except during log reset situations, in which (end_pos - start_pos) + * might get smaller than len_total (see bpf_vlog_reset()). + * Generally, (end_pos - start_pos) gives number of useful data in + * user log buffer. + */ + u64 start_pos; + u64 end_pos; char __user *ubuf; - u32 len_used; + u32 level; u32 len_total; + u32 len_max; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; }; -static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) -{ - return log->len_used >= log->len_total - 1; -} - #define BPF_LOG_LEVEL1 1 #define BPF_LOG_LEVEL2 2 #define BPF_LOG_STATS 4 +#define BPF_LOG_FIXED 8 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) -#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS | BPF_LOG_FIXED) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log && - ((log->level && log->ubuf && !bpf_verifier_log_full(log)) || - log->level == BPF_LOG_KERNEL); -} - -static inline bool -bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) -{ - return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && - log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); + return log && log->level; } #define BPF_MAX_SUBPROGS 256 @@ -574,7 +600,7 @@ struct bpf_verifier_env { u32 scratched_regs; /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; - u32 prev_log_len, prev_insn_print_len; + u64 prev_log_pos, prev_insn_print_pos; /* buffer used in reg_type_str() to generate reg_type string */ char type_str_buf[TYPE_STR_BUF_LEN]; }; @@ -585,6 +611,10 @@ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); +int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, + char __user *log_buf, u32 log_size); +void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); +int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { diff --git a/include/linux/btf.h b/include/linux/btf.h index 556b3e2e7471..495250162422 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -71,6 +71,10 @@ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ #define KF_RCU (1 << 7) /* kfunc takes either rcu or trusted pointer arguments */ +/* only one of KF_ITER_{NEW,NEXT,DESTROY} could be specified per kfunc */ +#define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ +#define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ +#define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the @@ -117,13 +121,11 @@ struct btf_struct_metas { struct btf_struct_meta types[]; }; -typedef void (*btf_dtor_kfunc_t)(void *); - extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, diff --git a/include/linux/filter.h b/include/linux/filter.h index efa5d4a1677e..5364b0c52c1d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -571,8 +571,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, @@ -1504,9 +1503,9 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, - u64 flags, const u64 flag_mask, - void *lookup_elem(struct bpf_map *map, u32 key)) +static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, + u64 flags, const u64 flag_mask, + void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; diff --git a/include/linux/module.h b/include/linux/module.h index 4435ad9439ab..886d24877c7c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -608,14 +608,6 @@ static inline bool within_module(unsigned long addr, const struct module *mod) /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); -/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if - symnum out of range. */ -int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, - char *name, char *module_name, int *exported); - -/* Look for this name: can be of form module:name. */ -unsigned long module_kallsyms_lookup_name(const char *name); - extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) @@ -662,17 +654,6 @@ static inline void __module_get(struct module *module) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); -/* For kallsyms to ask for address resolution. namebuf should be at - * least KSYM_NAME_LEN long: a pointer to namebuf is returned if - * found, otherwise NULL. */ -const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, const unsigned char **modbuildid, - char *namebuf); -int lookup_module_symbol_name(unsigned long addr, char *symname); -int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); - int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); @@ -763,39 +744,6 @@ static inline void module_put(struct module *module) #define module_name(mod) "kernel" -/* For kallsyms to ask for address resolution. NULL means not found. */ -static inline const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, - const unsigned char **modbuildid, - char *namebuf) -{ - return NULL; -} - -static inline int lookup_module_symbol_name(unsigned long addr, char *symname) -{ - return -ERANGE; -} - -static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) -{ - return -ERANGE; -} - -static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, - char *type, char *name, - char *module_name, int *exported) -{ - return -ERANGE; -} - -static inline unsigned long module_kallsyms_lookup_name(const char *name) -{ - return 0; -} - static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ @@ -891,7 +839,36 @@ int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -#else + +/* For kallsyms to ask for address resolution. namebuf should be at + * least KSYM_NAME_LEN long: a pointer to namebuf is returned if + * found, otherwise NULL. + */ +const char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, const unsigned char **modbuildid, + char *namebuf); +int lookup_module_symbol_name(unsigned long addr, char *symname); +int lookup_module_symbol_attrs(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char *modname, + char *name); + +/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if + * symnum out of range. + */ +int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *name, char *module_name, int *exported); + +/* Look for this name: can be of form module:name. */ +unsigned long module_kallsyms_lookup_name(const char *name); + +unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); + +#else /* CONFIG_MODULES && CONFIG_KALLSYMS */ + static inline int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, struct module *, unsigned long), @@ -899,6 +876,50 @@ static inline int module_kallsyms_on_each_symbol(const char *modname, { return -EOPNOTSUPP; } + +/* For kallsyms to ask for address resolution. NULL means not found. */ +static inline const char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, + const unsigned char **modbuildid, + char *namebuf) +{ + return NULL; +} + +static inline int lookup_module_symbol_name(unsigned long addr, char *symname) +{ + return -ERANGE; +} + +static inline int lookup_module_symbol_attrs(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char *modname, + char *name) +{ + return -ERANGE; +} + +static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *name, + char *module_name, int *exported) +{ + return -ERANGE; +} + +static inline unsigned long module_kallsyms_lookup_name(const char *name) +{ + return 0; +} + +static inline unsigned long find_kallsyms_symbol_value(struct module *mod, + const char *name) +{ + return 0; +} + #endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..b11b4517760f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1318,11 +1318,6 @@ struct task_struct { struct tlbflush_unmap_batch tlb_ubc; - union { - refcount_t rcu_users; - struct rcu_head rcu; - }; - /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; @@ -1459,6 +1454,8 @@ struct task_struct { unsigned long saved_state_change; # endif #endif + struct rcu_head rcu; + refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 82511b2f61ea..494a23a976b0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -938,6 +938,19 @@ struct sk_buff { __u8 ip_summed:2; __u8 ooo_okay:1; + /* private: */ + __u8 __mono_tc_offset[0]; + /* public: */ + __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ + __u8 tc_skip_classify:1; +#endif + __u8 remcsum_offload:1; + __u8 csum_complete_sw:1; + __u8 csum_level:2; + __u8 dst_pending_confirm:1; + __u8 l4_hash:1; __u8 sw_hash:1; __u8 wifi_acked_valid:1; @@ -947,19 +960,6 @@ struct sk_buff { __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; - - /* private: */ - __u8 __pkt_vlan_present_offset[0]; - /* public: */ - __u8 remcsum_offload:1; - __u8 csum_complete_sw:1; - __u8 csum_level:2; - __u8 dst_pending_confirm:1; - __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ -#ifdef CONFIG_NET_CLS_ACT - __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ -#endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif @@ -1066,13 +1066,13 @@ struct sk_buff { * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define TC_AT_INGRESS_MASK (1 << 0) -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) +#define TC_AT_INGRESS_MASK (1 << 6) #else -#define TC_AT_INGRESS_MASK (1 << 7) -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) +#define TC_AT_INGRESS_MASK (1 << 1) #endif -#define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) +#define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* @@ -5063,12 +5063,12 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } -#ifdef CONFIG_PAGE_POOL static inline void skb_mark_for_recycle(struct sk_buff *skb) { +#ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; -} #endif +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/net/fou.h b/include/net/fou.h index 80f56e275b08..824eb4b231fd 100644 --- a/include/net/fou.h +++ b/include/net/fou.h @@ -17,4 +17,6 @@ int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type); +int register_fou_bpf(void); + #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 255b32a90850..ed4b6ad3fcac 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -57,6 +57,13 @@ struct ip_tunnel_key { __u8 flow_flags; }; +struct ip_tunnel_encap { + u16 type; + u16 flags; + __be16 sport; + __be16 dport; +}; + /* Flags for ip_tunnel_info mode. */ #define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ #define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ @@ -75,6 +82,7 @@ struct ip_tunnel_key { struct ip_tunnel_info { struct ip_tunnel_key key; + struct ip_tunnel_encap encap; #ifdef CONFIG_DST_CACHE struct dst_cache dst_cache; #endif @@ -92,13 +100,6 @@ struct ip_tunnel_6rd_parm { }; #endif -struct ip_tunnel_encap { - u16 type; - u16 flags; - __be16 sport; - __be16 dport; -}; - struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry __rcu *next; __be32 addr; @@ -299,6 +300,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, __be32 remote, __be32 local, __be32 key); +void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); @@ -377,22 +379,23 @@ static inline int ip_encap_hlen(struct ip_tunnel_encap *e) return hlen; } -static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, +static inline int ip_tunnel_encap(struct sk_buff *skb, + struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { const struct ip_tunnel_encap_ops *ops; int ret = -EINVAL; - if (t->encap.type == TUNNEL_ENCAP_NONE) + if (e->type == TUNNEL_ENCAP_NONE) return 0; - if (t->encap.type >= MAX_IPTUN_ENCAP_OPS) + if (e->type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); - ops = rcu_dereference(iptun_encaps[t->encap.type]); + ops = rcu_dereference(iptun_encaps[e->type]); if (likely(ops && ops->build_header)) - ret = ops->build_header(skb, &t->encap, protocol, fl4); + ret = ops->build_header(skb, e, protocol, fl4); rcu_read_unlock(); return ret; diff --git a/include/net/tcp.h