[PATCH v5 7/9] riscv/kprobe: Prepare detour buffer for optimized kprobe

[Björn Töpel]

Chen Guokai <chenguokai17 at mails.ucas.ac.cn> writes:

> From: Liao Chang <liaochang1 at huawei.com>

> diff --git a/arch/riscv/kernel/probes/opt.c b/arch/riscv/kernel/probes/opt.c
> index 258a283c906d..bc232fce5b39 100644
> --- a/arch/riscv/kernel/probes/opt.c
> +++ b/arch/riscv/kernel/probes/opt.c
> @@ -11,9 +11,37 @@
>  #include <linux/kprobes.h>
>  #include <asm/kprobes.h>
>  #include <asm/patch.h>
> +#include <asm/asm-offsets.h>
>  
>  #include "simulate-insn.h"
>  #include "decode-insn.h"
> +#include "../../net/bpf_jit.h"
> +
> +static void

Super-nit, but I really prefer *not* breaking function name and return
value, for grepability.

> diff --git a/arch/riscv/kernel/probes/opt_trampoline.S b/arch/riscv/kernel/probes/opt_trampoline.S
> index 16160c4367ff..75e34e373cf2 100644
> --- a/arch/riscv/kernel/probes/opt_trampoline.S
> +++ b/arch/riscv/kernel/probes/opt_trampoline.S
> @@ -1,12 +1,137 @@
>  /* SPDX-License-Identifier: GPL-2.0-only */
>  /*
>   * Copyright (C) 2022 Guokai Chen
> + * Copyright (C) 2022 Liao, Chang <liaochang1 at huawei.com>
>   */
>  
>  #include <linux/linkage.h>
>  
> +#include <asm/asm.h>
>  #incldue <asm/csr.h>
>  #include <asm/asm-offsets.h>
>  
>  SYM_ENTRY(optprobe_template_entry, SYM_L_GLOBAL, SYM_A_NONE)
> +	addi  sp, sp, -(PT_SIZE_ON_STACK)
> +	REG_S x1,  PT_RA(sp)
> +	REG_S x2,  PT_SP(sp)
> +	REG_S x3,  PT_GP(sp)
> +	REG_S x4,  PT_TP(sp)
> +	REG_S x5,  PT_T0(sp)
> +	REG_S x6,  PT_T1(sp)
> +	REG_S x7,  PT_T2(sp)
> +	REG_S x8,  PT_S0(sp)
> +	REG_S x9,  PT_S1(sp)
> +	REG_S x10, PT_A0(sp)
> +	REG_S x11, PT_A1(sp)
> +	REG_S x12, PT_A2(sp)
> +	REG_S x13, PT_A3(sp)
> +	REG_S x14, PT_A4(sp)
> +	REG_S x15, PT_A5(sp)
> +	REG_S x16, PT_A6(sp)
> +	REG_S x17, PT_A7(sp)
> +	REG_S x18, PT_S2(sp)
> +	REG_S x19, PT_S3(sp)
> +	REG_S x20, PT_S4(sp)
> +	REG_S x21, PT_S5(sp)
> +	REG_S x22, PT_S6(sp)
> +	REG_S x23, PT_S7(sp)
> +	REG_S x24, PT_S8(sp)
> +	REG_S x25, PT_S9(sp)
> +	REG_S x26, PT_S10(sp)
> +	REG_S x27, PT_S11(sp)
> +	REG_S x28, PT_T3(sp)
> +	REG_S x29, PT_T4(sp)
> +	REG_S x30, PT_T5(sp)
> +	REG_S x31, PT_T6(sp)
> +	/* Update fp is friendly for stacktrace */
> +	addi  s0, sp, (PT_SIZE_ON_STACK)
> +	j 1f
> +
> +SYM_ENTRY(optprobe_template_save, SYM_L_GLOBAL, SYM_A_NONE)
> +	/*
> +	 * Step1:
> +	 * Filled with the pointer to optimized_kprobe data
> +	 */
> +	.dword 0
> +1:
> +	/* Load optimize_kprobe pointer from .dword below */
> +	auipc a0, 0
> +	REG_L a0, -8(a0)
> +	add   a1, sp, x0
> +
> +SYM_ENTRY(optprobe_template_call, SYM_L_GLOBAL, SYM_A_NONE)
> +	/*
> +	 * Step2:
> +	 * <IMME> of AUIPC/JALR are modified to the offset to optimized_callback
> +	 * jump target is loaded from above .dword.
> +	 */
> +	auipc ra, 0
> +	jalr  ra, 0(ra)
> +
> +	REG_L x1,  PT_RA(sp)
> +	REG_L x3,  PT_GP(sp)
> +	REG_L x4,  PT_TP(sp)
> +	REG_L x5,  PT_T0(sp)
> +	REG_L x6,  PT_T1(sp)
> +	REG_L x7,  PT_T2(sp)
> +	REG_L x8,  PT_S0(sp)
> +	REG_L x9,  PT_S1(sp)
> +	REG_L x10, PT_A0(sp)
> +	REG_L x11, PT_A1(sp)
> +	REG_L x12, PT_A2(sp)
> +	REG_L x13, PT_A3(sp)
> +	REG_L x14, PT_A4(sp)
> +	REG_L x15, PT_A5(sp)
> +	REG_L x16, PT_A6(sp)
> +	REG_L x17, PT_A7(sp)
> +	REG_L x18, PT_S2(sp)
> +	REG_L x19, PT_S3(sp)
> +	REG_L x20, PT_S4(sp)
> +	REG_L x21, PT_S5(sp)
> +	REG_L x22, PT_S6(sp)
> +	REG_L x23, PT_S7(sp)
> +	REG_L x24, PT_S8(sp)
> +	REG_L x25, PT_S9(sp)
> +	REG_L x26, PT_S10(sp)
> +	REG_L x27, PT_S11(sp)
> +	REG_L x28, PT_T3(sp)
> +	REG_L x29, PT_T4(sp)
> +	REG_L x30, PT_T5(sp)
> +	REG_L x31, PT_T6(sp)
> +	REG_L x2,  PT_SP(sp)
> +	addi  sp, sp, (PT_SIZE_ON_STACK)
> +
> +SYM_ENTRY(optprobe_template_insn, SYM_L_GLOBAL, SYM_A_NONE)
> +	/*
> +	 * Step3:
> +	 * NOPS will be replaced by the probed instruction, at worst case 3 RVC
> +	 * and 1 RVI instructions is about to execute out of line.
> +	 */
> +	nop

A nop here will be either a compressed nop or a non-compressed,
depending on the build (C-enabled or not), right? Maybe be explicit to
the assembler what you want?


Björn