mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 12:45:16 +07:00
b7b7013cac
In line with similar support for other architectures by Daniel Borkmann. 'MOD Default X' from test_bpf without constant blinding: 84 bytes emitted from JIT compiler (pass:3, flen:7) d0000000058a4688 + <x>: 0: nop 4: nop 8: std r27,-40(r1) c: std r28,-32(r1) 10: xor r8,r8,r8 14: xor r28,r28,r28 18: mr r27,r3 1c: li r8,66 20: cmpwi r28,0 24: bne 0x0000000000000030 28: li r8,0 2c: b 0x0000000000000044 30: divwu r9,r8,r28 34: mullw r9,r28,r9 38: subf r8,r9,r8 3c: rotlwi r8,r8,0 40: li r8,66 44: ld r27,-40(r1) 48: ld r28,-32(r1) 4c: mr r3,r8 50: blr ... and with constant blinding: 140 bytes emitted from JIT compiler (pass:3, flen:11) d00000000bd6ab24 + <x>: 0: nop 4: nop 8: std r27,-40(r1) c: std r28,-32(r1) 10: xor r8,r8,r8 14: xor r28,r28,r28 18: mr r27,r3 1c: lis r2,-22834 20: ori r2,r2,36083 24: rotlwi r2,r2,0 28: xori r2,r2,36017 2c: xoris r2,r2,42702 30: rotlwi r2,r2,0 34: mr r8,r2 38: rotlwi r8,r8,0 3c: cmpwi r28,0 40: bne 0x000000000000004c 44: li r8,0 48: b 0x000000000000007c 4c: divwu r9,r8,r28 50: mullw r9,r28,r9 54: subf r8,r9,r8 58: rotlwi r8,r8,0 5c: lis r2,-17137 60: ori r2,r2,39065 64: rotlwi r2,r2,0 68: xori r2,r2,39131 6c: xoris r2,r2,48399 70: rotlwi r2,r2,0 74: mr r8,r2 78: rotlwi r8,r8,0 7c: ld r27,-40(r1) 80: ld r28,-32(r1) 84: mr r3,r8 88: blr Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
111 lines
2.9 KiB
C
111 lines
2.9 KiB
C
/*
|
|
* bpf_jit64.h: BPF JIT compiler for PPC64
|
|
*
|
|
* Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
|
|
* IBM Corporation
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; version 2
|
|
* of the License.
|
|
*/
|
|
#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 ] 8*8 |
|
|
* [ tail_call_cnt ] 8 |
|
|
* [ local_tmp_var ] 8 |
|
|
* fp (r31) --> [ ebpf stack space ] 512 |
|
|
* [ frame header ] 32/112 |
|
|
* sp (r1) ---> [ stack pointer ] --------------
|
|
*/
|
|
|
|
/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */
|
|
#define BPF_PPC_STACK_SAVE (8*8)
|
|
/* for bpf JIT code internal usage */
|
|
#define BPF_PPC_STACK_LOCALS 16
|
|
/* Ensure this is quadword aligned */
|
|
#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + MAX_BPF_STACK + \
|
|
BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
/* BPF register usage */
|
|
#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 0)
|
|
#define SKB_DATA_REG (MAX_BPF_JIT_REG + 1)
|
|
#define TMP_REG_1 (MAX_BPF_JIT_REG + 2)
|
|
#define TMP_REG_2 (MAX_BPF_JIT_REG + 3)
|
|
|
|
/* BPF to ppc register mappings */
|
|
static const int b2p[] = {
|
|
/* 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,
|
|
[SKB_HLEN_REG] = 25,
|
|
[SKB_DATA_REG] = 26,
|
|
[TMP_REG_1] = 9,
|
|
[TMP_REG_2] = 10
|
|
};
|
|
|
|
/* PPC NVR range -- update this if we ever use NVRs below r24 */
|
|
#define BPF_PPC_NVR_MIN 24
|
|
|
|
/* Assembly helpers */
|
|
#define DECLARE_LOAD_FUNC(func) u64 func(u64 r3, u64 r4); \
|
|
u64 func##_negative_offset(u64 r3, u64 r4); \
|
|
u64 func##_positive_offset(u64 r3, u64 r4);
|
|
|
|
DECLARE_LOAD_FUNC(sk_load_word);
|
|
DECLARE_LOAD_FUNC(sk_load_half);
|
|
DECLARE_LOAD_FUNC(sk_load_byte);
|
|
|
|
#define CHOOSE_LOAD_FUNC(imm, func) \
|
|
(imm < 0 ? \
|
|
(imm >= SKF_LL_OFF ? func##_negative_offset : func) : \
|
|
func##_positive_offset)
|
|
|
|
#define SEEN_FUNC 0x1000 /* might call external helpers */
|
|
#define SEEN_STACK 0x2000 /* uses BPF stack */
|
|
#define SEEN_SKB 0x4000 /* uses sk_buff */
|
|
#define SEEN_TAILCALL 0x8000 /* uses tail calls */
|
|
|
|
struct codegen_context {
|
|
/*
|
|
* This is used to track register usage as well
|
|
* as calls to external helpers.
|
|
* - register usage is tracked with corresponding
|
|
* bits (r3-r10 and r25-r31)
|
|
* - rest of the bits can be used to track other
|
|
* things -- for now, we use bits 16 to 23
|
|
* encoded in SEEN_* macros above
|
|
*/
|
|
unsigned int seen;
|
|
unsigned int idx;
|
|
};
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#endif
|