linux/arch/riscv/kernel/mcount-dyn.S
Guo Ren 71f81b6842 riscv: ftrace: Reduce the detour code size to half
commit 6724a76cff upstream.

Use a temporary register to reduce the size of detour code from 16 bytes to
8 bytes. The previous implementation is from 'commit afc76b8b80 ("riscv:
Using PATCHABLE_FUNCTION_ENTRY instead of MCOUNT")'.

Before the patch:
<func_prolog>:
 0: REG_S  ra, -SZREG(sp)
 4: auipc  ra, ?
 8: jalr   ?(ra)
12: REG_L  ra, -SZREG(sp)
 (func_boddy)

After the patch:
<func_prolog>:
 0: auipc  t0, ?
 4: jalr   t0, ?(t0)
 (func_boddy)

This patch not just reduces the size of detour code, but also fixes an
important issue:

An Ftrace callback registered with FTRACE_OPS_FL_IPMODIFY flag can
actually change the instruction pointer, e.g. to "replace" the given
kernel function with a new one, which is needed for livepatching, etc.

In this case, the trampoline (ftrace_regs_caller) would not return to
<func_prolog+12> but would rather jump to the new function. So, "REG_L
ra, -SZREG(sp)" would not run and the original return address would not
be restored. The kernel is likely to hang or crash as a result.

This can be easily demonstrated if one tries to "replace", say,
cmdline_proc_show() with a new function with the same signature using
instruction_pointer_set(&fregs->regs, new_func_addr) in the Ftrace
callback.

Link: https://lore.kernel.org/linux-riscv/20221122075440.1165172-1-suagrfillet@gmail.com/
Link: https://lore.kernel.org/linux-riscv/d7d5730b-ebef-68e5-5046-e763e1ee6164@yadro.com/
Co-developed-by: Song Shuai <suagrfillet@gmail.com>
Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Evgenii Shatokhin <e.shatokhin@yadro.com>
Reviewed-by: Evgenii Shatokhin <e.shatokhin@yadro.com>
Link: https://lore.kernel.org/r/20230112090603.1295340-4-guoren@kernel.org
Cc: stable@vger.kernel.org
Fixes: 10626c32e3 ("riscv/ftrace: Add basic support")
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-03-10 09:40:12 +01:00

192 lines
3.7 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (C) 2017 Andes Technology Corporation */
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/asm.h>
#include <asm/csr.h>
#include <asm/unistd.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#include <asm-generic/export.h>
#include <asm/ftrace.h>
.text
#define FENTRY_RA_OFFSET 8
#define ABI_SIZE_ON_STACK 80
#define ABI_A0 0
#define ABI_A1 8
#define ABI_A2 16
#define ABI_A3 24
#define ABI_A4 32
#define ABI_A5 40
#define ABI_A6 48
#define ABI_A7 56
#define ABI_T0 64
#define ABI_RA 72
.macro SAVE_ABI
addi sp, sp, -ABI_SIZE_ON_STACK
REG_S a0, ABI_A0(sp)
REG_S a1, ABI_A1(sp)
REG_S a2, ABI_A2(sp)
REG_S a3, ABI_A3(sp)
REG_S a4, ABI_A4(sp)
REG_S a5, ABI_A5(sp)
REG_S a6, ABI_A6(sp)
REG_S a7, ABI_A7(sp)
REG_S t0, ABI_T0(sp)
REG_S ra, ABI_RA(sp)
.endm
.macro RESTORE_ABI
REG_L a0, ABI_A0(sp)
REG_L a1, ABI_A1(sp)
REG_L a2, ABI_A2(sp)
REG_L a3, ABI_A3(sp)
REG_L a4, ABI_A4(sp)
REG_L a5, ABI_A5(sp)
REG_L a6, ABI_A6(sp)
REG_L a7, ABI_A7(sp)
REG_L t0, ABI_T0(sp)
REG_L ra, ABI_RA(sp)
addi sp, sp, ABI_SIZE_ON_STACK
.endm
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
.macro SAVE_ALL
addi sp, sp, -PT_SIZE_ON_STACK
REG_S t0, PT_EPC(sp)
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)
.endm
.macro RESTORE_ALL
REG_L t0, PT_EPC(sp)
REG_L x1, PT_RA(sp)
REG_L x2, PT_SP(sp)
REG_L x3, PT_GP(sp)
REG_L x4, PT_TP(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)
addi sp, sp, PT_SIZE_ON_STACK
.endm
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
ENTRY(ftrace_caller)
SAVE_ABI
addi a0, t0, -FENTRY_RA_OFFSET
la a1, function_trace_op
REG_L a2, 0(a1)
mv a1, ra
mv a3, sp
ftrace_call:
.global ftrace_call
call ftrace_stub
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
addi a0, sp, ABI_RA
REG_L a1, ABI_T0(sp)
addi a1, a1, -FENTRY_RA_OFFSET
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
mv a2, s0
#endif
ftrace_graph_call:
.global ftrace_graph_call
call ftrace_stub
#endif
RESTORE_ABI
jr t0
ENDPROC(ftrace_caller)
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
ENTRY(ftrace_regs_caller)
SAVE_ALL
addi a0, t0, -FENTRY_RA_OFFSET
la a1, function_trace_op
REG_L a2, 0(a1)
mv a1, ra
mv a3, sp
ftrace_regs_call:
.global ftrace_regs_call
call ftrace_stub
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
addi a0, sp, PT_RA
REG_L a1, PT_EPC(sp)
addi a1, a1, -FENTRY_RA_OFFSET
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
mv a2, s0
#endif
ftrace_graph_regs_call:
.global ftrace_graph_regs_call
call ftrace_stub
#endif
RESTORE_ALL
jr t0
ENDPROC(ftrace_regs_caller)
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */