mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Kumar Kartikeya Dwivedi](/assets/img/avatar_default.png)
This patch prepares the kernel to support putting all kinds of kfunc BTF ID sets in the struct btf itself. The various kernel subsystems will make register_btf_kfunc_id_set call in the initcalls (for built-in code and modules). The 'hook' is one of the many program types, e.g. XDP and TC/SCHED_CLS, STRUCT_OPS, and 'types' are check (allowed or not), acquire, release, and ret_null (with PTR_TO_BTF_ID_OR_NULL return type). A maximum of BTF_KFUNC_SET_MAX_CNT (32) kfunc BTF IDs are permitted in a set of certain hook and type for vmlinux sets, since they are allocated on demand, and otherwise set as NULL. Module sets can only be registered once per hook and type, hence they are directly assigned. A new btf_kfunc_id_set_contains function is exposed for use in verifier, this new method is faster than the existing list searching method, and is also automatic. It also lets other code not care whether the set is unallocated or not. Note that module code can only do single register_btf_kfunc_id_set call per hook. This is why sorting is only done for in-kernel vmlinux sets, because there might be multiple sets for the same hook and type that must be concatenated, hence sorting them is required to ensure bsearch in btf_id_set_contains continues to work correctly. Next commit will update the kernel users to make use of this infrastructure. Finally, add __maybe_unused annotation for BTF ID macros for the !CONFIG_DEBUG_INFO_BTF case, so that they don't produce warnings during build time. The previous patch is also needed to provide synchronization against initialization for module BTF's kfunc_set_tab introduced here, as described below: The kfunc_set_tab pointer in struct btf is write-once (if we consider the registration phase (comprised of multiple register_btf_kfunc_id_set calls) as a single operation). In this sense, once it has been fully prepared, it isn't modified, only used for lookup (from the verifier context). For btf_vmlinux, it is initialized fully during the do_initcalls phase, which happens fairly early in the boot process, before any processes are present. This also eliminates the possibility of bpf_check being called at that point, thus relieving us of ensuring any synchronization between the registration and lookup function (btf_kfunc_id_set_contains). However, the case for module BTF is a bit tricky. The BTF is parsed, prepared, and published from the MODULE_STATE_COMING notifier callback. After this, the module initcalls are invoked, where our registration function will be called to populate the kfunc_set_tab for module BTF. At this point, BTF may be available to userspace while its corresponding module is still intializing. A BTF fd can then be passed to verifier using bpf syscall (e.g. for kfunc call insn). Hence, there is a race window where verifier may concurrently try to lookup the kfunc_set_tab. To prevent this race, we must ensure the operations are serialized, or waiting for the __init functions to complete. In the earlier registration API, this race was alleviated as verifier bpf_check_mod_kfunc_call didn't find the kfunc BTF ID until it was added by the registration function (called usually at the end of module __init function after all module resources have been initialized). If the verifier made the check_kfunc_call before kfunc BTF ID was added to the list, it would fail verification (saying call isn't allowed). The access to list was protected using a mutex. Now, it would still fail verification, but for a different reason (returning ENXIO due to the failed btf_try_get_module call in add_kfunc_call), because if the __init call is in progress the module will be in the middle of MODULE_STATE_COMING -> MODULE_STATE_LIVE transition, and the BTF_MODULE_LIVE flag for btf_module instance will not be set, so the btf_try_get_module call will fail. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20220114163953.1455836-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
207 lines
5.8 KiB
C
207 lines
5.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#ifndef _LINUX_BTF_IDS_H
|
|
#define _LINUX_BTF_IDS_H
|
|
|
|
struct btf_id_set {
|
|
u32 cnt;
|
|
u32 ids[];
|
|
};
|
|
|
|
#ifdef CONFIG_DEBUG_INFO_BTF
|
|
|
|
#include <linux/compiler.h> /* for __PASTE */
|
|
#include <linux/compiler_attributes.h> /* for __maybe_unused */
|
|
|
|
/*
|
|
* Following macros help to define lists of BTF IDs placed
|
|
* in .BTF_ids section. They are initially filled with zeros
|
|
* (during compilation) and resolved later during the
|
|
* linking phase by resolve_btfids tool.
|
|
*
|
|
* Any change in list layout must be reflected in resolve_btfids
|
|
* tool logic.
|
|
*/
|
|
|
|
#define BTF_IDS_SECTION ".BTF_ids"
|
|
|
|
#define ____BTF_ID(symbol) \
|
|
asm( \
|
|
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
|
|
".local " #symbol " ; \n" \
|
|
".type " #symbol ", STT_OBJECT; \n" \
|
|
".size " #symbol ", 4; \n" \
|
|
#symbol ": \n" \
|
|
".zero 4 \n" \
|
|
".popsection; \n");
|
|
|
|
#define __BTF_ID(symbol) \
|
|
____BTF_ID(symbol)
|
|
|
|
#define __ID(prefix) \
|
|
__PASTE(prefix, __COUNTER__)
|
|
|
|
/*
|
|
* The BTF_ID defines unique symbol for each ID pointing
|
|
* to 4 zero bytes.
