7caa976546
This commit replaces riscv's support for FTRACE_WITH_REGS with support
for FTRACE_WITH_ARGS. This is required for the ongoing effort to stop
relying on stop_machine() for RISCV's implementation of ftrace.
The main relevant benefit that this change will bring for the above
use-case is that now we don't have separate ftrace_caller and
ftrace_regs_caller trampolines. This will allow the callsite to call
ftrace_caller by modifying a single instruction. Now the callsite can
do something similar to:
When not tracing: | When tracing:
func: func:
auipc t0, ftrace_caller_top auipc t0, ftrace_caller_top
nop <=========<Enable/Disable>=========> jalr t0, ftrace_caller_bottom
[...] [...]
The above assumes that we are dropping the support of calling a direct
trampoline from the callsite. We need to drop this as the callsite can't
change the target address to call, it can only enable/disable a call to
a preset target (ftrace_caller in the above diagram). We can later optimize
this by calling an intermediate dispatcher trampoline before ftrace_caller.
Currently, ftrace_regs_caller saves all CPU registers in the format of
struct pt_regs and allows the tracer to modify them. We don't need to
save all of the CPU registers because at function entry only a subset of
pt_regs is live:
|----------+----------+---------------------------------------------|
| Register | ABI Name | Description |
|----------+----------+---------------------------------------------|
| x1 | ra | Return address for traced function |
| x2 | sp | Stack pointer |
| x5 | t0 | Return address for ftrace_caller trampoline |
| x8 | s0/fp | Frame pointer |
| x10-11 | a0-1 | Function arguments/return values |
| x12-17 | a2-7 | Function arguments |
|----------+----------+---------------------------------------------|
See RISCV calling convention[1] for the above table.
Saving just the live registers decreases the amount of stack space
required from 288 Bytes to 112 Bytes.
Basic testing was done with this on the VisionFive 2 development board.
Note:
- Moving from REGS to ARGS will mean that RISCV will stop supporting
KPROBES_ON_FTRACE as it requires full pt_regs to be saved.
- KPROBES_ON_FTRACE will be supplanted by FPROBES see [2].
[1] https://riscv.org/wp-content/uploads/2015/01/riscv-calling.pdf
[2] https://lore.kernel.org/all/170887410337.564249.6360118840946697039.stgit@devnote2/
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20240405142453.4187-1-puranjay@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
192 lines
4.3 KiB
ArmAsm
192 lines
4.3 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright (C) 2017 Andes Technology Corporation */
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/export.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/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_ARGS
|
|
|
|
/**
|
|
* SAVE_ABI_REGS - save regs against the ftrace_regs struct
|
|
*
|
|
* After the stack is established,
|
|
*
|
|
* 0(sp) stores the PC of the traced function which can be accessed
|
|
* by &(fregs)->epc in tracing function. Note that the real
|
|
* function entry address should be computed with -FENTRY_RA_OFFSET.
|
|
*
|
|
* 8(sp) stores the function return address (i.e. parent IP) that
|
|
* can be accessed by &(fregs)->ra in tracing function.
|
|
*
|
|
* The other regs are saved at the respective localtion and accessed
|
|
* by the respective ftrace_regs member.
|
|
*
|
|
* Here is the layout of stack for your reference.
|
|
*
|
|
* PT_SIZE_ON_STACK -> +++++++++
|
|
* + ..... +
|
|
* + a0-a7 + --++++-> ftrace_caller saved
|
|
* + t1 + --++++-> direct tramp address
|
|
* + s0 + --+ // frame pointer
|
|
* + sp + +
|
|
* + ra + --+ // parent IP
|
|
* sp -> + epc + --+ // PC
|
|
* +++++++++
|
|
**/
|
|
.macro SAVE_ABI_REGS
|
|
mv t4, sp // Save original SP in T4
|
|
addi sp, sp, -FREGS_SIZE_ON_STACK
|
|
|
|
REG_S t0, FREGS_EPC(sp)
|
|
REG_S x1, FREGS_RA(sp)
|
|
REG_S t4, FREGS_SP(sp) // Put original SP on stack
|
|
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
|
|
REG_S x8, FREGS_S0(sp)
|
|
#endif
|
|
REG_S x6, FREGS_T1(sp)
|
|
|
|
// save the arguments
|
|
REG_S x10, FREGS_A0(sp)
|
|
REG_S x11, FREGS_A1(sp)
|
|
REG_S x12, FREGS_A2(sp)
|
|
REG_S x13, FREGS_A3(sp)
|
|
REG_S x14, FREGS_A4(sp)
|
|
REG_S x15, FREGS_A5(sp)
|
|
REG_S x16, FREGS_A6(sp)
|
|
REG_S x17, FREGS_A7(sp)
|
|
.endm
|
|
|
|
.macro RESTORE_ABI_REGS, all=0
|
|
REG_L t0, FREGS_EPC(sp)
|
|
REG_L x1, FREGS_RA(sp)
|
|
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
|
|
REG_L x8, FREGS_S0(sp)
|
|
#endif
|
|
REG_L x6, FREGS_T1(sp)
|
|
|
|
// restore the arguments
|
|
REG_L x10, FREGS_A0(sp)
|
|
REG_L x11, FREGS_A1(sp)
|
|
REG_L x12, FREGS_A2(sp)
|
|
REG_L x13, FREGS_A3(sp)
|
|
REG_L x14, FREGS_A4(sp)
|
|
REG_L x15, FREGS_A5(sp)
|
|
REG_L x16, FREGS_A6(sp)
|
|
REG_L x17, FREGS_A7(sp)
|
|
|
|
addi sp, sp, FREGS_SIZE_ON_STACK
|
|
.endm
|
|
|
|
.macro PREPARE_ARGS
|
|
addi a0, t0, -FENTRY_RA_OFFSET
|
|
la a1, function_trace_op
|
|
REG_L a2, 0(a1)
|
|
mv a1, ra
|
|
mv a3, sp
|
|
.endm
|
|
|
|
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
|
|
|
|
#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
|
|
SYM_FUNC_START(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
|
|
|
|
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
|
|
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
|
|
SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
|
|
call ftrace_stub
|
|
#endif
|
|
RESTORE_ABI
|
|
jr t0
|
|
SYM_FUNC_END(ftrace_caller)
|
|
|
|
#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
|
|
SYM_FUNC_START(ftrace_caller)
|
|
mv t1, zero
|
|
SAVE_ABI_REGS
|
|
PREPARE_ARGS
|
|
|
|
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
|
|
call ftrace_stub
|
|
|
|
RESTORE_ABI_REGS
|
|
bnez t1, .Ldirect
|
|
jr t0
|
|
.Ldirect:
|
|
jr t1
|
|
SYM_FUNC_END(ftrace_caller)
|
|
|
|
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
|
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
|
|
SYM_CODE_START(ftrace_stub_direct_tramp)
|
|
jr t0
|
|
SYM_CODE_END(ftrace_stub_direct_tramp)
|
|
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
|