b/include/net/tcp.h index a0a91a988272..04a31643cda3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1117,6 +1117,9 @@ struct tcp_congestion_ops { int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); +int tcp_update_congestion_control(struct tcp_congestion_ops *type, + struct tcp_congestion_ops *old_type); +int tcp_validate_congestion_control(struct tcp_congestion_ops *ca); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); diff --git a/include/net/xdp.h b/include/net/xdp.h index 76aa748e7923..d1c5381fc95f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -318,35 +318,6 @@ void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); -/* When sending xdp_frame into the network stack, then there is no - * return point callback, which is needed to release e.g. DMA-mapping - * resources with page_pool. Thus, have explicit function to release - * frame resources. - */ -void __xdp_release_frame(void *data, struct xdp_mem_info *mem); -static inline void xdp_release_frame(struct xdp_frame *xdpf) -{ - struct xdp_mem_info *mem = &xdpf->mem; - struct skb_shared_info *sinfo; - int i; - - /* Curr only page_pool needs this */ - if (mem->type != MEM_TYPE_PAGE_POOL) - return; - - if (likely(!xdp_frame_has_frags(xdpf))) - goto out; - - sinfo = xdp_get_shared_info_from_frame(xdpf); - for (i = 0; i < sinfo->nr_frags; i++) { - struct page *page = skb_frag_page(&sinfo->frags[i]); - - __xdp_release_frame(page_address(page), mem); - } -out: - __xdp_release_frame(xdpf->data, mem); -} - static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 3e952e569418..d318c769b445 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -180,13 +180,8 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, if (likely(!cross_pg)) return false; - if (pool->dma_pages_cnt) { - return !(pool->dma_pages[addr >> PAGE_SHIFT] & - XSK_NEXT_PG_CONTIG_MASK); - } - - /* skb path */ - return addr + len > pool->addrs_cnt; + return pool->dma_pages_cnt && + !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 976b194eb775..3823100b7934 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1033,6 +1033,7 @@ enum bpf_attach_type { BPF_PERF_EVENT, BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, + BPF_STRUCT_OPS, __MAX_BPF_ATTACH_TYPE }; @@ -1108,7 +1109,7 @@ enum bpf_link_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) -/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will allow any alignment whatsoever. On platforms * with strict alignment requirements for loads ands stores (such * as sparc and mips) the verifier validates that all loads and @@ -1266,6 +1267,9 @@ enum { /* Create a map that is suitable to be an inner map with dynamic max entries */ BPF_F_INNER_MAP = (1U << 12), + +/* Create a map that will be registered/unregesitered by the backed bpf_link */ + BPF_F_LINK = (1U << 13), }; /* Flags for BPF_PROG_QUERY. */ @@ -1403,6 +1407,11 @@ union bpf_attr { __aligned_u64 fd_array; /* array of FDs */ __aligned_u64 core_relos; __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 log_true_size; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1488,6 +1497,11 @@ union bpf_attr { __u32 btf_size; __u32 btf_log_size; __u32 btf_log_level; + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 btf_log_true_size; }; struct { @@ -1507,7 +1521,10 @@ union bpf_attr { } task_fd_query; struct { /* struct used by BPF_LINK_CREATE command */ - __u32 prog_fd; /* eBPF program to attach */ + union { + __u32 prog_fd; /* eBPF program to attach */ + __u32 map_fd; /* struct_ops to attach */ + }; union { __u32 target_fd; /* object to attach to */ __u32 target_ifindex; /* target ifindex */ @@ -1548,12 +1565,23 @@ union bpf_attr { struct { /* struct used by BPF_LINK_UPDATE command */ __u32 link_fd; /* link fd */ - /* new program fd to update link with */ - __u32 new_prog_fd; + union { + /* new program fd to update link with */ + __u32 new_prog_fd; + /* new struct_ops map fd to update link with */ + __u32 new_map_fd; + }; __u32 flags; /* extra flags */ - /* expected link's program fd; is specified only if - * BPF_F_REPLACE flag is set in flags */ - __u32 old_prog_fd; + union { + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags. + */ + __u32 old_prog_fd; + /* expected link's map fd; is specified only + * if BPF_F_REPLACE flag is set. + */ + __u32 old_map_fd; + }; } link_update; struct { @@ -1647,17 +1675,17 @@ union bpf_attr { * Description * This helper is a "printk()-like" facility for debugging. It * prints a message defined by format *fmt* (of size *fmt_size*) - * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * to file *\/sys/kernel/tracing/trace* from TraceFS, if * available. It can take up to three additional **u64** * arguments (as an eBPF helpers, the total number of arguments is * limited to five). * * Each time the helper is called, it appends a line to the trace. - * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is - * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. + * Lines are discarded while *\/sys/kernel/tracing/trace* is + * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this. * The format of the trace is customizable, and the exact output * one will get depends on the options set in - * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *\/sys/kernel/tracing/trace_options* (see also the * *README* file under the same directory). However, it usually * defaults to something like: * @@ -6379,6 +6407,9 @@ struct bpf_link_info { struct { __u32 ifindex; } xdp; + struct { + __u32 map_id; + } struct_ops; }; } __attribute__((aligned(8))); @@ -7112,4 +7143,12 @@ enum { BPF_F_TIMER_ABS = (1ULL << 0), }; +/* BPF numbers iterator state */ +struct bpf_iter_num { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + #endif /* _UAPI__LINUX_BPF_H__ */ |
