From: Kui-Feng Lee <thinker.li@gmail.com> mainline inclusion from mainline-v6.9-rc1 commit f6be98d19985411ca1f3d53413d94d5b7f41c200 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IDC9YK Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commi... -------------------------------- Replace the static list of struct_ops types with per-btf struct_ops_tab to enable dynamic registration. Both bpf_dummy_ops and bpf_tcp_ca now utilize the registration function instead of being listed in bpf_struct_ops_types.h. Cc: netdev@vger.kernel.org Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com> Link: https://lore.kernel.org/r/20240119225005.668602-12-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org> Conflicts: net/bpf/bpf_dummy_struct_ops.c net/ipv4/bpf_tcp_ca.c [The struct lacks of the atti cfi_stubs, but the mainline version has it, so keep this atti and relevant functions.] Signed-off-by: Zicheng Qu <quzicheng@huawei.com> --- include/linux/bpf.h | 27 +++++--- include/linux/btf.h | 12 ++++ kernel/bpf/bpf_struct_ops.c | 100 ++++-------------------------- kernel/bpf/bpf_struct_ops_types.h | 12 ---- kernel/bpf/btf.c | 86 +++++++++++++++++++++++-- net/bpf/bpf_dummy_struct_ops.c | 34 +++++++++- net/ipv4/bpf_tcp_ca.c | 81 +++++++++++++++++++++++- 7 files changed, 234 insertions(+), 118 deletions(-) delete mode 100644 kernel/bpf/bpf_struct_ops_types.h diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 460a40e9caba..07cdb48e3823 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1796,9 +1796,20 @@ struct bpf_struct_ops_common_value { }; #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 + * a struct_ops type instead of calling __register_bpf_struct_ops() directly. + */ +#define register_bpf_struct_ops(st_ops, type) \ + ({ \ + struct bpf_struct_ops_##type { \ + struct bpf_struct_ops_common_value common; \ + struct type data ____cacheline_aligned_in_smp; \ + }; \ + BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ + __register_bpf_struct_ops(st_ops); \ + }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -1839,16 +1850,12 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else -static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) -{ - return NULL; -} -static inline void bpf_struct_ops_init(struct btf *btf, - struct bpf_verifier_log *log) -{ -} +#define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); diff --git a/include/linux/btf.h b/include/linux/btf.h index 8fae9a27c8d9..7b46ed1e245d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -485,6 +485,18 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) struct bpf_verifier_log; +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +struct bpf_struct_ops; +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops); +const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); +#else +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 9ae7dfc00fef..af4bf9ecb94b 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -62,35 +62,6 @@ static DEFINE_MUTEX(update_mutex); #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - struct bpf_struct_ops_common_value common; \ - struct _name data ____cacheline_aligned_in_smp; \ -}; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; - -static struct bpf_struct_ops_desc bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = { .st_ops = &bpf_##_name }, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; - const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -145,9 +116,9 @@ static bool is_valid_value_type(struct btf *btf, s32 value_id, return true; } -static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, - struct btf *btf, - struct bpf_verifier_log *log) +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; const struct btf_member *member; @@ -161,7 +132,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, sizeof(value_name)) { pr_warn("struct_ops name %s is too long\n", st_ops->name); - return; + return -EINVAL; } sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); @@ -170,13 +141,13 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (type_id < 0) { pr_warn("Cannot find struct %s in %s\n", st_ops->name, btf_get_name(btf)); - return; + return -EINVAL; } t = btf_type_by_id(btf, type_id); if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { pr_warn("Cannot support #%u members in struct %s\n", btf_type_vlen(t), st_ops->name); - return; + return -EINVAL; } value_id = btf_find_by_name_kind(btf, value_name, @@ -184,10 +155,10 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (value_id < 0) { pr_warn("Cannot find struct %s in %s\n", value_name, btf_get_name(btf)); - return; + return -EINVAL; } if (!is_valid_value_type(btf, value_id, t, value_name)) - return; + return -EINVAL; for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -196,13 +167,13 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!