mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2026-04-03 12:05:13 +02:00
1f8b8f0db0
[ Upstream commit710f5c7658] We have an increasing number of READ_ONCE(xxx->function) combined with INDIRECT_CALL_[1234]() helpers. Unfortunately this forces INDIRECT_CALL_[1234]() to read xxx->function many times, which is not what we wanted. Fix these macros so that xxx->function value is not reloaded. $ scripts/bloat-o-meter -t vmlinux.0 vmlinux add/remove: 0/0 grow/shrink: 1/65 up/down: 122/-1084 (-962) Function old new delta ip_push_pending_frames 59 181 +122 ip6_finish_output 687 681 -6 __udp_enqueue_schedule_skb 1078 1072 -6 ioam6_output 2319 2312 -7 xfrm4_rcv_encap_finish2 64 56 -8 xfrm4_output 297 289 -8 vrf_ip_local_out 278 270 -8 vrf_ip6_local_out 278 270 -8 seg6_input_finish 64 56 -8 rpl_output 700 692 -8 ipmr_forward_finish 124 116 -8 ip_forward_finish 143 135 -8 ip6mr_forward2_finish 100 92 -8 ip6_forward_finish 73 65 -8 input_action_end_bpf 1091 1083 -8 dst_input 52 44 -8 __xfrm6_output 801 793 -8 __xfrm4_output 83 75 -8 bpf_input 500 491 -9 __tcp_check_space 530 521 -9 input_action_end_dt6 291 280 -11 vti6_tnl_xmit 1634 1622 -12 bpf_xmit 1203 1191 -12 rpl_input 497 483 -14 rawv6_send_hdrinc 1355 1341 -14 ndisc_send_skb 1030 1016 -14 ipv6_srh_rcv 1377 1363 -14 ip_send_unicast_reply 1253 1239 -14 ip_rcv_finish 226 212 -14 ip6_rcv_finish 300 286 -14 input_action_end_x_core 205 191 -14 input_action_end_x 355 341 -14 input_action_end_t 205 191 -14 input_action_end_dx6_finish 127 113 -14 input_action_end_dx4_finish 373 359 -14 input_action_end_dt4 426 412 -14 input_action_end_core 186 172 -14 input_action_end_b6_encap 292 278 -14 input_action_end_b6 198 184 -14 igmp6_send 1332 1318 -14 ip_sublist_rcv 864 848 -16 ip6_sublist_rcv 1091 1075 -16 ipv6_rpl_srh_rcv 1937 1920 -17 xfrm_policy_queue_process 1246 1228 -18 seg6_output_core 903 885 -18 mld_sendpack 856 836 -20 NF_HOOK 756 736 -20 vti_tunnel_xmit 1447 1426 -21 input_action_end_dx6 664 642 -22 input_action_end 1502 1480 -22 sock_sendmsg_nosec 134 111 -23 ip6mr_forward2 388 364 -24 sock_recvmsg_nosec 134 109 -25 seg6_input_core 836 810 -26 ip_send_skb 172 146 -26 ip_local_out 140 114 -26 ip6_local_out 140 114 -26 __sock_sendmsg 162 136 -26 __ip_queue_xmit 1196 1170 -26 __ip_finish_output 405 379 -26 ipmr_queue_fwd_xmit 373 346 -27 sock_recvmsg 173 145 -28 ip6_xmit 1635 1607 -28 xfrm_output_resume 1418 1389 -29 ip_build_and_send_pkt 625 591 -34 dst_output 504 432 -72 Total: Before=25217686, After=25216724, chg -0.00% Fixes:283c16a2df("indirect call wrappers: helpers to speed-up indirect calls of builtin") Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20260227172603.1700433-1-edumazet@google.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
76 lines
2.4 KiB
C
76 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_INDIRECT_CALL_WRAPPER_H
|
|
#define _LINUX_INDIRECT_CALL_WRAPPER_H
|
|
|
|
#ifdef CONFIG_MITIGATION_RETPOLINE
|
|
|
|
/*
|
|
* INDIRECT_CALL_$NR - wrapper for indirect calls with $NR known builtin
|
|
* @f: function pointer
|
|
* @f$NR: builtin functions names, up to $NR of them
|
|
* @__VA_ARGS__: arguments for @f
|
|
*
|
|
* Avoid retpoline overhead for known builtin, checking @f vs each of them and
|
|
* eventually invoking directly the builtin function. The functions are checked
|
|
* in the given order. Fallback to the indirect call.
|
|
*/
|
|
#define INDIRECT_CALL_1(f, f1, ...) \
|
|
({ \
|
|
typeof(f) __f1 = (f); \
|
|
likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \
|
|
})
|
|
#define INDIRECT_CALL_2(f, f2, f1, ...) \
|
|
({ \
|
|
typeof(f) __f2 = (f); \
|
|
likely(__f2 == f2) ? f2(__VA_ARGS__) : \
|
|
INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \
|
|
})
|
|
#define INDIRECT_CALL_3(f, f3, f2, f1, ...) \
|
|
({ \
|
|
typeof(f) __f3 = (f); \
|
|
likely(__f3 == f3) ? f3(__VA_ARGS__) : \
|
|
INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \
|
|
})
|
|
#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \
|
|
({ \
|
|
typeof(f) __f4 = (f); \
|
|
likely(__f4 == f4) ? f4(__VA_ARGS__) : \
|
|
INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \
|
|
})
|
|
|
|
#define INDIRECT_CALLABLE_DECLARE(f) f
|
|
#define INDIRECT_CALLABLE_SCOPE
|
|
#define EXPORT_INDIRECT_CALLABLE(f) EXPORT_SYMBOL(f)
|
|
|
|
#else
|
|
#define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__)
|
|
#define INDIRECT_CALL_2(f, f2, f1, ...) f(__VA_ARGS__)
|
|
#define INDIRECT_CALL_3(f, f3, f2, f1, ...) f(__VA_ARGS__)
|
|
#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) f(__VA_ARGS__)
|
|
#define INDIRECT_CALLABLE_DECLARE(f)
|
|
#define INDIRECT_CALLABLE_SCOPE static
|
|
#define EXPORT_INDIRECT_CALLABLE(f)
|
|
#endif
|
|
|
|
/*
|
|
* We can use INDIRECT_CALL_$NR for ipv6 related functions only if ipv6 is
|
|
* builtin, this macro simplify dealing with indirect calls with only ipv4/ipv6
|
|
* alternatives
|
|
*/
|
|
#if IS_BUILTIN(CONFIG_IPV6)
|
|
#define INDIRECT_CALL_INET(f, f2, f1, ...) \
|
|
INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
|
|
#elif IS_ENABLED(CONFIG_INET)
|
|
#define INDIRECT_CALL_INET(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
|
|
#else
|
|
#define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__)
|
|
#endif
|
|
|
|
#if IS_ENABLED(CONFIG_INET)
|
|
#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
|
|
#else
|
|
#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__)
|
|
#endif
|
|
|
|
#endif
|