40272035e1
When the BPF routine doesn't call any function, the non volatile registers can be reallocated to volatile registers in order to avoid having to save them/restore on the stack. Before this patch, the test #359 ADD default X is: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 92 e1 00 2c stw r23,44(r1) 14: 93 01 00 30 stw r24,48(r1) 18: 93 21 00 34 stw r25,52(r1) 1c: 93 41 00 38 stw r26,56(r1) 20: 39 80 00 00 li r12,0 24: 39 60 00 00 li r11,0 28: 3b 40 00 00 li r26,0 2c: 3b 20 00 00 li r25,0 30: 7c 98 23 78 mr r24,r4 34: 7c 77 1b 78 mr r23,r3 38: 39 80 00 42 li r12,66 3c: 39 60 00 00 li r11,0 40: 7d 8c d2 14 add r12,r12,r26 44: 39 60 00 00 li r11,0 48: 7d 83 63 78 mr r3,r12 4c: 82 e1 00 2c lwz r23,44(r1) 50: 83 01 00 30 lwz r24,48(r1) 54: 83 21 00 34 lwz r25,52(r1) 58: 83 41 00 38 lwz r26,56(r1) 5c: 38 21 00 50 addi r1,r1,80 60: 4e 80 00 20 blr After this patch, the same test has become: 0: 7c 64 1b 78 mr r4,r3 4: 38 60 00 00 li r3,0 8: 94 21 ff b0 stwu r1,-80(r1) c: 60 00 00 00 nop 10: 39 80 00 00 li r12,0 14: 39 60 00 00 li r11,0 18: 39 00 00 00 li r8,0 1c: 38 e0 00 00 li r7,0 20: 7c 86 23 78 mr r6,r4 24: 7c 65 1b 78 mr r5,r3 28: 39 80 00 42 li r12,66 2c: 39 60 00 00 li r11,0 30: 7d 8c 42 14 add r12,r12,r8 34: 39 60 00 00 li r11,0 38: 7d 83 63 78 mr r3,r12 3c: 38 21 00 50 addi r1,r1,80 40: 4e 80 00 20 blr Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/b94562d7d2bb21aec89de0c40bb3cd91054b65a2.1616430991.git.christophe.leroy@csgroup.eu
92 lines
2.4 KiB
C
92 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* bpf_jit64.h: BPF JIT compiler for PPC64
|
|
*
|
|
* Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
|
|
* IBM Corporation
|
|
*/
|
|
#ifndef _BPF_JIT64_H
|
|
#define _BPF_JIT64_H
|
|
|
|
#include "bpf_jit.h"
|
|
|
|
/*
|
|
* Stack layout:
|
|
* Ensure the top half (upto local_tmp_var) stays consistent
|
|
* with our redzone usage.
|
|
*
|
|
* [ prev sp ] <-------------
|
|
* [ nv gpr save area ] 6*8 |
|
|
* [ tail_call_cnt ] 8 |
|
|
* [ local_tmp_var ] 8 |
|
|
* fp (r31) --> [ ebpf stack space ] upto 512 |
|
|
* [ frame header ] 32/112 |
|
|
* sp (r1) ---> [ stack pointer ] --------------
|
|
*/
|
|
|
|
/* for gpr non volatile registers BPG_REG_6 to 10 */
|
|
#define BPF_PPC_STACK_SAVE (6*8)
|
|
/* for bpf JIT code internal usage */
|
|
#define BPF_PPC_STACK_LOCALS 16
|
|
/* stack frame excluding BPF stack, ensure this is quadword aligned */
|
|
#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \
|
|
BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
/* BPF register usage */
|
|
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
|
|
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
|
|
|
|
/* BPF to ppc register mappings */
|
|
const int b2p[MAX_BPF_JIT_REG + 2] = {
|
|
/* function return value */
|
|
[BPF_REG_0] = 8,
|
|
/* function arguments */
|
|
[BPF_REG_1] = 3,
|
|
[BPF_REG_2] = 4,
|
|
[BPF_REG_3] = 5,
|
|
[BPF_REG_4] = 6,
|
|
[BPF_REG_5] = 7,
|
|
/* non volatile registers */
|
|
[BPF_REG_6] = 27,
|
|
[BPF_REG_7] = 28,
|
|
[BPF_REG_8] = 29,
|
|
[BPF_REG_9] = 30,
|
|
/* frame pointer aka BPF_REG_10 */
|
|
[BPF_REG_FP] = 31,
|
|
/* eBPF jit internal registers */
|
|
[BPF_REG_AX] = 2,
|
|
[TMP_REG_1] = 9,
|
|
[TMP_REG_2] = 10
|
|
};
|
|
|
|
/* PPC NVR range -- update this if we ever use NVRs below r27 */
|
|
#define BPF_PPC_NVR_MIN 27
|
|
|
|
/*
|
|
* WARNING: These can use TMP_REG_2 if the offset is not at word boundary,
|
|
* so ensure that it isn't in use already.
|
|
*/
|
|
#define PPC_BPF_LL(r, base, i) do { \
|
|
if ((i) % 4) { \
|
|
EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\
|
|
EMIT(PPC_RAW_LDX(r, base, \
|
|
b2p[TMP_REG_2])); \
|
|
} else \
|
|
EMIT(PPC_RAW_LD(r, base, i)); \
|
|
} while(0)
|
|
#define PPC_BPF_STL(r, base, i) do { \
|
|
if ((i) % 4) { \
|
|
EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\
|
|
EMIT(PPC_RAW_STDX(r, base, \
|
|
b2p[TMP_REG_2])); \
|
|
} else \
|
|
EMIT(PPC_RAW_STD(r, base, i)); \
|
|
} while(0)
|
|
#define PPC_BPF_STLU(r, base, i) do { EMIT(PPC_RAW_STDU(r, base, i)); } while(0)
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#endif
|