|
|
*/
|
|
#define BTF_ID(prefix, name) \
|
|
__BTF_ID(__ID(__BTF_ID__##prefix##__##name##__))
|
|
|
|
/*
|
|
* The BTF_ID_LIST macro defines pure (unsorted) list
|
|
* of BTF IDs, with following layout:
|
|
*
|
|
* BTF_ID_LIST(list1)
|
|
* BTF_ID(type1, name1)
|
|
* BTF_ID(type2, name2)
|
|
*
|
|
* list1:
|
|
* __BTF_ID__type1__name1__1:
|
|
* .zero 4
|
|
* __BTF_ID__type2__name2__2:
|
|
* .zero 4
|
|
*
|
|
*/
|
|
#define __BTF_ID_LIST(name, scope) \
|
|
asm( \
|
|
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
|
|
"." #scope " " #name "; \n" \
|
|
#name ":; \n" \
|
|
".popsection; \n");
|
|
|
|
#define BTF_ID_LIST(name) \
|
|
__BTF_ID_LIST(name, local) \
|
|
extern u32 name[];
|
|
|
|
#define BTF_ID_LIST_GLOBAL(name, n) \
|
|
__BTF_ID_LIST(name, globl)
|
|
|
|
/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
|
|
* a single entry.
|
|
*/
|
|
#define BTF_ID_LIST_SINGLE(name, prefix, typename) \
|
|
BTF_ID_LIST(name) \
|
|
BTF_ID(prefix, typename)
|
|
#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \
|
|
BTF_ID_LIST_GLOBAL(name, 1) \
|
|
BTF_ID(prefix, typename)
|
|
|
|
/*
|
|
* The BTF_ID_UNUSED macro defines 4 zero bytes.
|
|
* It's used when we want to define 'unused' entry
|
|
* in BTF_ID_LIST, like:
|
|
*
|
|
* BTF_ID_LIST(bpf_skb_output_btf_ids)
|
|
* BTF_ID(struct, sk_buff)
|
|
* BTF_ID_UNUSED
|
|
* BTF_ID(struct, task_struct)
|
|
*/
|
|
|
|
#define BTF_ID_UNUSED \
|
|
asm( \
|
|
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
|
|
".zero 4 \n" \
|
|
".popsection; \n");
|
|
|
|
/*
|
|
* The BTF_SET_START/END macros pair defines sorted list of
|
|
* BTF IDs plus its members count, with following layout:
|
|
*
|
|
* BTF_SET_START(list)
|
|
* BTF_ID(type1, name1)
|
|
* BTF_ID(type2, name2)
|
|
* BTF_SET_END(list)
|
|
*
|
|
* __BTF_ID__set__list:
|
|
* .zero 4
|
|
* list:
|
|
* __BTF_ID__type1__name1__3:
|
|
* .zero 4
|
|
* __BTF_ID__type2__name2__4:
|
|
* .zero 4
|
|
*
|
|
*/
|
|
#define __BTF_SET_START(name, scope) \
|
|
asm( \
|
|
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
|
|
"." #scope " __BTF_ID__set__" #name "; \n" \
|
|
"__BTF_ID__set__" #name ":; \n" \
|
|
".zero 4 \n" \
|
|
".popsection; \n");
|
|
|
|
#define BTF_SET_START(name) \
|
|
__BTF_ID_LIST(name, local) \
|
|
__BTF_SET_START(name, local)
|
|
|
|
#define BTF_SET_START_GLOBAL(name) \
|
|
__BTF_ID_LIST(name, globl) \
|
|
__BTF_SET_START(name, globl)
|
|
|
|
#define BTF_SET_END(name) \
|
|
asm( \
|
|
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
|
|
".size __BTF_ID__set__" #name ", .-" #name " \n" \
|
|
".popsection; \n"); \
|
|
extern struct btf_id_set name;
|
|
|
|
#else
|
|
|
|
#define BTF_ID_LIST(name) static u32 __maybe_unused name[5];
|
|
#define BTF_ID(prefix, name)
|
|
#define BTF_ID_UNUSED
|
|
#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n];
|
|
#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1];
|
|
#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1];
|
|
#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 };
|
|
#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 };
|
|
#define BTF_SET_END(name)
|
|
|
|
#endif /* CONFIG_DEBUG_INFO_BTF */
|
|
|
|
#ifdef CONFIG_NET
|
|
/* Define a list of socket types which can be the argument for
|
|
* skc_to_*_sock() helpers. All these sockets should have
|
|
* sock_common as the first argument in its memory layout.
|
|
*/
|
|
#define BTF_SOCK_TYPE_xxx \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \
|
|
BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)
|
|
|
|
enum {
|
|
#define BTF_SOCK_TYPE(name, str) name,
|
|
BTF_SOCK_TYPE_xxx
|
|
#undef BTF_SOCK_TYPE
|
|
MAX_BTF_SOCK_TYPE,
|
|
};
|
|
|
|
extern u32 btf_sock_ids[];
|
|
#endif
|
|
|
|
#define BTF_TRACING_TYPE_xxx \
|
|
BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct) \
|
|
BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file) \
|
|
BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct)
|
|
|
|
enum {
|
|
#define BTF_TRACING_TYPE(name, type) name,
|
|
BTF_TRACING_TYPE_xxx
|
|
#undef BTF_TRACING_TYPE
|
|
MAX_BTF_TRACING_TYPE,
|
|
};
|
|
|
|
extern u32 btf_tracing_ids[];
|
|
|
|
#endif
|