*mname) { pr_warn("anon member in struct %s is not supported\n", st_ops->name); - break; + return -EOPNOTSUPP; } if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); - break; + return -EOPNOTSUPP; } func_proto = btf_type_resolve_func_ptr(btf, @@ -214,7 +185,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, &st_ops->func_models[i])) { pr_warn("Error in parsing func ptr %s in struct %s\n", mname, st_ops->name); - break; + return -EINVAL; } } @@ -222,6 +193,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (st_ops->init(btf)) { pr_warn("Error in init bpf_struct_ops %s\n", st_ops->name); + return -EINVAL; } else { st_ops_desc->type_id = type_id; st_ops_desc->type = t; @@ -230,54 +202,8 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, value_id); } } -} -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) -{ - struct bpf_struct_ops_desc *st_ops_desc; - u32 i; - - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops_desc = &bpf_struct_ops[i]; - bpf_struct_ops_desc_init(st_ops_desc, btf, log); - } -} - -static const struct bpf_struct_ops_desc * -bpf_struct_ops_find_value(struct btf *btf, u32 value_id) -{ - unsigned int i; - - if (!value_id || !btf) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i].value_id == value_id) - return &bpf_struct_ops[i]; - } - - return NULL; -} - -const struct bpf_struct_ops_desc * -bpf_struct_ops_find(struct btf *btf, u32 type_id) -{ - unsigned int i; - - if (!type_id || !btf) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i].type_id == type_id) - return &bpf_struct_ops[i]; - } - - return NULL; + return 0; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf817..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include <net/tcp.h> -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b7db8a52ce58..affdc13d382c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/btf_ids.h> +#include <linux/bpf.h> #include <linux/bpf_lsm.h> #include <linux/skmsg.h> #include <linux/perf_event.h> @@ -5792,8 +5793,6 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); @@ -8887,11 +8886,13 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } +#ifdef CONFIG_BPF_JIT static int -btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) { struct btf_struct_ops_tab *tab, *new_tab; - int i; + int i, err; tab = btf->struct_ops_tab; if (!tab) { @@ -8921,7 +8922,84 @@ btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + btf->struct_ops_tab->cnt++; return 0; } + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return -EINVAL; + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 75c5a0b900d4..d6840fc8e555 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -7,7 +7,7 @@ #include <linux/bpf.h> #include <linux/btf.h> -extern struct bpf_struct_ops bpf_bpf_dummy_ops; +static struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); @@ -229,7 +229,29 @@ static void bpf_dummy_unreg(void *kdata) { } -struct bpf_struct_ops bpf_bpf_dummy_ops = { +static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb) +{ + return 0; +} + +static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, + char a3, unsigned long a4) +{ + return 0; +} + +static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb) +{ + return 0; +} + +static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { + .test_1 = bpf_dummy_test_1, + .test_2 = bpf_dummy_test_2, + .test_sleepable = bpf_dummy_test_sleepable, +}; + +static struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, .check_member = bpf_dummy_ops_check_member, @@ -237,4 +259,12 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .reg = bpf_dummy_reg, .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", + .cfi_stubs = &__bpf_bpf_dummy_ops, + .owner = THIS_MODULE, }; + +static int __init bpf_dummy_struct_ops_init(void) +{ + return register_bpf_struct_ops(&bpf_bpf_dummy_ops, bpf_dummy_ops); +} +late_initcall(bpf_dummy_struct_ops_init); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 4c20390b6ff8..5d83d7b058fa 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include <net/bpf_sk_storage.h> /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -277,7 +277,75 @@ static int bpf_tcp_ca_validate(void *kdata) return tcp_validate_congestion_control(kdata); } -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static u32 bpf_tcp_ca_ssthresh(struct sock *sk) +{ + return 0; +} + +static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked) +{ +} + +static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state) +{ +} + +static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev) +{ +} + +static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags) +{ +} + +static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample) +{ +} + +static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk) +{ + return 0; +} + +static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs) +{ +} + +static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk) +{ + return 0; +} + +static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk) +{ + return 0; +} + +static void __bpf_tcp_ca_init(struct sock *sk) +{ +} + +static void __bpf_tcp_ca_release(struct sock *sk) +{ +} + +static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { + .ssthresh = bpf_tcp_ca_ssthresh, + .cong_avoid = bpf_tcp_ca_cong_avoid, + .set_state = bpf_tcp_ca_set_state, + .cwnd_event = bpf_tcp_ca_cwnd_event, + .in_ack_event = bpf_tcp_ca_in_ack_event, + .pkts_acked = bpf_tcp_ca_pkts_acked, + .min_tso_segs = bpf_tcp_ca_min_tso_segs, + .cong_control = bpf_tcp_ca_cong_control, + .undo_cwnd = bpf_tcp_ca_undo_cwnd, + .sndbuf_expand = bpf_tcp_ca_sndbuf_expand, + + .init = __bpf_tcp_ca_init, + .release = __bpf_tcp_ca_release, +}; + +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -287,10 +355,17 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .init = bpf_tcp_ca_init, .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", + .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); -- 2.34.1